[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-daymade--claude-code-skills":3,"tool-daymade--claude-code-skills":64},[4,17,25,39,48,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",140436,2,"2026-04-05T23:32:43",[13,14,15],"开发框架","Agent","语言模型","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":10,"last_commit_at":23,"category_tags":24,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,15],{"id":26,"name":27,"github_repo":28,"description_zh":29,"stars":30,"difficulty_score":10,"last_commit_at":31,"category_tags":32,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[33,34,35,36,14,37,15,13,38],"图像","数据工具","视频","插件","其他","音频",{"id":40,"name":41,"github_repo":42,"description_zh":43,"stars":44,"difficulty_score":45,"last_commit_at":46,"category_tags":47,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,3,"2026-04-04T04:44:48",[14,33,13,15,37],{"id":49,"name":50,"github_repo":51,"description_zh":52,"stars":53,"difficulty_score":45,"last_commit_at":54,"category_tags":55,"status":16},519,"PaddleOCR","PaddlePaddle\u002FPaddleOCR","PaddleOCR 是一款基于百度飞桨框架开发的高性能开源光学字符识别工具包。它的核心能力是将图片、PDF 等文档中的文字提取出来，转换成计算机可读取的结构化数据，让机器真正“看懂”图文内容。\n\n面对海量纸质或电子文档，PaddleOCR 解决了人工录入效率低、数字化成本高的问题。尤其在人工智能领域，它扮演着连接图像与大型语言模型（LLM）的桥梁角色，能将视觉信息直接转化为文本输入，助力智能问答、文档分析等应用场景落地。\n\nPaddleOCR 适合开发者、算法研究人员以及有文档自动化需求的普通用户。其技术优势十分明显：不仅支持全球 100 多种语言的识别，还能在 Windows、Linux、macOS 等多个系统上运行，并灵活适配 CPU、GPU、NPU 等各类硬件。作为一个轻量级且社区活跃的开源项目，PaddleOCR 既能满足快速集成的需求，也能支撑前沿的视觉语言研究，是处理文字识别任务的理想选择。",74939,"2026-04-05T23:16:38",[15,33,13,37],{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":45,"last_commit_at":62,"category_tags":63,"status":16},2181,"OpenHands","OpenHands\u002FOpenHands","OpenHands 是一个专注于 AI 驱动开发的开源平台，旨在让智能体（Agent）像人类开发者一样理解、编写和调试代码。它解决了传统编程中重复性劳动多、环境配置复杂以及人机协作效率低等痛点，通过自动化流程显著提升开发速度。\n\n无论是希望提升编码效率的软件工程师、探索智能体技术的研究人员，还是需要快速原型验证的技术团队，都能从中受益。OpenHands 提供了灵活多样的使用方式：既可以通过命令行（CLI）或本地图形界面在个人电脑上轻松上手，体验类似 Devin 的流畅交互；也能利用其强大的 Python SDK 自定义智能体逻辑，甚至在云端大规模部署上千个智能体并行工作。\n\n其核心技术亮点在于模块化的软件智能体 SDK，这不仅构成了平台的引擎，还支持高度可组合的开发模式。此外，OpenHands 在 SWE-bench 基准测试中取得了 77.6% 的优异成绩，证明了其解决真实世界软件工程问题的能力。平台还具备完善的企业级功能，支持与 Slack、Jira 等工具集成，并提供细粒度的权限管理，适合从个人开发者到大型企业的各类用户场景。",70626,"2026-04-05T22:51:36",[15,14,13,36],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":76,"owner_location":79,"owner_email":76,"owner_twitter":76,"owner_website":80,"owner_url":81,"languages":82,"stars":111,"forks":112,"last_commit_at":113,"license":114,"difficulty_score":115,"env_os":116,"env_gpu":117,"env_ram":117,"env_deps":118,"category_tags":125,"github_topics":76,"view_count":10,"oss_zip_url":76,"oss_zip_packed_at":76,"status":16,"created_at":126,"updated_at":127,"faqs":128,"releases":129},4012,"daymade\u002Fclaude-code-skills","claude-code-skills","Professional Claude Code skills marketplace featuring production-ready skills for enhanced development workflows.","claude-code-skills 是一个专为 Claude Code 打造的专业技能市场，汇集了 43 个经过生产环境验证的实用技能，旨在显著提升开发工作流的效率。它核心解决了开发者在扩展 AI 编程能力时面临的痛点：官方工具往往只告知“做什么”，而缺乏对潜在陷阱和最佳实践的指引。\n\n该项目特别提供了一个名为\"skill-creator\"的核心元技能，帮助用户从零开始构建、验证并打包属于自己的定制化技能。与官方版本相比，它不仅提供操作指南，更内置了防错机制，包括前置依赖检查、架构选择决策树以及集成安全扫描功能，能有效避免常见的配置错误和安全漏洞。通过结构化的交互流程和详尽的失败案例库，它让技能开发过程更加稳健可靠。\n\n这款工具非常适合希望深度定制 AI 编程助手的软件开发者、技术团队以及高级极客用户。无论你是想直接复用现成的高效工作流，还是渴望创建符合特定业务场景的专属技能，claude-code-skills 都能提供从灵感探索到安全交付的全链路支持，让扩展 Claude Code 的能力变得简单且专业。","# Claude Code Skills Marketplace\n\n\u003Cdiv align=\"center\">\n\n[![English](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLanguage-English-blue)](.\u002FREADME.md)\n[![简体中文](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F语言-简体中文-red)](.\u002FREADME.zh-CN.md)\n\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n[![Skills](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fskills-43-blue.svg)](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills)\n[![Version](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fversion-1.39.0-green.svg)](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills)\n[![Claude Code](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClaude%20Code-2.0.13+-purple.svg)](https:\u002F\u002Fclaude.com\u002Fcode)\n[![PRs Welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg)](.\u002FCONTRIBUTING.md)\n[![Maintenance](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMaintained%3F-yes-green.svg)](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\u002Fgraphs\u002Fcommit-activity)\n\n\u003C\u002Fdiv>\n\nProfessional Claude Code skills marketplace featuring 43 production-ready skills for enhanced development workflows.\n\n## 📑 Table of Contents\n\n- [🌟 Essential Skill: skill-creator](#-essential-skill-skill-creator)\n- [🚀 Quick Installation](#-quick-installation)\n- [🇨🇳 Chinese User Guide](#-chinese-user-guide)\n- [📦 Other Available Skills](#-other-available-skills)\n- [🎬 Interactive Demo Gallery](#-interactive-demo-gallery)\n- [🎯 Use Cases](#-use-cases)\n- [📚 Documentation](#-documentation)\n- [🛠️ Requirements](#️-requirements)\n- [❓ FAQ](#-faq)\n- [🤝 Contributing](#-contributing)\n- [📄 License](#-license)\n\n---\n\n## 🌟 Essential Skill: skill-creator\n\n**⭐ Start here if you want to create your own skills!**\n\nThe `skill-creator` is the **meta-skill** that enables you to build, validate, and package your own Claude Code skills. It's the most important tool in this marketplace because it empowers you to extend Claude Code with your own specialized workflows.\n\n### Why This skill-creator?\n\nThis is a **production-hardened fork** of [Anthropic's official skill-creator](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fskill-creator), born from building real skills and hitting every wall the official version doesn't warn you about.\n\n**The official skill-creator tells you _what_ to build. Ours also tells you _what not to try_ — and why.**\n\n| You're trying to... | Official | This Fork |\n|---------------------|----------|-----------|\n| Research before building | \"Check available MCPs\" (5 lines) | 8-channel search protocol with decision matrix: Adopt \u002F Extend \u002F Build |\n| Create a skill interactively | Prose-based instructions | 9 structured AskUserQuestion checkpoints — user never loses context |\n| Avoid common mistakes | No guidance | Cache edit warnings, prerequisite checks, security scan gate |\n| Know the architecture options | Not mentioned | Inline vs Fork decision guide with examples (choosing wrong silently breaks your skill) |\n| Validate before shipping | Basic YAML check | Expanded validator (all frontmatter fields, path reference integrity, whitespace issues) |\n| Catch security issues | No tooling | `security_scan.py` with gitleaks integration — hard gate before packaging |\n| Learn from real failures | No failure cases | Battle-tested methodology with documented failure patterns and gotchas |\n\n**Quality comparison** (independent audit, 8 dimensions):\n\n| Dimension | Official | This Fork |\n|-----------|----------|-----------|\n| Actionability | 7 | 9 |\n| Error Prevention | 5 | 9 |\n| Prior Art Research | 4 | 9 |\n| Counter Review Process | 4 | 8 |\n| Real-World Lessons | 3 | 8 |\n| User Experience | 4 | 9 |\n| **Total (out of 80)** | **42** | **65** |\n\n> Full methodology: [skill-creator\u002Freferences\u002Fskill-development-methodology.md](.\u002Fskill-creator\u002Freferences\u002Fskill-development-methodology.md)\n\n### Quick Install\n\n**In Claude Code (in-app):**\n```text\n\u002Fplugin marketplace add daymade\u002Fclaude-code-skills\n```\n\nThen:\n1. Select **Browse and install plugins**\n2. Select **daymade\u002Fclaude-code-skills**\n3. Select **skill-creator**\n4. Select **Install now**\n\n**From your terminal (CLI):**\n```bash\nclaude plugin marketplace add https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\n# Marketplace name: daymade-skills (from marketplace.json)\nclaude plugin install skill-creator@daymade-skills\n```\n\n### What You Can Do\n\nAfter installing skill-creator, simply ask Claude Code:\n\n```\n\"Create a new skill called my-awesome-skill in ~\u002Fmy-skills\"\n\n\"Validate my skill at ~\u002Fmy-skills\u002Fmy-awesome-skill\"\n\n\"Package my skill at ~\u002Fmy-skills\u002Fmy-awesome-skill for distribution\"\n```\n\nClaude Code, with skill-creator loaded, will guide you through the entire skill creation process - from understanding your requirements to packaging the final skill.\n\n📚 **Full documentation**: [skill-creator\u002FSKILL.md](.\u002Fskill-creator\u002FSKILL.md)\n\n### Live Demos\n\n**📝 Initialize New Skill**\n\n![Initialize Skill Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_1c2c4748b423.gif)\n\n**✅ Validate Skill Structure**\n\n![Validate Skill Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_e1a9b3ad3859.gif)\n\n**📦 Package Skill for Distribution**\n\n![Package Skill Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_c9de46d4576a.gif)\n\n---\n\n## 🚀 Quick Installation\n\n### Install Inside Claude Code (In-App)\n\n```text\n\u002Fplugin marketplace add daymade\u002Fclaude-code-skills\n```\n\nThen:\n1. Select **Browse and install plugins**\n2. Select **daymade\u002Fclaude-code-skills**\n3. Select the plugin you want\n4. Select **Install now**\n\n### Automated Installation (Recommended)\n\n**macOS\u002FLinux:**\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fdaymade\u002Fclaude-code-skills\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n```\n\n**Windows (PowerShell):**\n```powershell\niwr -useb https:\u002F\u002Fraw.githubusercontent.com\u002Fdaymade\u002Fclaude-code-skills\u002Fmain\u002Fscripts\u002Finstall.ps1 | iex\n```\n\n### Manual Installation\n\nAdd the marketplace:\n```bash\nclaude plugin marketplace add https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\n```\n\nMarketplace name is `daymade-skills` (from marketplace.json). Use `@daymade-skills` when installing plugins.\nDo not use the repo path as a marketplace name (e.g. `@daymade\u002Fclaude-code-skills` will fail).\nIn Claude Code, use `\u002Fplugin ...` slash commands. In your terminal, use `claude plugin ...`.\n\n**Essential Skill** (recommended first install):\n```bash\nclaude plugin install skill-creator@daymade-skills\n```\n\n**Install Other Skills:**\n```bash\n# GitHub operations\nclaude plugin install github-ops@daymade-skills\n\n# Document conversion\nclaude plugin install doc-to-markdown@daymade-skills\n\n# Diagram generation\nclaude plugin install mermaid-tools@daymade-skills\n\n# Statusline customization\nclaude plugin install statusline-generator@daymade-skills\n\n# Teams communication\nclaude plugin install teams-channel-post-writer@daymade-skills\n\n# Repomix extraction\nclaude plugin install repomix-unmixer@daymade-skills\n\n# AI\u002FLLM icons\nclaude plugin install llm-icon-finder@daymade-skills\n\n# CLI demo generation\nclaude plugin install cli-demo-generator@daymade-skills\n\n# Cloudflare diagnostics\nclaude plugin install cloudflare-troubleshooting@daymade-skills\n\n# UI design system extraction\nclaude plugin install ui-designer@daymade-skills\n\n# Presentation creation\nclaude plugin install ppt-creator@daymade-skills\n\n# YouTube video\u002Faudio downloading\nclaude plugin install youtube-downloader@daymade-skills\n\n# Secure repomix packaging\nclaude plugin install repomix-safe-mixer@daymade-skills\n\n# ASR transcript correction\nclaude plugin install transcript-fixer@daymade-skills\n\n# Video comparison and quality analysis\nclaude plugin install video-comparer@daymade-skills\n\n# QA testing infrastructure with autonomous execution\nclaude plugin install qa-expert@daymade-skills\n\n# Prompt optimization using EARS methodology\nclaude plugin install prompt-optimizer@daymade-skills\n\n# Session history recovery\nclaude plugin install claude-code-history-files-finder@daymade-skills\n\n# Documentation consolidation\nclaude plugin install docs-cleaner@daymade-skills\n\n# PDF generation with Chinese font support\nclaude plugin install pdf-creator@daymade-skills\n\n# CLAUDE.md progressive disclosure optimization\nclaude plugin install claude-md-progressive-disclosurer@daymade-skills\n\n# CCPM skill registry search and management\nclaude plugin install skills-search@daymade-skills\n\n# Promptfoo LLM evaluation framework\nclaude plugin install promptfoo-evaluation@daymade-skills\n\n# iOS app development\nclaude plugin install iOS-APP-developer@daymade-skills\n\n# Twitter\u002FX content fetching\nclaude plugin install twitter-reader@daymade-skills\n\n# Skill quality review and improvement\nclaude plugin install skill-reviewer@daymade-skills\n\n# GitHub contribution strategy\nclaude plugin install github-contributor@daymade-skills\n\n# Windows Remote Desktop \u002F AVD connection diagnosis\nclaude plugin install windows-remote-desktop-connection-doctor@daymade-skills\n\n# Product analysis and optimization\nclaude plugin install product-analysis@daymade-skills\n\n# Financial data collection for US equities\nclaude plugin install financial-data-collector@daymade-skills\n\n# Excel automation for creation, parsing, and macOS control\nclaude plugin install excel-automation@daymade-skills\n\n# Programmatic macOS screenshot capture workflows\nclaude plugin install capture-screen@daymade-skills\n\n# Resume interrupted Claude work from local session artifacts\nclaude plugin install continue-claude-work@daymade-skills\n\n# Scrapling CLI extraction and troubleshooting\nclaude plugin install scrapling-skill@daymade-skills\n```\n\nEach skill can be installed independently - choose only what you need!\n\n---\n\n## 🇨🇳 Chinese User Guide\n\n**For Chinese users:** We highly recommend using [CC-Switch](https:\u002F\u002Fgithub.com\u002Ffarion1231\u002Fcc-switch) to manage Claude Code API provider configurations.\n\nCC-Switch enables you to:\n- ✅ Quickly switch between different API providers (DeepSeek, Qwen, GLM, etc.)\n- ✅ Test endpoint response times to find the fastest provider\n- ✅ Manage MCP server configurations\n- ✅ Auto-backup and import\u002Fexport settings\n- ✅ Cross-platform support (Windows, macOS, Linux)\n\n**Setup:** Download from [Releases](https:\u002F\u002Fgithub.com\u002Ffarion1231\u002Fcc-switch\u002Freleases), install, add your API configs, and switch via UI or system tray.\n\n### Complete Chinese Documentation\n\nFor full documentation in Chinese, see [README.zh-CN.md](.\u002FREADME.zh-CN.md).\n\n---\n\n## 📦 Other Available Skills\n\n### 1. **github-ops** - GitHub Operations Suite\n\nComprehensive GitHub operations using gh CLI and GitHub API.\n\n**When to use:**\n- Creating, viewing, or managing pull requests\n- Managing issues and repository settings\n- Querying GitHub API endpoints\n- Working with GitHub Actions workflows\n- Automating GitHub operations\n\n**Key features:**\n- PR creation with JIRA integration\n- Issue management workflows\n- GitHub API (REST & GraphQL) operations\n- Workflow automation\n- Enterprise GitHub support\n\n**🎬 Live Demo**\n\n![GitHub Ops Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_65679b1ee583.gif)\n\n---\n\n### 2. **doc-to-markdown** - Document Conversion Suite\n\nConverts documents to markdown with Windows\u002FWSL path handling and PDF image extraction.\n\n**When to use:**\n- Converting .doc\u002F.docx\u002FPDF\u002FPPTX to markdown\n- Extracting images from PDF files\n- Processing Confluence exports\n- Handling Windows\u002FWSL path conversions\n\n**Key features:**\n- Multi-format document conversion\n- PDF image extraction using PyMuPDF\n- Windows\u002FWSL path automation\n- Confluence export processing\n- Helper scripts for path conversion and image extraction\n\n**🎬 Live Demo**\n\n![Markdown Tools Demo](.\u002Fdemos\u002Fdoc-to-markdown\u002Fconvert-docs.gif)\n\n---\n\n### 3. **mermaid-tools** - Diagram Generation\n\nExtracts Mermaid diagrams from markdown and generates high-quality PNG images.\n\n**When to use:**\n- Converting Mermaid diagrams to PNG\n- Extracting diagrams from markdown files\n- Processing documentation with embedded diagrams\n- Creating presentation-ready visuals\n\n**Key features:**\n- Automatic diagram extraction\n- High-resolution PNG generation\n- Smart sizing based on diagram type\n- Customizable dimensions and scaling\n- WSL2 Chrome\u002FPuppeteer support\n\n**🎬 Live Demo**\n\n![Mermaid Tools Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_14efada40ccf.gif)\n\n---\n\n### 4. **statusline-generator** - Statusline Customization\n\nConfigures Claude Code statuslines with multi-line layouts and cost tracking.\n\n**When to use:**\n- Customizing Claude Code statusline\n- Adding cost tracking (session\u002Fdaily)\n- Displaying git status\n- Multi-line layouts for narrow screens\n- Color customization\n\n**Key features:**\n- Multi-line statusline layouts\n- ccusage cost integration\n- Git branch status indicators\n- Customizable colors\n- Portrait screen optimization\n\n**🎬 Live Demo**\n\n![Statusline Generator Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_138d9a84c202.gif)\n\n---\n\n### 5. **teams-channel-post-writer** - Teams Communication\n\nCreates educational Teams channel posts for internal knowledge sharing.\n\n**When to use:**\n- Writing Teams posts about features\n- Sharing Claude Code best practices\n- Documenting lessons learned\n- Creating internal announcements\n- Teaching effective prompting patterns\n\n**Key features:**\n- Post templates with proven structure\n- Writing guidelines for quality content\n- \"Normal vs Better\" example patterns\n- Emphasis on underlying principles\n- Ready-to-use markdown templates\n\n**🎬 Live Demo**\n\n![Teams Channel Post Writer Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_e48d6082e10f.gif)\n\n---\n\n### 6. **repomix-unmixer** - Repository Extraction\n\nExtracts files from repomix-packed repositories and restores directory structures.\n\n**When to use:**\n- Unmixing repomix output files\n- Extracting packed repositories\n- Restoring file structures\n- Reviewing repomix content\n- Converting repomix to usable files\n\n**Key features:**\n- Multi-format support (XML, Markdown, JSON)\n- Auto-format detection\n- Directory structure preservation\n- UTF-8 encoding support\n- Comprehensive validation workflows\n\n**🎬 Live Demo**\n\n![Repomix Unmixer Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_fa124d5ae642.gif)\n\n---\n\n### 7. **llm-icon-finder** - AI\u002FLLM Brand Icon Finder\n\nAccess 100+ AI model and LLM provider brand icons from lobe-icons library.\n\n**When to use:**\n- Finding brand icons for AI models\u002Fproviders\n- Downloading logos for Claude, GPT, Gemini, etc.\n- Getting icons in multiple formats (SVG\u002FPNG\u002FWEBP)\n- Building AI tool documentation\n- Creating presentations about LLMs\n\n**Key features:**\n- 100+ AI\u002FLLM model icons\n- Multiple format support (SVG, PNG, WEBP)\n- URL generation for direct access\n- Local download capabilities\n- Searchable icon catalog\n\n**🎬 Live Demo**\n\n![LLM Icon Finder Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_ac372876ec88.gif)\n\n---\n\n### 8. **cli-demo-generator** - CLI Demo Generation\n\nGenerate professional animated CLI demos and terminal recordings with VHS automation.\n\n**When to use:**\n- Creating demos for documentation\n- Recording terminal workflows as GIFs\n- Generating animated tutorials\n- Batch-generating multiple demos\n- Showcasing CLI tools\n\n**Key features:**\n- Automated demo generation from command lists\n- Batch processing with YAML\u002FJSON configs\n- Interactive recording with asciinema\n- Smart timing based on command complexity\n- Multiple output formats (GIF, MP4, WebM)\n- VHS tape file templates\n\n**🎬 Live Demo**\n\n![CLI Demo Generator Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_1af0c07fd9d7.gif)\n\n---\n\n### 9. **cloudflare-troubleshooting** - Cloudflare Diagnostics\n\nInvestigate and resolve Cloudflare configuration issues using API-driven evidence gathering.\n\n**When to use:**\n- Site shows ERR_TOO_MANY_REDIRECTS\n- SSL\u002FTLS configuration errors\n- DNS resolution problems\n- Cloudflare-related issues\n\n**Key features:**\n- Evidence-based investigation methodology\n- Comprehensive Cloudflare API reference\n- SSL\u002FTLS mode troubleshooting (Flexible, Full, Strict)\n- DNS, cache, and firewall diagnostics\n- Agentic approach with optional helper scripts\n\n**🎬 Live Demo**\n\n![Cloudflare Troubleshooting Demo](.\u002Fdemos\u002Fcloudflare-troubleshooting\u002Fdiagnose-redirect-loop.gif)\n\n---\n\n### 10. **ui-designer** - UI Design System Extractor\n\nExtract design systems from reference UI images and generate implementation-ready design prompts.\n\n**When to use:**\n- Have UI screenshots\u002Fmockups to analyze\n- Need to extract color palettes, typography, spacing\n- Building MVP UI matching reference aesthetics\n- Creating consistent design systems\n- Generating multiple UI variations\n\n**Key features:**\n- Systematic design system extraction from images\n- Color palette, typography, component analysis\n- Interactive MVP PRD generation\n- Template-driven workflow (design system → PRD → implementation prompt)\n- Multi-variation UI generation (3 mobile, 2 web)\n- React + Tailwind CSS + Lucide icons\n\n**🎬 Live Demo**\n\n![UI Designer Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_158f7eb336a3.gif)\n\n---\n\n### 11. **ppt-creator** - Professional Presentation Creation\n\nCreate persuasive, audience-ready slide decks from topics or documents with data-driven charts and dual-format PPTX output.\n\n**When to use:**\n- Creating presentations, pitch decks, or keynotes\n- Need structured content with professional storytelling\n- Require data visualization and charts\n- Want complete PPTX files with speaker notes\n- Building business reviews or product pitches\n\n**Key features:**\n- Pyramid Principle structure (conclusion → reasons → evidence)\n- Assertion-evidence slide framework\n- Automatic data synthesis and chart generation (matplotlib)\n- Dual-path PPTX creation (Marp CLI + document-skills:pptx)\n- Complete orchestration: content → data → charts → PPTX with charts\n- 45-60 second speaker notes per slide\n- Quality scoring with auto-refinement (target: 75\u002F100)\n\n**🎬 Live Demo**\n\n![PPT Creator Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_a17295906e62.gif)\n\n---\n\n### 12. **youtube-downloader** - YouTube Video & Audio Downloader\n\nDownload YouTube videos and audio using yt-dlp with robust error handling and automatic workarounds for common issues.\n\n**When to use:**\n- Downloading YouTube videos or playlists\n- Extracting audio from YouTube videos as MP3\n- Experiencing yt-dlp download failures or nsig extraction errors\n- Need help with format selection or quality options\n- Working with YouTube content in regions with access restrictions\n\n**Key features:**\n- Auto PO Token provider (Docker-first, browser fallback) for high-quality access\n- Browser-cookie verification for “not a bot” prompts (privacy-friendly)\n- Audio-only download with MP3 conversion\n- Format listing and custom format selection\n- Output directory customization\n- Proxy-aware downloads for restricted environments\n\n**🎬 Live Demo**\n\n![YouTube Downloader Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_56856411bc65.gif)\n\n---\n\n### 13. **repomix-safe-mixer** - Secure Repomix Packaging\n\nSafely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing.\n\n**When to use:**\n- Packaging code with repomix for distribution or sharing\n- Creating reference packages from proprietary codebases\n- Security concerns about accidentally exposing credentials\n- Pre-commit security checks for hardcoded secrets\n- Auditing codebases for credential exposure\n\n**Key features:**\n- Detects 20+ credential patterns (AWS, Supabase, Stripe, OpenAI, etc.)\n- Scan → Report → Pack workflow with automatic blocking\n- Standalone security scanner for pre-commit hooks\n- Environment variable replacement guidance\n- JSON output for CI\u002FCD integration\n- Exclude patterns for false positive handling\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n---\n\n### 14. **transcript-fixer** - ASR Transcription Correction\n\nCorrect speech-to-text (ASR\u002FSTT) transcription errors through dictionary-based rules and AI-powered corrections with automatic pattern learning.\n\n**When to use:**\n- Correcting meeting notes, lecture recordings, or interview transcripts\n- Fixing Chinese\u002FEnglish homophone errors and technical terminology\n- Building domain-specific correction dictionaries\n- Improving transcript accuracy through iterative learning\n- Collaborating with teams on shared correction knowledge bases\n\n**Key features:**\n- Two-stage correction pipeline (dictionary + AI)\n- Automatic pattern detection and learning\n- Domain-specific dictionaries (general, embodied_ai, finance, medical)\n- SQLite-based correction repository\n- Team collaboration with import\u002Fexport\n- GLM API integration for AI corrections\n- Cost optimization through dictionary promotion\n\n**Example workflow:**\n```bash\n# Initialize and add corrections\nuv run scripts\u002Ffix_transcription.py --init\nuv run scripts\u002Ffix_transcription.py --add \"错误词\" \"正确词\" --domain general\n\n# Run full correction pipeline\nuv run scripts\u002Ffix_transcription.py --input meeting.md --stage 3\n\n# Review and approve learned patterns\nuv run scripts\u002Ffix_transcription.py --review-learned\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [transcript-fixer\u002Freferences\u002F](.\u002Ftranscript-fixer\u002Freferences\u002F) for workflow guides, SQL queries, troubleshooting, best practices, team collaboration, and API setup.\n\n**Requirements**: Python 3.6+, uv package manager, GLM API key (get from https:\u002F\u002Fopen.bigmodel.cn\u002F)\n\n---\n\n### 15. **video-comparer** - Video Comparison and Quality Analysis\n\nCompare two videos and generate interactive HTML reports with quality metrics and frame-by-frame visual comparisons.\n\n**When to use:**\n- Comparing original and compressed videos\n- Analyzing video compression quality and efficiency\n- Evaluating codec performance or bitrate reduction impact\n- Assessing before\u002Fafter compression results\n- Quality analysis for video encoding workflows\n\n**Key features:**\n- Quality metrics calculation (PSNR, SSIM)\n- Frame-by-frame visual comparison with three viewing modes:\n  - Slider mode: Drag to reveal differences\n  - Side-by-side mode: Simultaneous display\n  - Grid mode: Compact 2-column layout\n- Video metadata extraction (codec, resolution, bitrate, duration, file size)\n- Self-contained HTML reports (no server required, works offline)\n- Security features (path validation, resource limits, timeout controls)\n- Multi-platform FFmpeg support (macOS, Linux, Windows)\n\n**Example usage:**\n```bash\n# Basic comparison\npython3 scripts\u002Fcompare.py original.mp4 compressed.mp4\n\n# Custom output and frame interval\npython3 scripts\u002Fcompare.py original.mp4 compressed.mp4 -o report.html --interval 10\n\n# Batch processing\nfor original in originals\u002F*.mp4; do\n    compressed=\"compressed\u002F$(basename \"$original\")\"\n    output=\"reports\u002F$(basename \"$original\" .mp4).html\"\n    python3 scripts\u002Fcompare.py \"$original\" \"$compressed\" -o \"$output\"\ndone\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [video-comparer\u002Freferences\u002F](.\u002Fvideo-comparer\u002Freferences\u002F) for quality metrics interpretation, FFmpeg commands, and configuration options.\n\n**Requirements**: Python 3.8+, FFmpeg\u002FFFprobe (install via `brew install ffmpeg`, `apt install ffmpeg`, or `winget install ffmpeg`)\n\n---\n\n### 16. **qa-expert** - Comprehensive QA Testing Infrastructure\n\nEstablish world-class QA testing processes with autonomous LLM execution, Google Testing Standards, and OWASP security best practices.\n\n**When to use:**\n- Setting up QA infrastructure for new or existing projects\n- Writing standardized test cases following Google Testing Standards (AAA pattern)\n- Implementing security testing (OWASP Top 10 coverage)\n- Executing comprehensive test plans with automatic progress tracking\n- Filing bugs with proper P0-P4 severity classification\n- Calculating quality metrics and enforcing quality gates\n- Enabling autonomous LLM-driven test execution (100x speedup)\n- Preparing QA documentation for third-party team handoffs\n\n**Key features:**\n- **One-command initialization**: Complete QA infrastructure with templates, CSVs, and documentation\n- **Autonomous execution**: Master prompt enables LLM to auto-execute all tests, auto-track results, auto-file bugs\n- **Google Testing Standards**: AAA pattern compliance, 90% coverage targets, fail-fast validation\n- **OWASP security testing**: 90% Top 10 coverage with specific attack vectors\n- **Quality gates enforcement**: 100% execution, ≥80% pass rate, 0 P0 bugs, ≥80% code coverage\n- **Ground Truth Principle**: Prevents doc\u002FCSV sync issues (test docs = authoritative source)\n- **Bug tracking**: P0-P4 classification with detailed repro steps and environment info\n- **Day 1 onboarding**: 5-hour guide for new QA engineers\n- **30+ LLM prompts**: Ready-to-use prompts for specific QA tasks\n- **Metrics dashboard**: Test execution progress, pass rate, bug analysis, quality gates status\n\n**Example usage:**\n```bash\n# Initialize QA project (creates full infrastructure)\npython3 scripts\u002Finit_qa_project.py my-app .\u002F\n\n# Calculate quality metrics and gates status\npython3 scripts\u002Fcalculate_metrics.py tests\u002FTEST-EXECUTION-TRACKING.csv\n\n# For autonomous execution, copy master prompt from:\n# references\u002Fmaster_qa_prompt.md → paste to LLM → auto-executes 342 tests over 5 weeks\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [qa-expert\u002Freferences\u002F](.\u002Fqa-expert\u002Freferences\u002F) for:\n- `master_qa_prompt.md` - Single command for autonomous execution (100x speedup)\n- `google_testing_standards.md` - AAA pattern, coverage thresholds, OWASP testing\n- `day1_onboarding.md` - 5-hour onboarding timeline for new QA engineers\n- `ground_truth_principle.md` - Preventing doc\u002FCSV sync issues\n- `llm_prompts_library.md` - 30+ ready-to-use QA prompts\n\n**Requirements**: Python 3.8+\n\n**💡 Innovation**: The autonomous execution capability (via master prompt) enables LLM to execute entire test suites 100x faster than manual execution, with zero human error in tracking. Perfect for third-party QA handoffs - just provide the master prompt and they can start testing immediately.\n\n---\n\n### 17. **prompt-optimizer** - Prompt Engineering with EARS Methodology\n\nTransform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) - a methodology created by Rolls-Royce for converting natural language into testable requirements.\n\n**Methodology inspired by:** [阿星AI工作室 (A-Xing AI Studio)](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FyUVX-9FovSq7ZGChkHpuXQ), which pioneered combining EARS with domain theory grounding for practical prompt enhancement.\n\n**When to use:**\n- Converting loose requirements into structured specifications\n- Optimizing prompts for AI code generation or content creation\n- Breaking down vague feature requests into atomic, testable statements\n- Adding domain theory grounding to technical requirements\n- Transforming \"build X\" requests into detailed implementation specs\n- Learning prompt engineering best practices with proven frameworks\n\n**Key features:**\n- **EARS transformation**: 5 sentence patterns (ubiquitous, event-driven, state-driven, conditional, unwanted behavior)\n- **6-step optimization workflow**: Analyze → Transform → Identify theories → Extract examples → Enhance → Present\n- **Domain theory catalog**: 40+ frameworks mapped to 10 domains (productivity, UX, gamification, learning, e-commerce, security)\n- **Structured prompt framework**: Role\u002FSkills\u002FWorkflows\u002FExamples\u002FFormats template\n- **Advanced techniques**: Multi-stakeholder requirements, non-functional specs, complex conditional logic\n- **Complete examples**: Procrastination app, e-commerce product page, learning dashboard, password reset\n- **Theory grounding**: GTD, BJ Fogg Behavior Model, Gestalt Principles, AIDA, Zero Trust, and more\n- **Progressive disclosure**: Bundled references (ears_syntax.md, domain_theories.md, examples.md)\n\n**Example usage:**\n```markdown\n# Before (vague)\n\"Build me a password reset feature\"\n\n# After EARS transformation (7 atomic requirements)\n1. When user clicks \"Forgot Password\", the system shall display email input field\n2. When user submits valid email, the system shall send password reset link valid for 1 hour\n3. When user clicks reset link, the system shall verify token has not expired\n4. When token is valid, the system shall display password creation form requiring minimum 12 characters, 1 uppercase, 1 number, 1 special character\n5. When user submits new password meeting requirements, the system shall hash password with bcrypt and invalidate reset token\n6. When user attempts password reset more than 3 times in 1 hour, the system shall block further attempts for 1 hour\n7. If reset token has expired, the system shall display error message and option to request new link\n\n# Enhanced with domain theories\n- Zero Trust Architecture (verify at each step)\n- Defense in Depth (rate limiting + token expiration + password complexity)\n- Progressive Disclosure (multi-step UX flow)\n\n# Full prompt includes Role, Skills, Workflows, Examples, Formats\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [prompt-optimizer\u002Freferences\u002F](.\u002Fprompt-optimizer\u002Freferences\u002F) for:\n- `ears_syntax.md` - Complete EARS patterns and transformation rules\n- `domain_theories.md` - 40+ theories mapped to domains with selection guidance\n- `examples.md` - Full transformation examples with before\u002Fafter comparisons\n\n**💡 Innovation**: EARS methodology eliminates ambiguity by forcing explicit conditions, triggers, and measurable criteria. Combined with domain theory grounding (GTD, BJ Fogg, Gestalt, etc.), it transforms \"build a todo app\" into a complete specification with behavioral psychology principles, UX best practices, and concrete test cases - enabling test-driven development from day one.\n\n---\n\n### 18. **claude-code-history-files-finder** - Session History Recovery\n\nFind and recover content from Claude Code session history files stored in `~\u002F.claude\u002Fprojects\u002F`.\n\n**When to use:**\n- Recovering deleted or lost files from previous Claude Code sessions\n- Searching for specific code across conversation history\n- Tracking file modifications across multiple sessions\n- Finding sessions containing specific keywords or implementations\n\n**Key features:**\n- **Session search**: Find sessions by keywords with frequency ranking\n- **Content recovery**: Extract files from Write tool calls with deduplication\n- **Statistics analysis**: Message counts, tool usage breakdown, file operations\n- **Batch operations**: Process multiple sessions with keyword filtering\n- **Streaming processing**: Handle large session files (>100MB) efficiently\n\n**Example usage:**\n```bash\n# List recent sessions for a project\npython3 scripts\u002Fanalyze_sessions.py list \u002Fpath\u002Fto\u002Fproject\n\n# Search sessions for keywords\npython3 scripts\u002Fanalyze_sessions.py search \u002Fpath\u002Fto\u002Fproject \"ComponentName\" \"featureX\"\n\n# Recover deleted files from a session\npython3 scripts\u002Frecover_content.py ~\u002F.claude\u002Fprojects\u002F...\u002Fsession.jsonl -k DeletedComponent -o .\u002Frecovered\u002F\n\n# Get session statistics\npython3 scripts\u002Fanalyze_sessions.py stats \u002Fpath\u002Fto\u002Fsession.jsonl --show-files\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [claude-code-history-files-finder\u002Freferences\u002F](.\u002Fclaude-code-history-files-finder\u002Freferences\u002F) for:\n- `session_file_format.md` - JSONL structure and extraction patterns\n- `workflow_examples.md` - Detailed recovery and analysis workflows\n\n---\n\n### 19. **docs-cleaner** - Documentation Consolidation\n\nConsolidate redundant documentation while preserving all valuable content.\n\n**When to use:**\n- Cleaning up documentation bloat across projects\n- Merging redundant docs covering the same topics\n- Reducing documentation sprawl after rapid development\n- Consolidating multiple files into authoritative sources\n\n**Key features:**\n- **Content preservation**: Never lose valuable information during cleanup\n- **Redundancy detection**: Identify overlapping documentation\n- **Smart merging**: Combine related docs while maintaining structure\n- **Validation**: Ensure consolidated docs are complete and accurate\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n---\n\n### 20. **skills-search** - CCPM Skill Registry Search\n\nSearch, discover, install, and manage Claude Code skills from the CCPM (Claude Code Plugin Manager) registry.\n\n**When to use:**\n- Finding skills for specific tasks (e.g., \"find PDF skills\")\n- Installing skills by name\n- Listing currently installed skills\n- Getting detailed information about a skill\n- Managing your Claude Code skill collection\n\n**Key features:**\n- **Registry search**: Search CCPM registry with `ccpm search \u003Cquery>`\n- **Skill installation**: Install skills with `ccpm install \u003Cskill-name>`\n- **Version support**: Install specific versions with `@version` syntax\n- **Bundle installation**: Install pre-configured skill bundles (web-dev, content-creation, developer-tools)\n- **Multiple formats**: Supports registry names, GitHub owner\u002Frepo, and full URLs\n- **Skill info**: Get detailed skill information with `ccpm info \u003Cskill-name>`\n\n**Example usage:**\n```bash\n# Search for skills\nccpm search pdf              # Find PDF-related skills\nccpm search \"code review\"    # Find code review skills\n\n# Install skills\nccpm install skill-creator                # From registry\nccpm install daymade\u002Fskill-creator        # From GitHub\nccpm install skill-creator@1.0.0          # Specific version\n\n# List and manage\nccpm list                    # List installed skills\nccpm info skill-creator      # Get skill details\nccpm uninstall pdf-processor # Remove a skill\n\n# Install bundles\nccpm install-bundle web-dev  # Install web development skills bundle\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [skills-search\u002FSKILL.md](.\u002Fskills-search\u002FSKILL.md) for complete command reference\n\n**Requirements**: CCPM CLI (`npm install -g @daymade\u002Fccpm`)\n\n---\n\n### 21. **pdf-creator** - PDF Creation with Chinese Font Support\n\nCreate professional PDF documents from markdown with proper Chinese typography using WeasyPrint.\n\n**When to use:**\n- Converting markdown to PDF for sharing or printing\n- Generating formal documents (legal filings, reports)\n- Ensuring correct Chinese font rendering\n\n**Key features:**\n- WeasyPrint + Markdown conversion pipeline\n- Built-in Chinese font fallbacks\n- A4 layout defaults with print-friendly margins\n- Batch conversion scripts\n\n**Example usage:**\n```bash\nuv run --with weasyprint --with markdown scripts\u002Fmd_to_pdf.py input.md output.pdf\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [pdf-creator\u002FSKILL.md](.\u002Fpdf-creator\u002FSKILL.md) for setup and workflow details.\n\n**Requirements**: Python 3.8+, `weasyprint`, `markdown`\n\n---\n\n### 22. **claude-md-progressive-disclosurer** - CLAUDE.md Optimization\n\nOptimize user CLAUDE.md files using progressive disclosure to reduce context bloat while preserving critical rules.\n\n**When to use:**\n- CLAUDE.md is too long or repetitive\n- Need to move detailed procedures into references\n- Want to extract reusable workflows into skills\n\n**Key features:**\n- Section classification (keep\u002Fmove\u002Fextract\u002Fremove)\n- Before\u002Fafter line-count reporting\n- Reference file and pointer formats\n- Best-practice optimization workflow\n\n**Example usage:**\n```\n\"Optimize my ~\u002F.claude\u002FCLAUDE.md using progressive disclosure and propose a plan.\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [claude-md-progressive-disclosurer\u002FSKILL.md](.\u002Fclaude-md-progressive-disclosurer\u002FSKILL.md).\n\n---\n\n### 23. **promptfoo-evaluation** - Promptfoo LLM Evaluation\n\nConfigure and run LLM evaluations with Promptfoo for prompt testing and model comparisons.\n\n**When to use:**\n- Setting up prompt tests and eval configs\n- Comparing LLM outputs across providers\n- Adding custom assertions or LLM-as-judge grading\n\n**Key features:**\n- promptfooconfig.yaml templates\n- Python custom assertions\n- llm-rubric scoring guidance\n- Built-in preview (echo provider) workflows\n\n**Example usage:**\n```bash\nnpx promptfoo@latest init\nnpx promptfoo@latest eval\nnpx promptfoo@latest view\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [promptfoo-evaluation\u002Freferences\u002Fpromptfoo_api.md](.\u002Fpromptfoo-evaluation\u002Freferences\u002Fpromptfoo_api.md).\n\n**Requirements**: Node.js (Promptfoo via `npx promptfoo@latest`)\n\n---\n\n### 24. **iOS-APP-developer** - iOS App Development\n\nBuild, configure, and debug iOS apps with XcodeGen, SwiftUI, and Swift Package Manager.\n\n**When to use:**\n- Setting up XcodeGen `project.yml`\n- Fixing SPM dependency or embed issues\n- Handling code signing and device deployment errors\n- Debugging camera\u002FAVFoundation problems\n\n**Key features:**\n- XcodeGen project templates\n- SPM dynamic framework embedding fixes\n- Code signing and provisioning guidance\n- Device deployment and troubleshooting checklists\n\n**Example usage:**\n```bash\nxcodegen generate\nxcodebuild -destination 'platform=iOS Simulator,name=iPhone 17' build\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [iOS-APP-developer\u002Freferences\u002Fxcodegen-full.md](.\u002FiOS-APP-developer\u002Freferences\u002Fxcodegen-full.md).\n\n**Requirements**: macOS + Xcode, XcodeGen\n\n---\n\n### 25. **twitter-reader** - Twitter\u002FX Content Fetching\n\nFetch Twitter\u002FX post content using Jina.ai API to bypass JavaScript restrictions without authentication.\n\n**When to use:**\n- Retrieving tweet content for analysis or documentation\n- Fetching thread replies and conversation context\n- Extracting images and media from posts\n- Batch downloading multiple tweets for reference\n\n**Key features:**\n- No JavaScript rendering or browser automation needed\n- No Twitter authentication required\n- Returns markdown-formatted content with metadata\n- Supports both individual and batch fetching\n- Includes author, timestamp, post text, images, and replies\n- Environment variable configuration for secure API key management\n\n**Example usage:**\n```bash\n# Set your Jina API key (get from https:\u002F\u002Fjina.ai\u002F)\nexport JINA_API_KEY=\"your_api_key_here\"\n\n# Fetch a single tweet\ncurl \"https:\u002F\u002Fr.jina.ai\u002Fhttps:\u002F\u002Fx.com\u002FUSER\u002Fstatus\u002FTWEET_ID\" \\\n  -H \"Authorization: Bearer ${JINA_API_KEY}\"\n\n# Batch fetch multiple tweets\nscripts\u002Ffetch_tweets.sh \\\n  \"https:\u002F\u002Fx.com\u002Fuser\u002Fstatus\u002F123\" \\\n  \"https:\u002F\u002Fx.com\u002Fuser\u002Fstatus\u002F456\"\n\n# Fetch to file using Python script\npython scripts\u002Ffetch_tweet.py https:\u002F\u002Fx.com\u002Fuser\u002Fstatus\u002F123 output.md\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [twitter-reader\u002FSKILL.md](.\u002Ftwitter-reader\u002FSKILL.md) for full details and URL format support.\n\n**Requirements**:\n- **Jina.ai API key** (get from https:\u002F\u002Fjina.ai\u002F - free tier available)\n- **curl** (pre-installed on most systems)\n- **Python 3.6+** (for Python script)\n\n---\n\n### 26. **macos-cleaner** - Intelligent macOS Disk Space Recovery\n\n**The safest way to reclaim disk space on macOS.** Analyze system caches, application remnants, large files, and development environments with intelligent categorization and interactive cleanup.\n\n**Why macos-cleaner stands out:**\n- **Safety-First Philosophy**: Never deletes without explicit user confirmation. Every operation includes risk assessment (🟢 Safe \u002F 🟡 Caution \u002F 🔴 Keep).\n- **Intelligence Over Automation**: Analyzes first, explains thoroughly, then lets you decide. Unlike one-click cleaners that blindly delete, we help you understand what you're removing and why.\n- **Developer-Friendly**: Deep analysis of Docker, Homebrew, npm, pip caches - tools that generic cleaners miss.\n- **Transparent & Educational**: Every recommendation includes an explanation of what the file is, why it's safe (or not), and what happens if you delete it.\n- **Professional Quality**: Built by developers who know the pain of accidentally deleting important files. Includes comprehensive safety checks and Time Machine backup recommendations.\n\n**Our design principles:**\n1. **User Control First**: You make the decisions, we provide the insights\n2. **Explain Everything**: No mysterious deletions - full transparency on impact\n3. **Conservative Defaults**: When uncertain, we preserve rather than delete\n4. **Developer Context**: Understand development tool caches, not just system files\n5. **Hybrid Approach**: Combine script precision with visual tools (Mole integration)\n\n**When to use:**\n- Your Mac is running out of disk space (>80% full)\n- You're a developer with Docker\u002Fnpm\u002Fpip\u002FHomebrew caches piling up\n- You want to understand what's consuming space, not just delete blindly\n- You need to clean up after uninstalled applications\n- You prefer understanding over automation\n\n**Key features:**\n- **Smart Cache Analysis**: Categorizes system caches, app caches, logs by safety level\n- **Application Remnant Detection**: Finds orphaned data from uninstalled apps with confidence scoring\n- **Large File Discovery**: Intelligent categorization (videos, archives, databases, disk images, build artifacts)\n- **Development Environment Cleanup**: Docker (images, containers, volumes, build cache), Homebrew, npm, pip, old Git repos\n- **Interactive Safe Deletion**: Batch confirmation, selective deletion, undo-friendly (uses Trash when possible)\n- **Before\u002FAfter Reports**: Track space recovery with detailed breakdown\n- **Mole Integration**: Seamless workflow with visual cleanup tool for GUI preferences\n- **Risk Categorization**: Every item labeled with safety level and explanation\n- **Time Machine Awareness**: Recommends backups before large deletions (>10 GB)\n\n**What makes us different:**\n- ✅ **Trust Through Transparency**: Other cleaners hide what they delete. We show everything and explain why.\n- ✅ **Developer-Centric**: We clean Docker, not just browser caches. We understand `.git` directories, `node_modules`, and build artifacts.\n- ✅ **Safety Checks Built-In**: Protection against deleting system files, user data, credentials, active databases, or files in use.\n- ✅ **Educational**: Learn what's safe to delete and why, so you can maintain your Mac confidently.\n- ❌ **Not a One-Click Solution**: We don't delete automatically. If you want \"clean everything now\", use other tools. We're for users who want control.\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install macos-cleaner@daymade-skills\n\n# Ask Claude Code to analyze your Mac\n\"My Mac is running out of space, help me analyze what's using storage\"\n\n# Claude will:\n# 1. Run comprehensive disk analysis\n# 2. Present categorized findings with safety levels\n# 3. Explain each category (caches, remnants, large files, dev tools)\n# 4. Recommend cleanup approach\n# 5. Execute ONLY what you confirm\n\n# Example analysis output:\n📊 Disk Space Analysis\n━━━━━━━━━━━━━━━━━━━━━━━━\nTotal:     500 GB\nUsed:      450 GB (90%)\nAvailable:  50 GB (10%)\n\n🟢 Safe to Clean (95 GB):\n  - System caches:     45 GB (apps regenerate automatically)\n  - Homebrew cache:     5 GB (reinstalls when needed)\n  - npm cache:          3 GB (safe to clear)\n  - Old logs:           8 GB (diagnostic data only)\n  - Trash:             34 GB (already marked for deletion)\n\n🟡 Review Recommended (62 GB):\n  - Large downloads:   38 GB (may contain important files)\n  - App remnants:       8 GB (verify apps are truly uninstalled)\n  - Docker images:     12 GB (may be in use)\n  - Old .git repos:     4 GB (verify project is archived)\n\n🔴 Keep Unless Certain (0 GB):\n  - No high-risk items detected\n\nRecommendation: Start with 🟢 Safe items (95 GB), then review 🟡 items together.\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [macos-cleaner\u002Freferences\u002F](.\u002Fmacos-cleaner\u002Freferences\u002F) for:\n- `cleanup_targets.md` - Detailed explanations of every cleanup target\n- `mole_integration.md` - How to combine scripts with Mole visual tool\n- `safety_rules.md` - Comprehensive safety guidelines and what to never delete\n\n**Requirements**:\n- **Python 3.6+** (pre-installed on macOS)\n- **macOS** (tested on macOS 10.15+)\n- **Optional**: [Mole](https:\u002F\u002Fgithub.com\u002Ftw93\u002FMole) for visual cleanup interface\n\n---\n\n### 27. **fact-checker** - Document Fact-Checking\n\nVerify factual claims in documents using web search and official sources, then propose corrections with user confirmation.\n\n**When to use:**\n- Fact-checking documents for accuracy\n- Verifying AI model specifications and technical documentation\n- Updating outdated information in documents\n- Validating statistical claims and benchmarks\n- Checking API capabilities and version numbers\n\n**Key features:**\n- Web search integration with authoritative sources\n- AI model specification verification\n- Technical documentation accuracy checks\n- Statistical data validation\n- Automated correction reports with user confirmation\n- Supports general factual statements and technical claims\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install fact-checker@daymade-skills\n\n# Fact-check a document\n\"Please fact-check this section about AI model capabilities\"\n\n# Verify technical specs\n\"Check if these Claude model specifications are still accurate\"\n\n# Update outdated info\n\"Verify and update the version numbers in this documentation\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [fact-checker\u002FSKILL.md](.\u002Ffact-checker\u002FSKILL.md) for full workflow and claim types.\n\n**Requirements**:\n- Web search access (via Claude Code)\n\n---\n\n### 28. **skill-reviewer** - Skill Quality Review & Improvement\n\nReview and improve Claude Code skills against official best practices with three powerful modes.\n\n**When to use:**\n- Validating your own skills before publishing\n- Evaluating others' skill repositories\n- Contributing improvements to open-source skills via auto-PR\n- Ensuring skills follow marketplace standards\n\n**Key features:**\n- **Self-review mode**: Run automated validation via skill-creator scripts\n- **External review mode**: Clone, analyze, and generate improvement reports\n- **Auto-PR mode**: Fork → improve → submit PR with additive-only changes\n- **Evaluation checklist**: Frontmatter, instructions, resources verification\n- **Additive-only principle**: Never delete files when contributing to others\n- **PR guidelines**: Tone recommendations and professional templates\n- **Auto-install dependencies**: Automatically installs skill-creator if missing\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install skill-reviewer@daymade-skills\n\n# Self-review your skill\n\"Validate my skill at ~\u002Fmy-skills\u002Fmy-awesome-skill\"\n\n# Review external skill repository\n\"Review the skills at https:\u002F\u002Fgithub.com\u002Fuser\u002Fskill-repo\"\n\n# Auto-PR improvements\n\"Fork, improve, and submit PR for https:\u002F\u002Fgithub.com\u002Fuser\u002Fskill-repo\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [skill-reviewer\u002Freferences\u002F](.\u002Fskill-reviewer\u002Freferences\u002F) for:\n- `evaluation_checklist.md` - Complete skill evaluation criteria\n- `pr_template.md` - Professional PR description template\n- `marketplace_template.json` - Marketplace configuration template\n\n---\n\n### 29. **github-contributor** - GitHub Contribution Strategy\n\nStrategic guide for becoming an effective GitHub contributor and building your open-source reputation.\n\n**When to use:**\n- Looking for projects to contribute to\n- Learning contribution best practices\n- Building your GitHub presence and reputation\n- Understanding how to write high-quality PRs\n\n**Key features:**\n- **Four contribution types**: Documentation, Code Quality, Bug Fixes, Features\n- **Project selection criteria**: What makes a good first project vs red flags\n- **PR excellence workflow**: Before → During → After submission checklist\n- **Reputation building ladder**: Documentation → Bug Fixes → Features → Maintainer\n- **GitHub CLI commands**: Quick reference for fork, PR, issue operations\n- **Conventional commit format**: Type, scope, description structure\n- **Common mistakes**: What to avoid and best practices\n\n**Contribution types explained:**\n```\nLevel 1: Documentation fixes (lowest barrier, high impact)\n    ↓ (build familiarity)\nLevel 2: Code quality (medium effort, demonstrates skill)\n    ↓ (understand codebase)\nLevel 3: Bug fixes (high impact, builds trust)\n    ↓ (trusted contributor)\nLevel 4: Feature additions (highest visibility)\n    ↓ (potential maintainer)\n```\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install github-contributor@daymade-skills\n\n# Find good first issues\n\"Help me find projects with good first issues in Python\"\n\n# Write a high-quality PR\n\"Guide me through creating a PR for this bug fix\"\n\n# Build contribution strategy\n\"Help me plan a contribution strategy for building my GitHub profile\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [github-contributor\u002Freferences\u002F](.\u002Fgithub-contributor\u002Freferences\u002F) for:\n- `pr_checklist.md` - Complete PR quality checklist\n- `project_evaluation.md` - How to evaluate projects for contribution\n- `communication_templates.md` - Issue and PR communication templates\n\n---\n\n### 31. **i18n-expert** - Internationalization & Localization\n\nComplete internationalization\u002Flocalization setup and auditing for UI codebases. Configure i18n frameworks, replace hard-coded strings with translation keys, ensure locale parity between en-US and zh-CN, and validate pluralization and formatting.\n\n**When to use:**\n- Setting up i18n for new React\u002FNext.js\u002FVue applications\n- Auditing existing i18n implementations for key parity and completeness\n- Replacing hard-coded strings with translation keys\n- Ensuring proper error code mapping to localized messages\n- Validating pluralization, date\u002Ftime\u002Fnumber formatting across locales\n- Implementing language switching and SEO metadata localization\n\n**Key features:**\n- Library selection and setup (react-i18next, next-intl, vue-i18n)\n- Key architecture and locale file organization (JSON, YAML, PO, XLIFF)\n- Translation generation strategy (AI, professional, manual)\n- Routing and language detection\u002Fswitching\n- SEO and metadata localization\n- RTL support for applicable locales\n- Key parity validation between en-US and zh-CN\n- Pluralization and formatting validation\n- Error code mapping to localized messages\n- Bundled i18n_audit.py script for key usage extraction\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install i18n-expert@daymade-skills\n\n# Setup i18n for a new project\n\"Set up i18n for my React app with English and Chinese support\"\n\n# Audit existing i18n implementation\n\"Audit the i18n setup and find missing translation keys\"\n\n# Replace hard-coded strings\n\"Replace all hard-coded strings in this component with i18n keys\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [i18n-expert\u002FSKILL.md](.\u002Fi18n-expert\u002FSKILL.md) for complete workflow and architecture guidance.\n\n**Requirements**:\n- **Python 3.6+** (for audit script)\n- **React\u002FNext.js\u002FVue** (framework-specific i18n library)\n\n---\n\n### 32. **claude-skills-troubleshooting** - Plugin & Skill Troubleshooting\n\nDiagnose and resolve Claude Code plugin and skill configuration issues. Debug plugin installation, enablement, and activation problems with systematic workflows.\n\n**When to use:**\n- Plugins installed but not showing in available skills list\n- Skills not activating as expected despite installation\n- Troubleshooting enabledPlugins configuration in settings.json\n- Debugging \"plugin not working\" or \"skill not showing\" issues\n- Understanding plugin state architecture and lifecycle\n\n**Key features:**\n- Quick diagnosis via diagnostic script (detects installed vs enabled mismatch)\n- Plugin state architecture documentation (installed_plugins.json vs settings.json)\n- Marketplace cache freshness detection and update guidance\n- Known GitHub issues tracking (#17832, #19696, #17089, #13543, #16260)\n- Batch enable script for missing plugins from a marketplace\n- Skills vs Commands architecture explanation\n- Comprehensive diagnostic commands reference\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install claude-skills-troubleshooting@daymade-skills\n\n# Run diagnostic\npython3 scripts\u002Fdiagnose_plugins.py\n\n# Batch enable missing plugins\npython3 scripts\u002Fenable_all_plugins.py daymade-skills\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [claude-skills-troubleshooting\u002FSKILL.md](.\u002Fclaude-skills-troubleshooting\u002FSKILL.md) for complete troubleshooting workflow and architecture guidance.\n\n**Requirements**: None (uses Claude Code built-in Python)\n\n---\n\n### 33. **meeting-minutes-taker** - Meeting Minutes Generator\n\nTransform meeting transcripts into high-fidelity, structured meeting minutes with iterative human review.\n\n**When to use:**\n- Meeting transcript provided and minutes\u002Fnotes\u002Fsummaries requested\n- Multiple versions of meeting minutes need merging without content loss\n- Existing minutes need review against original transcript for missing items\n\n**Key features:**\n- Multi-pass parallel generation with UNION merge strategy\n- Evidence-based recording with speaker quotes\n- Mermaid diagrams for architecture discussions\n- Iterative human-in-the-loop refinement workflow\n- Cross-AI comparison for bias reduction\n- Completeness checklist for systematic review\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install meeting-minutes-taker@daymade-skills\n\n# Then provide a meeting transcript and request minutes\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [meeting-minutes-taker\u002FSKILL.md](.\u002Fmeeting-minutes-taker\u002FSKILL.md) for complete workflow and template guidance.\n\n**Requirements**: None\n\n---\n\n### 34. **deep-research** - Research Report Generator\n\nGenerate format-controlled research reports with evidence tracking and citations.\n\n**When to use:**\n- Need a structured research report, literature review, or market\u002Findustry analysis\n- Require strict section formatting or a template to be enforced\n- Need evidence mapping, citations, and source quality review\n- Want multi-pass synthesis to avoid missing key findings\n\n**Key features:**\n- Report spec and format contract workflow\n- Evidence table with source quality rubric\n- Multi-pass complete drafting with UNION merge\n- Citation verification and conflict handling\n- Ready-to-use report template and formatting rules\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install deep-research@daymade-skills\n\n# Then provide a report spec or template and request a deep research report\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [deep-research\u002FSKILL.md](.\u002Fdeep-research\u002FSKILL.md) and [deep-research\u002Freferences\u002Fresearch_report_template.md](.\u002Fdeep-research\u002Freferences\u002Fresearch_report_template.md) for workflow and structure.\n\n**Requirements**: None\n\n---\n\n### 35. **competitors-analysis** - Evidence-Based Competitor Tracking\n\nAnalyze competitor repositories with evidence-based approach. All analysis must be based on actual cloned code, never assumptions.\n\n**When to use:**\n- Track and analyze competitor products or technologies\n- Create evidence-based competitor profiles\n- Generate competitive analysis reports\n- Need to document technical decisions with cited sources\n\n**Key features:**\n- Pre-analysis checklist to ensure repositories are cloned locally\n- Forbidden patterns to prevent assumptions (\"推测...\", \"可能...\", \"应该...\")\n- Required patterns for source citation (file:line_number format)\n- Tech stack analysis guides for Node.js, Python, Rust projects\n- Directory structure conventions for organized competitor tracking\n- Bundled templates: profile template, analysis checklist\n- Management script for batch clone\u002Fpull\u002Fstatus operations\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install competitors-analysis@daymade-skills\n\n# Then ask Claude to analyze a competitor\n\"分析竞品 https:\u002F\u002Fgithub.com\u002Forg\u002Frepo\"\n\"添加竞品到 flowzero 产品的竞品列表\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [competitors-analysis\u002FSKILL.md](.\u002Fcompetitors-analysis\u002FSKILL.md) and [competitors-analysis\u002Freferences\u002F](.\u002Fcompetitors-analysis\u002Freferences\u002F) for templates.\n\n**Requirements**: Git (for cloning repositories)\n\n---\n\n### 36. **tunnel-doctor** - Tailscale + Proxy\u002FVPN Conflict Fixer\n\nDiagnose and fix conflicts when using Tailscale alongside proxy\u002FVPN tools (Shadowrocket, Clash, Surge) on macOS. Covers four independent conflict layers with specific guidance for SSH access to WSL instances.\n\n**When to use:**\n- Tailscale ping works but SSH\u002FTCP connections time out\n- Proxy tools hijack the Tailscale CGNAT range (100.64.0.0\u002F10)\n- Browser returns HTTP 503 but curl and SSH work\n- `git push\u002Fpull` fails with \"failed to begin relaying via HTTP\"\n- Setting up Tailscale SSH to WSL and encountering `operation not permitted`\n- Need to make Tailscale and Shadowrocket\u002FClash\u002FSurge coexist on macOS\n\n**Key features:**\n- Four-layer diagnostic model: route hijacking, HTTP env vars, system proxy bypass, SSH ProxyCommand double tunneling\n- Per-tool fix guides for Shadowrocket, Clash, and Surge\n- SSH ProxyCommand double tunnel detection and fix (git push\u002Fpull failures)\n- Tailscale SSH ACL configuration (`check` vs `accept`)\n- WSL snap vs apt Tailscale installation (snap sandbox breaks SSH)\n- Remote development SOP with proxy-safe Makefile patterns\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install tunnel-doctor@daymade-skills\n\n# Then ask Claude to diagnose\n\"Tailscale ping works but SSH times out\"\n\"Fix Tailscale and Shadowrocket route conflict on macOS\"\n\"git push fails with failed to begin relaying via HTTP\"\n\"Set up Tailscale SSH to my WSL instance\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [tunnel-doctor\u002Freferences\u002Fproxy_conflict_reference.md](.\u002Ftunnel-doctor\u002Freferences\u002Fproxy_conflict_reference.md) for per-tool configuration and conflict architecture.\n\n---\n\n### 37. **windows-remote-desktop-connection-doctor** - AVD\u002FW365 Connection Quality Diagnostician\n\nDiagnose Windows App (Microsoft Remote Desktop \u002F Azure Virtual Desktop \u002F W365) connection quality issues on macOS, with focus on transport protocol optimization (UDP Shortpath vs WebSocket fallback).\n\n**When to use:**\n- VDI connection is slow with high RTT (>100ms)\n- Transport Protocol shows WebSocket instead of UDP\n- RDP Shortpath fails to establish\n- Connection quality degraded after changing network location\n- Need to identify VPN\u002Fproxy interference with STUN\u002FTURN\n\n**Key features:**\n- 5-step diagnostic workflow from connection info collection to fix verification\n- Transport protocol analysis (UDP Shortpath > TCP > WebSocket hierarchy)\n- VPN\u002Fproxy interference detection (ShadowRocket TUN mode, Tailscale exit node)\n- Windows App log parsing for health check failures, certificate errors, FetchClientOptions timeouts\n- ISP UDP restriction testing with STUN connectivity checks\n- Chinese ISP-specific guidance for UDP throttling issues\n- Working vs broken log comparison methodology\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install windows-remote-desktop-connection-doctor@daymade-skills\n\n# Then ask Claude to diagnose\n\"My VDI connection shows WebSocket instead of UDP, RTT is 165ms\"\n\"Diagnose why RDP Shortpath is not working\"\n\"Windows App transport protocol stuck on WebSocket\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [windows-remote-desktop-connection-doctor\u002Freferences\u002F](.\u002Fwindows-remote-desktop-connection-doctor\u002Freferences\u002F) for log analysis patterns and AVD transport protocol details.\n\n---\n\n### 38. **product-analysis** - Multi-Path Product Analysis & Optimization\n\nRun a scalable, evidence-driven product audit using parallel Claude Code agents and optional Codex CLI parallelization. Covers UX, API, architecture, and competitive benchmark workflows with quantified findings and priority recommendations.\n\n**When to use:**\n- Product launch readiness reviews\n- Multi-perspective codebase and UX audits before release\n- API quality checks with endpoint and consumption consistency reviews\n- Competitive benchmarking against selected competitor repos\n\n**Key features:**\n- Auto-detects tool context (project stack + optional `codex` availability)\n- Parallel analysis across dimensions: `full`, `ux`, `api`, `arch`, `compare`\n- Multi-agent synthesis with quantified findings and P0\u002FP1\u002FP2 recommendations\n- Built-in comparison hooks with `competitors-analysis`\n- Cross-validation workflow to reduce overfitting from a single model perspective\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install product-analysis@daymade-skills\n\n# Then ask Claude for analysis\n\"Run product-analysis in full mode for launch audit\"\n\"Do a UX audit and report quantified navigation findings\"\n\"Run API audit and identify unused endpoints\"\n\"Compare this product with our top competitors\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [product-analysis\u002FSKILL.md](.\u002Fproduct-analysis\u002FSKILL.md) and [product-analysis\u002Freferences\u002Fanalysis_dimensions.md](.\u002Fproduct-analysis\u002Freferences\u002Fanalysis_dimensions.md) for dimension definitions and workflow guidance.\n\n**Requirements**: Optional `codex` CLI (for multi-model parallel mode). Skill runs with Claude only if `codex` is not installed.\n\n---\n\n### 39. **financial-data-collector** - Financial Data Collection for US Equities\n\nCollect real financial data for any US publicly traded company from free public sources (yfinance). Output structured JSON with market data, historical financials (income statement, cash flow, balance sheet), WACC inputs, and analyst estimates - ready for downstream DCF modeling, comps analysis, or earnings review.\n\n**When to use:**\n- Collecting structured financial data before building DCF or valuation models\n- Pulling market data (price, shares, beta, market cap) for any US equity ticker\n- Gathering historical income statement, cash flow, and balance sheet data\n- Getting risk-free rate (10Y Treasury) and analyst consensus estimates\n\n**Key features:**\n- Robust yfinance field mapping with alias chains (handles API instability across versions)\n- NaN year detection and transparent reporting (never fills with estimates)\n- 9-check validation: field completeness, market cap cross-check, CapEx sign convention, net debt consistency\n- NO FALLBACK principle: missing data returns `null` with `_source` attribution, never default values\n- FCF definition mismatch flagging (yfinance FCF ≠ investment bank FCF due to SBC)\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install financial-data-collector@daymade-skills\n\n# Then ask Claude to collect data\n\"Collect financial data for META\"\n\"Get financials for AAPL --years 3\"\n\"Pull DCF inputs for NVDA\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [financial-data-collector\u002FSKILL.md](.\u002Ffinancial-data-collector\u002FSKILL.md), [output-schema.md](.\u002Ffinancial-data-collector\u002Freferences\u002Foutput-schema.md), and [yfinance-pitfalls.md](.\u002Ffinancial-data-collector\u002Freferences\u002Fyfinance-pitfalls.md).\n\n**Requirements**: Python 3.11+, `yfinance`, `pandas` (auto-installed via uv inline dependencies).\n\n---\n\n### 40. **excel-automation** - Excel Creation, Parsing, and macOS Control\n\nCreate professionally formatted Excel files, parse complex `.xlsm` models with stdlib XML\u002FZIP workflows, and control Microsoft Excel windows on macOS via AppleScript.\n\n**When to use:**\n- Building finance-ready spreadsheets with consistent formatting rules\n- Parsing complex bank\u002Fbroker `.xlsm` files that fail in `openpyxl`\n- Extracting targeted sheet\u002Fcell data without loading huge workbooks\n- Automating Excel window operations (zoom, scroll, select) on macOS\n\n**Key features:**\n- Production template for formatted workbook generation via `openpyxl`\n- Complex workbook parser using `zipfile` + `xml.etree` (no heavy dependencies)\n- Corrupted `definedNames` repair workflow for problematic files\n- Verified AppleScript command patterns with timeout safeguards\n- Bundled formatting reference for colors, number formats, and table patterns\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install excel-automation@daymade-skills\n\n# Then ask Claude to automate Excel workflows\n\"Create a formatted valuation template workbook\"\n\"Parse this .xlsm and extract the DCF sheet\"\n\"Generate an AppleScript sequence to zoom and scroll Excel before screenshot\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [excel-automation\u002FSKILL.md](.\u002Fexcel-automation\u002FSKILL.md) and [formatting-reference.md](.\u002Fexcel-automation\u002Freferences\u002Fformatting-reference.md).\n\n**Requirements**: Python 3.8+, `uv`, `openpyxl` (auto via `uv run --with openpyxl`), macOS for AppleScript window control.\n\n---\n\n### 41. **capture-screen** - Programmatic macOS Screenshot Capture\n\nCapture application windows by CGWindowID with a reliable three-step workflow: discover window IDs via Swift, control app state via AppleScript, and capture outputs with `screencapture`.\n\n**When to use:**\n- Automating repeatable screenshot workflows for documentation\n- Capturing specific app windows instead of full-screen screenshots\n- Producing multi-shot sequences after scripted scroll\u002Fzoom changes\n- Building visual evidence capture pipelines on macOS\n\n**Key features:**\n- Bundled Swift script to resolve accurate window IDs (`CGWindowListCopyWindowInfo`)\n- Verified AppleScript patterns for app activation and window preparation\n- Window-scoped capture commands with silent mode, delays, and format control\n- Multi-shot workflow pattern for section-by-section capture\n- Clear anti-pattern notes for methods that fail on macOS\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install capture-screen@daymade-skills\n\n# Then ask Claude to capture windows programmatically\n\"Find the Excel window ID and capture it silently\"\n\"Create a multi-shot capture workflow for this workbook\"\n\"Capture Chrome window sections with scripted scrolling\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [capture-screen\u002FSKILL.md](.\u002Fcapture-screen\u002FSKILL.md).\n\n**Requirements**: macOS (Swift + AppleScript + `screencapture`).\n\n---\n\n### 42. **continue-claude-work** - Resume Interrupted Claude Work\n\nRecover actionable context from local `~\u002F.claude` session artifacts and continue implementation without reopening the old interactive session. Uses a bundled Python script for intelligent context extraction.\n\n**When to use:**\n- A user provides a Claude session ID and wants the task continued\n- You need to inspect local `.claude` JSONL files instead of running `claude --resume`\n- A previous session was interrupted and the next concrete step must be reconstructed\n- A multi-agent workflow was interrupted and you need to know which subagents completed\n\n**Key features:**\n- Compact-boundary-aware extraction — reads Claude's own session compaction summaries as highest-signal context\n- Subagent workflow recovery — reports completed vs. interrupted subagents with last outputs\n- Session end reason detection — classifies clean exit, interrupted (ctrl-c), error cascade, or abandoned\n- Size-adaptive strategy — different reading approaches for small (\u003C500KB) vs. large (>5MB) sessions\n- Noise filtering — skips progress\u002Fqueue-operation\u002Fapi_error messages (37-53% of session lines)\n- Self-session exclusion, stale index fallback, MEMORY.md integration, git workspace state\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install continue-claude-work@daymade-skills\n\n# Then ask Claude to resume from local artifacts\n\"continue work from session 123e4567-e89b-12d3-a456-426614174000\"\n\"don't resume, just read the .claude files and continue\"\n\"check what I was working on in the last session and keep going\"\n```\n\n📚 **Documentation**: See [continue-claude-work\u002FSKILL.md](.\u002Fcontinue-claude-work\u002FSKILL.md).\n\n**Requirements**: Python 3.8+, `git` for workspace reconciliation.\n\n---\n\n### 43. **scrapling-skill** - Reliable Scrapling CLI Workflows\n\nInstall, troubleshoot, and use Scrapling CLI with a verified static-first workflow for extracting HTML, Markdown, or text from webpages. Includes a diagnostic script for broken extras installs, Playwright browser runtime checks, and smoke tests against real URLs.\n\n**When to use:**\n- Users mention Scrapling, `uv tool install scrapling`, or `scrapling extract`\n- You need to choose between static and browser-backed fetching\n- You need to extract article bodies from WeChat public pages (`mp.weixin.qq.com`)\n- A Scrapling install works partially but fails on missing extras, browser runtime, or TLS verification\n\n**Key features:**\n- Bundled `diagnose_scrapling.py` script for CLI, browser runtime, and live URL smoke tests\n- Verified default path: start with `extract get`, escalate to `extract fetch` only when needed\n- WeChat extraction pattern using `#js_content` for clean article Markdown\n- Troubleshooting guidance for missing `click`, Playwright runtime setup, and `curl: (60)` trust-store failures\n- Output validation workflow using file size and content checks instead of exit-code assumptions\n\n**Example usage:**\n```bash\n# Install the skill\nclaude plugin install scrapling-skill@daymade-skills\n\n# Then ask Claude to work through Scrapling for you\n\"Install Scrapling CLI and verify the setup\"\n\"Extract this WeChat article into Markdown with Scrapling\"\n\"Decide whether this page needs static or browser-backed fetching\"\n```\n\n**🎬 Live Demo**\n\n*Coming soon*\n\n📚 **Documentation**: See [scrapling-skill\u002FSKILL.md](.\u002Fscrapling-skill\u002FSKILL.md) and [scrapling-skill\u002Freferences\u002Ftroubleshooting.md](.\u002Fscrapling-skill\u002Freferences\u002Ftroubleshooting.md).\n\n**Requirements**: Python 3.6+, `uv`, Scrapling CLI, and Playwright browser runtime for browser-backed fetches.\n\n---\n\n## 🎬 Interactive Demo Gallery\n\nWant to see all demos in one place with click-to-enlarge functionality? Check out our [interactive demo gallery](.\u002Fdemos\u002Findex.html) or browse the [demos directory](.\u002Fdemos\u002F).\n\n## 🎯 Use Cases\n\n### For GitHub Workflows\nUse **github-ops** to streamline PR creation, issue management, and API operations.\n\n### For Documentation\nCombine **doc-to-markdown** for document conversion and **mermaid-tools** for diagram generation to create comprehensive documentation. Use **llm-icon-finder** to add brand icons.\n\n### For Research & Analysis\nUse **deep-research** to produce format-controlled research reports with evidence tables and citations. Combine with **fact-checker** to validate claims or with **twitter-reader** for social-source collection.\n\n### For Competitive Intelligence\nUse **competitors-analysis** to track and analyze competitor repositories with evidence-based approach. All findings are sourced from actual code (file:line_number), eliminating speculation. Combine with **deep-research** for comprehensive competitive landscape reports.\n\n### For PDF & Printable Documents\nUse **pdf-creator** to convert markdown to print-ready PDFs with proper Chinese font support for formal documents and reports.\n\n### For Team Communication\nUse **teams-channel-post-writer** to share knowledge and **statusline-generator** to track costs while working.\n\n### For Repository Management & Security\nUse **repomix-unmixer** to extract and validate repomix-packed skills or repositories. Use **repomix-safe-mixer** to package codebases securely, automatically detecting and blocking hardcoded credentials before distribution.\n\n### For Skill Development\nUse **skill-creator** (see [Essential Skill](#-essential-skill-skill-creator) section above) to build, validate, and package your own Claude Code skills following best practices.\n\n### For Presentations & Business Communication\nUse **ppt-creator** to generate professional slide decks with data visualizations, structured storytelling, and complete PPTX output for pitches, reviews, and keynotes.\n\n### For Video Quality Analysis\nUse **video-comparer** to analyze compression results, evaluate codec performance, and generate interactive comparison reports. Combine with **youtube-downloader** to compare different quality downloads.\n\n### For Media & Content Download\nUse **youtube-downloader** to download YouTube videos and extract audio from videos with automatic workarounds for common download issues.\n\n### For Transcription & ASR Correction\nUse **transcript-fixer** to correct speech-to-text errors in meeting notes, lectures, and interviews through dictionary-based rules and AI-powered corrections with automatic learning.\n\n### For Financial Data & Investment Research\nUse **financial-data-collector** to pull structured financial data for any US public company, then feed the JSON output into DCF modeling, comps analysis, or earnings review workflows.\n\n### For Excel & Financial Modeling Automation\nUse **excel-automation** to create formatted workbooks, parse complex `.xlsm` models, and automate Excel window controls for repetitive analyst workflows.\n\n### For Visual Capture Automation on macOS\nUse **capture-screen** to script repeatable app-window screenshots. Combine with **excel-automation** to generate report-ready workbook visuals.\n\n### For Meeting Documentation\nUse **meeting-minutes-taker** to transform raw meeting transcripts into structured, evidence-based minutes. Combine with **transcript-fixer** to clean up ASR errors before generating minutes. Features multi-pass generation with UNION merge to avoid content loss.\n\n### For QA Testing & Quality Assurance\nUse **qa-expert** to establish comprehensive QA testing infrastructure with autonomous LLM execution, Google Testing Standards, and OWASP security testing. Perfect for project launches, third-party QA handoffs, and enforcing quality gates (100% execution, ≥80% pass rate, 0 P0 bugs). The master prompt enables 100x faster test execution with zero tracking errors.\n\n### For Prompt Engineering & Requirements Engineering\nUse **prompt-optimizer** to transform vague feature requests into precise EARS specifications with domain theory grounding. Perfect for product requirements documents, AI-assisted coding, and learning prompt engineering best practices. Combine with **skill-creator** to create well-structured skill prompts, or with **ppt-creator** to ensure presentation content requirements are clearly specified.\n\n### For Session History & File Recovery\nUse **claude-code-history-files-finder** to recover deleted files from previous Claude Code sessions, search for specific implementations across conversation history, or track file evolution over time. Essential for recovering accidentally deleted code or finding that feature implementation you remember but can't locate.\n\n### For Resuming Interrupted Claude Sessions\nUse **continue-claude-work** to recover the last actionable request from local `~\u002F.claude` artifacts and continue implementation without reopening the original session. Combine with **claude-code-history-files-finder** when you need broader cross-session search, statistics, or deleted-file recovery.\n\n### For Web Extraction & WeChat Articles\nUse **scrapling-skill** to install and validate Scrapling CLI, choose between static and browser-backed fetching, and extract clean Markdown from sites like `mp.weixin.qq.com`. Combine with **deep-research** to turn extracted sources into structured reports or with **docs-cleaner** to normalize captured article content.\n\n### For Documentation Maintenance\nUse **docs-cleaner** to consolidate redundant documentation while preserving valuable content. Perfect for cleaning up documentation sprawl after rapid development phases or merging overlapping docs into authoritative sources.\n\n### For CLAUDE.md Optimization\nUse **claude-md-progressive-disclosurer** to reduce CLAUDE.md bloat by moving detailed sections into references while keeping core rules visible.\n\n### For Skill Discovery & Management\nUse **skills-search** to find, install, and manage Claude Code skills from the CCPM registry. Perfect for discovering new skills for specific tasks, installing skill bundles for common workflows, and keeping your skill collection organized.\n\n### For LLM Evaluation & Model Comparison\nUse **promptfoo-evaluation** to set up prompt tests, compare model outputs, and run automated evaluations with custom assertions.\n\n### For iOS App Development\nUse **iOS-APP-developer** to configure XcodeGen projects, resolve SPM dependency issues, and troubleshoot code signing or device deployment.\n\n### For macOS System Maintenance & Disk Space Recovery\nUse **macos-cleaner** to intelligently analyze and reclaim disk space on macOS with safety-first approach. Unlike one-click cleaners that blindly delete, macos-cleaner explains what each file is, categorizes by risk level (🟢\u002F🟡\u002F🔴), and requires explicit confirmation before any deletion. Perfect for developers dealing with Docker\u002FHomebrew\u002Fnpm\u002Fpip cache bloat, users wanting to understand storage consumption, or anyone who values transparency over automation. Combines script-based precision with optional Mole visual tool integration for hybrid workflow.\n\n### For Twitter\u002FX Content Research\nUse **twitter-reader** to fetch tweet content without JavaScript rendering or authentication. Perfect for documenting social media discussions, archiving threads, analyzing tweet content, or gathering reference material from Twitter\u002FX. Combine with **doc-to-markdown** to convert fetched content into other formats, or with **repomix-safe-mixer** to package research collections securely.\n\n### For Skill Quality & Open-Source Contributions\nUse **skill-reviewer** to validate your own skills against best practices before publishing, or to review and improve others' skill repositories. Combine with **github-contributor** to find high-impact open-source projects, create professional PRs, and build your contributor reputation. Perfect for developers who want to contribute to the Claude Code ecosystem or any GitHub project systematically.\n\n### For Internationalization & Localization\nUse **i18n-expert** to set up complete i18n infrastructure for React\u002FNext.js\u002FVue applications, audit existing implementations for missing translation keys, and ensure locale parity between en-US and zh-CN. Perfect for teams launching products to global markets, maintaining multi-language UIs, or replacing hard-coded strings with proper i18n keys. Combine with **skill-creator** to create locale-aware skills, or with **docs-cleaner** to consolidate documentation across multiple languages.\n\n### For Network & VPN Troubleshooting\nUse **tunnel-doctor** to diagnose and fix conflicts between Tailscale and proxy\u002FVPN tools on macOS across four independent layers (route hijacking, HTTP env vars, system proxy, SSH ProxyCommand). Essential when Tailscale ping works but TCP connections fail, when git push fails with \"failed to begin relaying via HTTP\", or when setting up Tailscale SSH to WSL instances alongside Shadowrocket, Clash, or Surge.\n\n### For Product Audits\nUse **product-analysis** for structured pre-release and architecture reviews. It combines UX, API, and architecture analysis into measurable findings with priority-ranked recommendations. Add `compare` mode to benchmark against competitor implementations through evidence-backed reports.\n\n### For Remote Desktop & VDI Optimization\nUse **windows-remote-desktop-connection-doctor** to diagnose Azure Virtual Desktop \u002F W365 connection quality issues on macOS. Essential when transport shows WebSocket instead of UDP Shortpath, when RTT is unexpectedly high, or when RDP Shortpath fails after changing network locations. Combines network evidence gathering with Windows App log analysis for systematic root cause identification.\n\n### For Plugin & Skill Troubleshooting\nUse **claude-skills-troubleshooting** to diagnose and resolve Claude Code plugin and skill configuration issues. Debug why plugins appear installed but don't show in available skills, understand the installed_plugins.json vs settings.json enabledPlugins architecture, and batch-enable missing plugins from a marketplace. Essential for marketplace maintainers debugging installation issues, developers troubleshooting skill activation, or anyone confused by the GitHub #17832 auto-enable bug.\n\n## 📚 Documentation\n\nEach skill includes:\n- **SKILL.md**: Core instructions and workflows\n- **scripts\u002F**: Executable utilities (Python\u002FBash)\n- **references\u002F**: Detailed documentation\n- **assets\u002F**: Templates and resources (where applicable)\n\n### Quick Links\n\n- **github-ops**: See `github-ops\u002Freferences\u002Fapi_reference.md` for API documentation\n- **doc-to-markdown**: See `doc-to-markdown\u002Freferences\u002Fconversion-examples.md` for conversion scenarios\n- **mermaid-tools**: See `mermaid-tools\u002Freferences\u002Fsetup_and_troubleshooting.md` for setup guide\n- **statusline-generator**: See `statusline-generator\u002Freferences\u002Fcolor_codes.md` for customization\n- **teams-channel-post-writer**: See `teams-channel-post-writer\u002Freferences\u002Fwriting-guidelines.md` for quality standards\n- **repomix-unmixer**: See `repomix-unmixer\u002Freferences\u002Frepomix-format.md` for format specifications\n- **skill-creator**: See `skill-creator\u002FSKILL.md` for complete skill creation workflow\n- **llm-icon-finder**: See `llm-icon-finder\u002Freferences\u002Ficons-list.md` for available icons\n- **cli-demo-generator**: See `cli-demo-generator\u002Freferences\u002Fvhs_syntax.md` for VHS syntax and `cli-demo-generator\u002Freferences\u002Fbest_practices.md` for demo guidelines\n- **cloudflare-troubleshooting**: See `cloudflare-troubleshooting\u002Freferences\u002Fapi_overview.md` for API documentation\n- **ui-designer**: See `ui-designer\u002FSKILL.md` for design system extraction workflow\n- **ppt-creator**: See `ppt-creator\u002Freferences\u002FWORKFLOW.md` for 9-stage creation process and `ppt-creator\u002Freferences\u002FORCHESTRATION_OVERVIEW.md` for automation\n- **youtube-downloader**: See `youtube-downloader\u002FSKILL.md` for usage examples and troubleshooting\n- **repomix-safe-mixer**: See `repomix-safe-mixer\u002Freferences\u002Fcommon_secrets.md` for detected credential patterns\n- **video-comparer**: See `video-comparer\u002Freferences\u002Fvideo_metrics.md` for quality metrics interpretation and `video-comparer\u002Freferences\u002Fconfiguration.md` for customization options\n- **transcript-fixer**: See `transcript-fixer\u002Freferences\u002Fworkflow_guide.md` for step-by-step workflows and `transcript-fixer\u002Freferences\u002Fteam_collaboration.md` for collaboration patterns\n- **qa-expert**: See `qa-expert\u002Freferences\u002Fmaster_qa_prompt.md` for autonomous execution (100x speedup) and `qa-expert\u002Freferences\u002Fgoogle_testing_standards.md` for AAA pattern and OWASP testing\n- **prompt-optimizer**: See `prompt-optimizer\u002Freferences\u002Fears_syntax.md` for EARS transformation patterns, `prompt-optimizer\u002Freferences\u002Fdomain_theories.md` for theory catalog, and `prompt-optimizer\u002Freferences\u002Fexamples.md` for complete transformations\n- **claude-code-history-files-finder**: See `claude-code-history-files-finder\u002Freferences\u002Fsession_file_format.md` for JSONL structure and `claude-code-history-files-finder\u002Freferences\u002Fworkflow_examples.md` for recovery workflows\n- **docs-cleaner**: See `docs-cleaner\u002FSKILL.md` for consolidation workflows\n- **deep-research**: See `deep-research\u002Freferences\u002Fresearch_report_template.md` for report structure and `deep-research\u002Freferences\u002Fsource_quality_rubric.md` for source triage\n- **pdf-creator**: See `pdf-creator\u002FSKILL.md` for PDF conversion and font setup\n- **claude-md-progressive-disclosurer**: See `claude-md-progressive-disclosurer\u002FSKILL.md` for CLAUDE.md optimization workflow\n- **skills-search**: See `skills-search\u002FSKILL.md` for CCPM CLI commands and registry operations\n- **promptfoo-evaluation**: See `promptfoo-evaluation\u002Freferences\u002Fpromptfoo_api.md` for evaluation patterns\n- **iOS-APP-developer**: See `iOS-APP-developer\u002Freferences\u002Fxcodegen-full.md` for XcodeGen options and project.yml details\n- **twitter-reader**: See `twitter-reader\u002FSKILL.md` for API key setup and URL format support\n- **macos-cleaner**: See `macos-cleaner\u002Freferences\u002Fcleanup_targets.md` for detailed cleanup target explanations, `macos-cleaner\u002Freferences\u002Fmole_integration.md` for Mole visual tool integration, and `macos-cleaner\u002Freferences\u002Fsafety_rules.md` for comprehensive safety guidelines\n- **skill-reviewer**: See `skill-reviewer\u002Freferences\u002Fevaluation_checklist.md` for complete evaluation criteria, `skill-reviewer\u002Freferences\u002Fpr_template.md` for PR templates, and `skill-reviewer\u002Freferences\u002Fmarketplace_template.json` for marketplace configuration\n- **github-contributor**: See `github-contributor\u002Freferences\u002Fpr_checklist.md` for PR quality checklist, `github-contributor\u002Freferences\u002Fproject_evaluation.md` for project evaluation criteria, and `github-contributor\u002Freferences\u002Fcommunication_templates.md` for issue\u002FPR templates\n- **i18n-expert**: See `i18n-expert\u002FSKILL.md` for complete i18n setup workflow, key architecture guidance, and audit procedures\n- **claude-skills-troubleshooting**: See `claude-skills-troubleshooting\u002FSKILL.md` for plugin troubleshooting workflow and architecture\n- **fact-checker**: See `fact-checker\u002FSKILL.md` for fact-checking workflow and claim verification process\n- **competitors-analysis**: See `competitors-analysis\u002FSKILL.md` for evidence-based analysis workflow and `competitors-analysis\u002Freferences\u002Fprofile_template.md` for competitor profile template\n- **windows-remote-desktop-connection-doctor**: See `windows-remote-desktop-connection-doctor\u002Freferences\u002Fwindows_app_log_analysis.md` for log parsing patterns and `windows-remote-desktop-connection-doctor\u002Freferences\u002Favd_transport_protocols.md` for transport protocol details\n- **product-analysis**: See `product-analysis\u002FSKILL.md` for workflow and `product-analysis\u002Freferences\u002Fsynthesis_methodology.md` for cross-agent weighting and recommendation logic\n- **excel-automation**: See `excel-automation\u002FSKILL.md` for create\u002Fparse\u002Fcontrol workflows and `excel-automation\u002Freferences\u002Fformatting-reference.md` for formatting standards\n- **capture-screen**: See `capture-screen\u002FSKILL.md` for CGWindowID-based screenshot workflows on macOS\n- **continue-claude-work**: See `continue-claude-work\u002FSKILL.md` for local artifact recovery, drift checks, and resume workflow\n- **scrapling-skill**: See `scrapling-skill\u002FSKILL.md` for the CLI workflow and `scrapling-skill\u002Freferences\u002Ftroubleshooting.md` for verified Scrapling failure modes\n\n## 🛠️ Requirements\n\n- **Claude Code** 2.0.13 or higher\n- **Python 3.6+** (for scripts in multiple skills)\n- **gh CLI** (for github-ops)\n- **markitdown** (for doc-to-markdown)\n- **mermaid-cli** (for mermaid-tools)\n- **yt-dlp** (for youtube-downloader): `brew install yt-dlp` or `pip install yt-dlp`\n- **FFmpeg\u002FFFprobe** (for video-comparer): `brew install ffmpeg`, `apt install ffmpeg`, or `winget install ffmpeg`\n- **weasyprint, markdown** (for pdf-creator)\n- **VHS** (for cli-demo-generator): `brew install vhs`\n- **Jina.ai API key** (for twitter-reader): Free tier available at https:\u002F\u002Fjina.ai\u002F\n- **asciinema** (optional, for cli-demo-generator interactive recording)\n- **ccusage** (optional, for statusline cost tracking)\n- **pandas & matplotlib** (optional, for ppt-creator chart generation)\n- **Marp CLI** (optional, for ppt-creator Marp PPTX export): `npm install -g @marp-team\u002Fmarp-cli`\n- **Mole** (optional, for macos-cleaner visual cleanup): Download from https:\u002F\u002Fgithub.com\u002Ftw93\u002FMole\n- **repomix** (for repomix-safe-mixer): `npm install -g repomix`\n- **CCPM CLI** (for skills-search): `npm install -g @daymade\u002Fccpm`\n- **Promptfoo** (for promptfoo-evaluation): `npx promptfoo@latest`\n- **macOS + Xcode, XcodeGen** (for iOS-APP-developer)\n- **Codex CLI** (optional, for product-analysis multi-model mode)\n- **uv + openpyxl** (for excel-automation): `uv run --with openpyxl ...`\n- **macOS** (for capture-screen and excel-automation AppleScript control workflows)\n- **Python 3.8+** (for continue-claude-work): bundled script for session extraction (no external dependencies)\n- **uv + Scrapling CLI** (for scrapling-skill): `uv tool install 'scrapling[shell]'` and `scrapling install` for browser-backed fetches\n\n## ❓ FAQ\n\n### How do I know which skills to install?\n\nStart with **skill-creator** if you want to create your own skills. Otherwise, browse the [Other Available Skills](#-other-available-skills) section and install what matches your workflow.\n\n### Can I use these skills without Claude Code?\n\nNo, these skills are specifically designed for Claude Code. You'll need Claude Code 2.0.13 or higher.\n\n### How do I update skills?\n\nUse the same install command to update:\n```bash\nclaude plugin install skill-name@daymade-skills\n```\n\n### Can I contribute my own skill?\n\nAbsolutely! See [CONTRIBUTING.md](.\u002FCONTRIBUTING.md) for guidelines. We recommend using the skill-creator to ensure your skill meets quality standards.\n\n### Are these skills safe to use?\n\nYes, all skills are open-source and reviewed. The code is available in this repository for inspection.\n\n### How do Chinese users handle API access?\n\nWe recommend using [CC-Switch](https:\u002F\u002Fgithub.com\u002Ffarion1231\u002Fcc-switch) to manage API provider configurations. See the [Chinese User Guide](#-chinese-user-guide) section above.\n\n### What's the difference between skill-creator and other skills?\n\n**skill-creator** is a meta-skill - it helps you create other skills. The other skills are end-user skills that provide specific functionalities (GitHub ops, document conversion, etc.). If you want to extend Claude Code with your own workflows, start with skill-creator.\n\n---\n\n## 🤝 Contributing\n\nContributions are welcome! Please feel free to:\n\n1. Open issues for bugs or feature requests\n2. Submit pull requests with improvements\n3. Share feedback on skill quality\n\n### Skill Quality Standards\n\nAll skills in this marketplace follow:\n- Imperative\u002Finfinitive writing style\n- Progressive disclosure pattern\n- Proper resource organization\n- Comprehensive documentation\n- Tested and validated\n\n## 📄 License\n\nThis marketplace is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## ⭐ Support\n\nIf you find these skills useful, please:\n- ⭐ Star this repository\n- 🐛 Report issues\n- 💡 Suggest improvements\n- 📢 Share with your team\n\n## 🔗 Related Resources\n\n- [Claude Code Documentation](https:\u002F\u002Fdocs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code)\n- [Agent Skills Guide](https:\u002F\u002Fdocs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code\u002Fskills)\n- [Plugin Marketplaces](https:\u002F\u002Fdocs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code\u002Fplugin-marketplaces)\n- [Anthropic Skills Repository](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills)\n\n## 📞 Contact\n\n- **GitHub**: [@daymade](https:\u002F\u002Fgithub.com\u002Fdaymade)\n- **Email**: daymadev89@gmail.com\n- **Repository**: [daymade\u002Fclaude-code-skills](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills)\n\n---\n\n**Built with ❤️ using the skill-creator skill for Claude Code**\n\nLast updated: 2026-01-22 | Marketplace version 1.23.0\n","# Claude 代码技能市场\n\n\u003Cdiv align=\"center\">\n\n[![英语](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLanguage-English-blue)](.\u002FREADME.md)\n[![简体中文](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F语言-简体中文-red)](.\u002FREADME.zh-CN.md)\n\n[![许可证：MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n[![技能数量](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fskills-43-blue.svg)](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills)\n[![版本号](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fversion-1.39.0-green.svg)](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills)\n[![Claude Code](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClaude%20Code-2.0.13+-purple.svg)](https:\u002F\u002Fclaude.com\u002Fcode)\n[![欢迎提交 PR](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPRs-welcome-brightgreen.svg)](.\u002FCONTRIBUTING.md)\n[![维护状态](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMaintained%3F-yes-green.svg)](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\u002Fgraphs\u002Fcommit-activity)\n\n\u003C\u002Fdiv>\n\n专业的 Claude 代码技能市场，提供 43 种可直接用于生产的技能，以提升开发工作流效率。\n\n## 📑 目录\n\n- [🌟 核心技能：skill-creator](#-essential-skill-skill-creator)\n- [🚀 快速安装](#-quick-installation)\n- [🇨🇳 中文用户指南](#-chinese-user-guide)\n- [📦 其他可用技能](#-other-available-skills)\n- [🎬 交互式演示图库](#-interactive-demo-gallery)\n- [🎯 使用场景](#-use-cases)\n- [📚 文档](#-documentation)\n- [🛠️ 系统要求](#️-requirements)\n- [❓ 常见问题解答](#-faq)\n- [🤝 贡献](#-contributing)\n- [📄 许可证](#-license)\n\n---\n\n## 🌟 核心技能：skill-creator\n\n**⭐ 如果你想创建自己的技能，请从这里开始！**\n\n`skill-creator` 是一个元技能，它使你能够构建、验证和打包自己的 Claude 代码技能。它是本市场中最重要的工具，因为它赋予你扩展 Claude 代码功能的能力，以满足特定的工作流程需求。\n\n### 为什么选择这个 skill-creator？\n\n这是对 [Anthropic 官方 skill-creator](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills\u002Ftree\u002Fmain\u002Fskills\u002Fskill-creator) 的 **生产级增强分支**，源自于我们实际开发技能的经验，并且解决了官方版本未提及的各种问题。\n\n**官方的 skill-creator 只告诉你“应该做什么”，而我们的版本还告诉你“不应该尝试什么”——以及原因。**\n\n| 你在尝试... | 官方版本 | 这个分支 |\n|---------------------|----------|-----------|\n| 构建前的研究 | “检查可用的 MCP”（5 行） | 8 通道搜索协议与决策矩阵：采用 \u002F 扩展 \u002F 自建 |\n| 交互式创建技能 | 文本指令 | 9 个结构化的 AskUserQuestion 检查点——用户不会丢失上下文 |\n| 避免常见错误 | 无指导 | 缓存编辑警告、先决条件检查、安全扫描门控 |\n| 了解架构选项 | 未提及 | 内联与分叉决策指南及示例（选错会无声地破坏你的技能） |\n| 发布前验证 | 基本 YAML 检查 | 扩展验证器（所有 frontmatter 字段、路径引用完整性、空白问题） |\n| 捕获安全问题 | 无工具 | `security_scan.py` 结合 gitleaks 集成——打包前的硬性门槛 |\n| 从实际失败中学习 | 无失败案例 | 经过实战检验的方法论，附带记录的失败模式和陷阱 |\n\n**质量对比**（独立审计，8 个维度）：\n\n| 维度 | 官方版本 | 这个分支 |\n|-----------|----------|-----------|\n| 可操作性 | 7 | 9 |\n| 错误预防 | 5 | 9 |\n| 先行研究 | 4 | 9 |\n| 对照审查过程 | 4 | 8 |\n| 实战经验 | 3 | 8 |\n| 用户体验 | 4 | 9 |\n| **总分（满分 80）** | **42** | **65** |\n\n> 完整方法论：[skill-creator\u002Freferences\u002Fskill-development-methodology.md](.\u002Fskill-creator\u002Freferences\u002Fskill-development-methodology.md)\n\n### 快速安装\n\n**在 Claude Code 应用内：**\n```text\n\u002Fplugin marketplace add daymade\u002Fclaude-code-skills\n```\n\n然后：\n1. 选择 **浏览并安装插件**\n2. 选择 **daymade\u002Fclaude-code-skills**\n3. 选择 **skill-creator**\n4. 选择 **立即安装**\n\n**通过终端（CLI）：**\n```bash\nclaude plugin marketplace add https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\n# 市场名称：daymade-skills（来自 marketplace.json）\nclaude plugin install skill-creator@daymade-skills\n```\n\n### 你可以做什么\n\n安装 skill-creator 后，只需向 Claude Code 提出请求：\n\n```\n“在 ~\u002Fmy-skills 目录下创建一个名为 my-awesome-skill 的新技能”\n\n“验证位于 ~\u002Fmy-skills\u002Fmy-awesome-skill 的我的技能”\n\n“将位于 ~\u002Fmy-skills\u002Fmy-awesome-skill 的技能打包以便分发”\n```\n\n加载了 skill-creator 的 Claude Code 将引导你完成整个技能创建流程——从明确需求到最终打包发布。\n\n📚 **完整文档**：[skill-creator\u002FSKILL.md](.\u002Fskill-creator\u002FSKILL.md)\n\n### 实时演示\n\n**📝 初始化新技能**\n\n![初始化技能演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_1c2c4748b423.gif)\n\n**✅ 验证技能结构**\n\n![验证技能演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_e1a9b3ad3859.gif)\n\n**📦 打包技能以供分发**\n\n![打包技能演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_c9de46d4576a.gif)\n\n---\n\n## 🚀 快速安装\n\n### 在 Claude Code 应用内安装\n\n```text\n\u002Fplugin marketplace add daymade\u002Fclaude-code-skills\n```\n\n然后：\n1. 选择 **浏览并安装插件**\n2. 选择 **daymade\u002Fclaude-code-skills**\n3. 选择你需要的插件\n4. 选择 **立即安装**\n\n### 自动化安装（推荐）\n\n**macOS\u002FLinux：**\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fdaymade\u002Fclaude-code-skills\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n```\n\n**Windows（PowerShell）：**\n```powershell\niwr -useb https:\u002F\u002Fraw.githubusercontent.com\u002Fdaymade\u002Fclaude-code-skills\u002Fmain\u002Fscripts\u002Finstall.ps1 | iex\n```\n\n### 手动安装\n\n添加市场：\n```bash\nclaude plugin marketplace add https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\n```\n\n市场名称为 `daymade-skills`（来自 marketplace.json）。安装插件时请使用 `@daymade-skills`。请勿使用仓库路径作为市场名称（例如，`@daymade\u002Fclaude-code-skills` 会导致失败）。\n在 Claude Code 中，请使用 `\u002Fplugin ...` 斜杠命令；在终端中，则使用 `claude plugin ...`。\n\n**核心技能**（建议首次安装）：\n```bash\nclaude plugin install skill-creator@daymade-skills\n```\n\n**安装其他技能：**\n```bash\n# GitHub 操作\nclaude plugin install github-ops@daymade-skills\n\n# 文档转换\nclaude plugin install doc-to-markdown@daymade-skills\n\n# 图表生成\nclaude plugin install mermaid-tools@daymade-skills\n\n# 状态栏自定义\nclaude plugin install statusline-generator@daymade-skills\n\n# 团队沟通\nclaude plugin install teams-channel-post-writer@daymade-skills\n\n# Repomix 提取\nclaude plugin install repomix-unmixer@daymade-skills\n\n# AI\u002FLLM 图标\nclaude plugin install llm-icon-finder@daymade-skills\n\n# CLI 演示生成\nclaude plugin install cli-demo-generator@daymade-skills\n\n# Cloudflare 诊断\nclaude plugin install cloudflare-troubleshooting@daymade-skills\n\n# UI 设计系统提取\nclaude plugin install ui-designer@daymade-skills\n\n# 演示文稿制作\nclaude 插件安装 ppt-creator@daymade-skills\n\n# YouTube 视频\u002F音频下载\nclaude 插件安装 youtube-downloader@daymade-skills\n\n# 安全的 repomix 打包\nclaude 插件安装 repomix-safe-mixer@daymade-skills\n\n# ASR 文本转录校正\nclaude 插件安装 transcript-fixer@daymade-skills\n\n# 视频比较与质量分析\nclaude 插件安装 video-comparer@daymade-skills\n\n# 具有自主执行功能的 QA 测试基础设施\nclaude 插件安装 qa-expert@daymade-skills\n\n# 使用 EARS 方法论优化提示词\nclaude 插件安装 prompt-optimizer@daymade-skills\n\n# 会话历史恢复\nclaude 插件安装 claude-code-history-files-finder@daymade-skills\n\n# 文档整理\nclaude 插件安装 docs-cleaner@daymade-skills\n\n# 支持中文字体的 PDF 生成\nclaude 插件安装 pdf-creator@daymade-skills\n\n# CLAUDE.md 渐进式披露优化\nclaude 插件安装 claude-md-progressive-disclosurer@daymade-skills\n\n# CCPM 技能注册表搜索与管理\nclaude 插件安装 skills-search@daymade-skills\n\n# Promptfoo LLM 评估框架\nclaude 插件安装 promptfoo-evaluation@daymade-skills\n\n# iOS 应用开发\nclaude 插件安装 iOS-APP-developer@daymade-skills\n\n# Twitter\u002FX 内容抓取\nclaude 插件安装 twitter-reader@daymade-skills\n\n# 技能质量审查与提升\nclaude 插件安装 skill-reviewer@daymade-skills\n\n# GitHub 贡献策略\nclaude 插件安装 github-contributor@daymade-skills\n\n# Windows 远程桌面 \u002F AVD 连接诊断\nclaude 插件安装 windows-remote-desktop-connection-doctor@daymade-skills\n\n# 产品分析与优化\nclaude 插件安装 product-analysis@daymade-skills\n\n# 美国股票金融数据收集\nclaude 插件安装 financial-data-collector@daymade-skills\n\n# Excel 自动化：创建、解析及 macOS 控制\nclaude 插件安装 excel-automation@daymade-skills\n\n# 基于程序的 macOS 截图工作流\nclaude 插件安装 capture-screen@daymade-skills\n\n# 从本地会话文件中恢复中断的 Claude 工作\nclaude 插件安装 continue-claude-work@daymade-skills\n\n# Scrapling CLI 数据提取与故障排除\nclaude 插件安装 scrapling-skill@daymade-skills\n```\n\n每个技能都可以独立安装——只需选择你需要的即可！\n\n---\n\n## 🇨🇳 中文用户指南\n\n**针对中文用户：** 我们强烈推荐使用 [CC-Switch](https:\u002F\u002Fgithub.com\u002Ffarion1231\u002Fcc-switch) 来管理 Claude Code API 提供商配置。\n\nCC-Switch 让你能够：\n- ✅ 快速切换不同的 API 提供商（DeepSeek、通义千问、GLM 等）\n- ✅ 测试端点响应时间，找到最快的提供商\n- ✅ 管理 MCP 服务器配置\n- ✅ 自动备份并导入导出设置\n- ✅ 跨平台支持（Windows、macOS、Linux）\n\n**安装方法：** 从 [Releases](https:\u002F\u002Fgithub.com\u002Ffarion1231\u002Fcc-switch\u002Freleases) 下载，安装后添加你的 API 配置，并通过 UI 或系统托盘进行切换。\n\n### 完整的中文文档\n\n如需完整的中文文档，请参阅 [README.zh-CN.md](.\u002FREADME.zh-CN.md)。\n\n---\n\n## 📦 其他可用技能\n\n### 1. **github-ops** - GitHub 操作套件\n\n使用 gh CLI 和 GitHub API 的全面 GitHub 操作工具。\n\n**适用场景：**\n- 创建、查看或管理拉取请求\n- 管理问题和仓库设置\n- 查询 GitHub API 端点\n- 处理 GitHub Actions 工作流\n- 自动化 GitHub 操作\n\n**主要功能：**\n- 带 JIRA 集成的 PR 创建\n- 问题管理工作流\n- GitHub API（REST 和 GraphQL）操作\n- 工作流自动化\n- 企业版 GitHub 支持\n\n**🎬 实时演示**\n\n![GitHub Ops 演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_65679b1ee583.gif)\n\n---\n\n### 2. **doc-to-markdown** - 文档转换套件\n\n将文档转换为 Markdown，支持 Windows\u002FWSL 路径处理，并可提取 PDF 中的图片。\n\n**适用场景：**\n- 将 .doc\u002F.docx\u002FPDF\u002FPPTX 转换为 Markdown\n- 从 PDF 文件中提取图片\n- 处理 Confluence 导出文件\n- 处理 Windows\u002FWSL 路径转换\n\n**主要功能：**\n- 多格式文档转换\n- 使用 PyMuPDF 提取 PDF 图片\n- Windows\u002FWSL 路径自动化\n- Confluence 导出文件处理\n- 辅助脚本用于路径转换和图片提取\n\n**🎬 实时演示**\n\n![Markdown 工具演示](.\u002Fdemos\u002Fdoc-to-markdown\u002Fconvert-docs.gif)\n\n---\n\n### 3. **mermaid-tools** - 图表生成工具\n\n从 Markdown 中提取 Mermaid 图表，并生成高质量的 PNG 图像。\n\n**适用场景：**\n- 将 Mermaid 图表转换为 PNG\n- 从 Markdown 文件中提取图表\n- 处理包含图表的文档\n- 制作演示文稿级别的可视化内容\n\n**主要功能：**\n- 自动提取图表\n- 高分辨率 PNG 生成\n- 根据图表类型智能调整大小\n- 可自定义尺寸和缩放比例\n- WSL2 Chrome\u002FPuppeteer 支持\n\n**🎬 实时演示**\n\n![Mermaid 工具演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_14efada40ccf.gif)\n\n---\n\n### 4. **statusline-generator** - 状态栏自定义工具\n\n配置 Claude Code 状态栏，支持多行布局和费用跟踪。\n\n**适用场景：**\n- 自定义 Claude Code 状态栏\n- 添加费用跟踪（会话\u002F每日）\n- 显示 Git 状态\n- 适用于窄屏的多行布局\n- 颜色自定义\n\n**主要功能：**\n- 多行状态栏布局\n- 集成 ccusage 费用统计\n- Git 分支状态指示器\n- 可自定义颜色\n- 针对竖屏优化\n\n**🎬 实时演示**\n\n![状态栏生成器演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_138d9a84c202.gif)\n\n---\n\n### 5. **teams-channel-post-writer** - Teams 沟通工具\n\n创建用于内部知识分享的教育类 Teams 频道帖子。\n\n**适用场景：**\n- 编写关于功能的 Teams 帖子\n- 分享 Claude Code 最佳实践\n- 记录经验教训\n- 发布内部公告\n- 教授有效的提示词模式\n\n**主要功能：**\n- 结构成熟的帖子模板\n- 高质量内容写作指南\n- “普通 vs 更好” 示例模式\n- 强调底层原理\n- 即用型 Markdown 模板\n\n**🎬 实时演示**\n\n![Teams 频道帖子撰写演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_e48d6082e10f.gif)\n\n---\n\n### 6. **repomix-unmixer** - 仓库解压工具\n\n从 repomix 打包的仓库中提取文件，并恢复目录结构。\n\n**适用场景：**\n- 解压 repomix 输出文件\n- 提取打包的仓库内容\n- 恢复文件结构\n- 审查 repomix 内容\n- 将 repomix 转换为可用文件\n\n**主要功能：**\n- 支持多种格式（XML、Markdown、JSON）\n- 自动检测文件格式\n- 保留目录结构\n- 支持 UTF-8 编码\n- 全面的验证流程\n\n**🎬 实时演示**\n\n![Repomix 解压演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_fa124d5ae642.gif)\n\n---\n\n### 7. **llm-icon-finder** - AI\u002FLLM 品牌图标查找工具\n\n从 lobe-icons 库中获取 100 多个 AI 模型和 LLM 提供商的品牌图标。\n\n**适用场景：**\n- 查找 AI 模型或提供商的品牌图标\n- 下载 Claude、GPT、Gemini 等的 logo\n- 获取多种格式的图标（SVG\u002FPNG\u002FWEBP）\n- 构建 AI 工具文档\n- 制作关于 LLM 的演示文稿\n\n**核心功能：**\n- 100+ 个 AI\u002FLLM 模型图标\n- 支持多种格式（SVG、PNG、WEBP）\n- 可生成直接访问的 URL\n- 支持本地下载\n- 图标目录可搜索\n\n**🎬 实时演示**\n\n![LLM 图标查找工具演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_ac372876ec88.gif)\n\n---\n\n### 8. **cli-demo-generator** - CLI 演示生成工具\n\n使用 VHS 自动化功能，生成专业的动画 CLI 演示和终端录制视频。\n\n**适用场景：**\n- 为文档制作演示\n- 将终端工作流程录制为 GIF 动画\n- 生成动画教程\n- 批量生成多个演示\n- 展示 CLI 工具\n\n**核心功能：**\n- 根据命令列表自动生成演示\n- 支持 YAML\u002FJSON 配置文件进行批量处理\n- 使用 asciinema 进行交互式录制\n- 根据命令复杂度智能调整时间\n- 多种输出格式（GIF、MP4、WebM）\n- 提供 VHS 磁带风格的文件模板\n\n**🎬 实时演示**\n\n![CLI 演示生成工具演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_1af0c07fd9d7.gif)\n\n---\n\n### 9. **cloudflare-troubleshooting** - Cloudflare 诊断工具\n\n通过 API 驱动的数据收集，调查并解决 Cloudflare 配置问题。\n\n**适用场景：**\n- 网站出现“ERR_TOO_MANY_REDIRECTS”错误\n- SSL\u002FTLS 配置错误\n- DNS 解析问题\n- 其他与 Cloudflare 相关的问题\n\n**核心功能：**\n- 基于证据的诊断方法\n- 全面的 Cloudflare API 参考\n- SSL\u002FTLS 模式故障排除（Flexible、Full、Strict）\n- DNS、缓存和防火墙诊断\n- 提供辅助脚本的代理式操作方式\n\n**🎬 实时演示**\n\n![Cloudflare 诊断工具演示](.\u002Fdemos\u002Fcloudflare-troubleshooting\u002Fdiagnose-redirect-loop.gif)\n\n---\n\n### 10. **ui-designer** - UI 设计系统提取工具\n\n从参考 UI 图片中提取设计系统，并生成可直接用于开发的设计提示。\n\n**适用场景：**\n- 需要分析 UI 截图或原型\n- 需要提取颜色方案、字体排版和间距规范\n- 构建符合参考美学的 MVP UI\n- 创建一致的设计系统\n- 生成多种 UI 变体\n\n**核心功能：**\n- 从图片中系统化提取设计系统\n- 分析颜色方案、字体排版和组件\n- 交互式生成 MVP PRD\n- 基于模板的工作流（设计系统 → PRD → 实现提示）\n- 生成多版本 UI（3 种移动端、2 种网页端）\n- 支持 React + Tailwind CSS + Lucide 图标\n\n**🎬 实时演示**\n\n![UI 设计师演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_158f7eb336a3.gif)\n\n---\n\n### 11. **ppt-creator** - 专业演示文稿制作工具\n\n根据主题或文档，结合数据驱动的图表，创建具有说服力且适合观众的幻灯片，并输出双格式 PPTX 文件。\n\n**适用场景：**\n- 制作演示文稿、商业提案或主题演讲\n- 需要结构化的内容和专业的叙事方式\n- 要求数据可视化和图表\n- 希望获得包含演讲者备注的完整 PPTX 文件\n- 构建业务回顾或产品推介\n\n**核心功能：**\n- 金字塔原理结构（结论→理由→证据）\n- 论点-证据式幻灯片框架\n- 自动合成数据并生成图表（matplotlib）\n- 双路径 PPTX 创建（Marp CLI + document-skills:pptx）\n- 完整编排：内容→数据→图表→带图表的 PPTX\n- 每张幻灯片配有 45-60 秒的演讲者备注\n- 质量评分与自动优化（目标：75\u002F100）\n\n**🎬 实时演示**\n\n![PPT 创造者演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_a17295906e62.gif)\n\n---\n\n### 12. **youtube-downloader** - YouTube 视频及音频下载器\n\n使用 yt-dlp 下载 YouTube 视频和音频，具备强大的错误处理能力，并针对常见问题提供自动解决方案。\n\n**适用场景：**\n- 下载 YouTube 视频或播放列表\n- 从 YouTube 视频中提取 MP3 格式的音频\n- 经常遇到 yt-dlp 下载失败或 nsig 提取错误的情况\n- 需要帮助选择格式或质量选项\n- 在受访问限制的地区处理 YouTube 内容\n\n**核心功能：**\n- 自动 PO Token 提供程序（优先使用 Docker，备用浏览器），以确保高质量访问\n- 浏览器 Cookie 验证，用于应对“不是机器人”的提示（隐私友好）\n- 仅下载音频并转换为 MP3\n- 列出可用格式并支持自定义选择\n- 可自定义输出目录\n- 支持代理下载，适用于受限环境\n\n**🎬 实时演示**\n\n![YouTube 下载器演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_readme_56856411bc65.gif)\n\n---\n\n### 13. **repomix-safe-mixer** - 安全的 Repomix 打包工具\n\n使用 repomix 安全打包代码库，可在打包前自动检测并移除硬编码的凭证信息。\n\n**适用场景：**\n- 使用 repomix 打包代码以分发或共享\n- 从专有代码库中创建参考包\n- 担心意外暴露凭证信息的安全隐患\n- 在提交前对硬编码密钥进行安全检查\n- 审计代码库是否存在凭证泄露风险\n\n**核心功能：**\n- 检测 20 多种凭证模式（AWS、Supabase、Stripe、OpenAI 等）\n- 扫描→报告→打包的工作流程，并自动阻止危险操作\n- 独立的安全扫描器，可用于预提交钩子\n- 提供环境变量替换建议\n- JSON 输出，便于与 CI\u002FCD 集成\n- 支持排除模式，以处理误报情况\n\n**🎬 实时演示**\n\n*即将上线*\n\n---\n\n### 14. **transcript-fixer** - ASR 转录修正工具\n\n通过基于词典的规则和 AI 驱动的修正，结合自动模式学习，纠正语音转文字（ASR\u002FSTT）转录中的错误。\n\n**适用场景：**\n- 修正会议记录、讲座录音或访谈转录\n- 纠正中英文同音异义词错误以及技术术语\n- 构建领域特定的修正词典\n- 通过迭代学习提升转录准确率\n- 与团队协作构建共享的修正知识库\n\n**核心功能：**\n- 两阶段修正流程（词典+AI）\n- 自动检测和学习模式\n- 领域特定词典（通用、embodied_ai、金融、医疗）\n- 基于 SQLite 的修正数据库\n- 支持团队协作，可导入导出\n- 集成 GLM API 进行 AI 修正\n- 通过词典推广实现成本优化\n\n**示例工作流程：**\n```bash\n# 初始化并添加修正\nuv run scripts\u002Ffix_transcription.py --init\nuv run scripts\u002Ffix_transcription.py --add \"错误词\" \"正确词\" --domain general\n\n# 运行完整的修正流程\nuv run scripts\u002Ffix_transcription.py --input meeting.md --stage 3\n\n# 之前（模糊）\n“帮我做一个密码重置功能”\n\n# 经过 EARS 转换后（7 个原子需求）\n1. 当用户点击“忘记密码”时，系统应显示邮箱输入框。\n2. 当用户提交有效邮箱时，系统应发送有效期为 1 小时的密码重置链接。\n3. 当用户点击重置链接时，系统应验证令牌未过期。\n4. 当令牌有效时，系统应显示密码创建表单，要求至少包含 12 个字符、1 个大写字母、1 个数字和 1 个特殊字符。\n5. 当用户提交符合要求的新密码时，系统应使用 bcrypt 对密码进行哈希处理，并使重置令牌失效。\n6. 当用户在 1 小时内尝试密码重置超过 3 次时，系统应阻止进一步尝试，持续 1 小时。\n7. 如果重置令牌已过期，系统应显示错误信息及请求新链接的选项。\n\n# 结合领域理论增强\n- 零信任架构（每一步都进行验证）\n- 多层防御（速率限制 + 令牌过期 + 密码复杂度）\n- 渐进式披露（多步骤用户体验流程）\n\n# 完整提示包括角色、技能、工作流、示例和格式\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [prompt-optimizer\u002Freferences\u002F](.\u002Fprompt-optimizer\u002Freferences\u002F) 获取：\n- `ears_syntax.md` - 完整的 EARS 模式与转换规则\n- `domain_theories.md` - 40 多种映射到各领域的理论及选择指南\n- `examples.md` - 包含转换前后的完整示例\n\n**💡 创新点**：EARS 方法论通过强制明确条件、触发器和可衡量标准来消除歧义。结合领域理论基础（如 GTD、BJ Fogg、格式塔等），它能将“构建一个待办事项应用”转化为包含行为心理学原理、用户体验最佳实践和具体测试用例的完整规范，从而实现从第一天起就以测试驱动开发的方式进行开发。\n\n---\n\n### 18. **claude-code-history-files-finder** - Claude Code 会话历史文件查找工具\n\n用于查找并恢复存储在 `~\u002F.claude\u002Fprojects\u002F` 中的 Claude Code 会话历史文件内容。\n\n**适用场景：**\n- 恢复之前 Claude Code 会话中被删除或丢失的文件\n- 在会话历史中搜索特定代码\n- 跟踪多个会话中的文件修改情况\n- 查找包含特定关键字或实现的会话\n\n**主要功能：**\n- **会话搜索**：按关键字查找会话，并按出现频率排序\n- **内容恢复**：从 Write 工具调用中提取文件，并去除重复内容\n- **统计分析**：消息数量、工具使用情况分解、文件操作记录\n- **批量处理**：支持对多个会话进行关键词筛选处理\n- **流式处理**：高效处理大型会话文件（>100MB）\n\n**使用示例：**\n```bash\n# 列出某个项目的近期会话\npython3 scripts\u002Fanalyze_sessions.py list \u002Fpath\u002Fto\u002Fproject\n\n# 搜索会话中的关键字\npython3 scripts\u002Fanalyze_sessions.py search \u002Fpath\u002Fto\u002Fproject \"ComponentName\" \"featureX\"\n\n# 从会话中恢复已删除的文件\npython3 scripts\u002Frecover_content.py ~\u002F.claude\u002Fprojects\u002F...\u002Fsession.jsonl -k DeletedComponent -o .\u002Frecovered\u002F\n\n# 获取会话统计信息\npython3 scripts\u002Fanalyze_sessions.py stats \u002Fpath\u002Fto\u002Fsession.jsonl --show-files\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [claude-code-history-files-finder\u002Freferences\u002F](.\u002Fclaude-code-history-files-finder\u002Freferences\u002F) 获取：\n- `session_file_format.md` - JSONL 格式结构及提取模式\n- `workflow_examples.md` - 详细的恢复和分析工作流程\n\n---\n\n### 19. **docs-cleaner** - 文档整合工具\n\n整合冗余文档，同时保留所有有价值的内容。\n\n**适用场景：**\n- 清理项目中的文档膨胀问题\n- 合并覆盖相同主题的冗余文档\n- 在快速开发后减少文档散乱现象\n- 将多个文件整合为权威来源\n\n**主要功能：**\n- **内容保留**：清理过程中绝不会丢失有价值的信息\n- **冗余检测**：识别重复的文档内容\n- **智能合并**：在保持结构的同时合并相关文档\n- **验证**：确保整合后的文档完整且准确\n\n**🎬 实时演示**\n\n*即将推出*\n\n---\n\n### 20. **skills-search** - CCPM 技能注册表搜索工具\n\n从 CCPM（Claude Code 插件管理器）注册表中搜索、发现、安装和管理 Claude Code 技能。\n\n**适用场景：**\n- 为特定任务寻找技能（例如，“查找 PDF 相关技能”）\n- 按名称安装技能\n- 列出当前已安装的技能\n- 获取某项技能的详细信息\n- 管理自己的 Claude Code 技能库\n\n**主要功能：**\n- **注册表搜索**：使用 `ccpm search \u003Cquery>` 搜索 CCPM 注册表\n- **技能安装**：使用 `ccpm install \u003Cskill-name>` 安装技能\n- **版本支持**：可通过 `@version` 语法安装指定版本\n- **捆绑安装**：安装预配置的技能包（Web 开发、内容创作、开发者工具等）\n- **多种格式**：支持注册表名称、GitHub 用户名\u002F仓库名以及完整 URL\n- **技能信息**：使用 `ccpm info \u003Cskill-name>` 获取技能详细信息\n\n**使用示例：**\n```bash\n# 搜索技能\nccpm search pdf              # 查找 PDF 相关技能\nccpm search \"code review\"    # 查找代码审查技能\n\n# 安装技能\nccpm install skill-creator                # 从注册表安装\nccpm install daymade\u002Fskill-creator        # 从 GitHub 安装\nccpm install skill-creator@1.0.0          # 安装特定版本\n\n# 列出并管理\nccpm list                    # 列出已安装的技能\nccpm info skill-creator      # 获取技能详情\nccpm uninstall pdf-processor # 卸载某项技能\n\n# 安装技能包\nccpm install-bundle web-dev  # 安装 Web 开发技能包\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [skills-search\u002FSKILL.md](.\u002Fskills-search\u002FSKILL.md) 获取完整的命令参考。\n\n**要求**：CCPM CLI（`npm install -g @daymade\u002Fccpm`）\n\n---\n\n### 21. **pdf-creator** - 支持中文字体的 PDF 创建工具\n\n使用 WeasyPrint 将 Markdown 转换为具有正确中文字体排版的专业 PDF 文档。\n\n**适用场景：**\n- 将 Markdown 转换为 PDF 用于分享或打印\n- 生成正式文档（法律文件、报告等）\n- 确保中文字体正确渲染\n\n**主要功能：**\n- WeasyPrint + Markdown 转换流水线\n- 内置中文字体回退机制\n- 默认 A4 布局，带有适合打印的页边距\n- 批量转换脚本\n\n**使用示例：**\n```bash\nuv run --with weasyprint --with markdown scripts\u002Fmd_to_pdf.py input.md output.pdf\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [pdf-creator\u002FSKILL.md](.\u002Fpdf-creator\u002FSKILL.md) 获取设置和工作流程详情。\n\n**要求**：Python 3.8+、`weasyprint`、`markdown`\n\n---\n\n### 22. **claude-md-progressive-disclosurer** - CLAUDE.md 优化\n\n使用渐进式披露优化用户的 CLAUDE.md 文件，以减少上下文膨胀，同时保留关键规则。\n\n**适用场景：**\n- CLAUDE.md 过于冗长或重复\n- 需要将详细流程移至参考文档\n- 希望将可重用的工作流提取为技能\n\n**主要功能：**\n- 段落分类（保留\u002F移动\u002F提取\u002F删除）\n- 优化前后的行数报告\n- 参考文件和指针格式\n- 最佳实践优化工作流\n\n**示例用法：**\n```\n“使用渐进式披露优化我的 ~\u002F.claude\u002FCLAUDE.md，并提出一个计划。”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [claude-md-progressive-disclosurer\u002FSKILL.md](.\u002Fclaude-md-progressive-disclosurer\u002FSKILL.md)。\n\n---\n\n### 23. **promptfoo-evaluation** - Promptfoo LLM 评估\n\n使用 Promptfoo 配置并运行 LLM 评估，用于提示测试和模型比较。\n\n**适用场景：**\n- 设置提示测试和评估配置\n- 比较不同提供商的 LLM 输出\n- 添加自定义断言或由 LLM 作为裁判进行评分\n\n**主要功能：**\n- promptfooconfig.yaml 模板\n- Python 自定义断言\n- llm-rubric 评分指南\n- 内置预览（echo provider）工作流\n\n**示例用法：**\n```bash\nnpx promptfoo@latest init\nnpx promptfoo@latest eval\nnpx promptfoo@latest view\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [promptfoo-evaluation\u002Freferences\u002Fpromptfoo_api.md](.\u002Fpromptfoo-evaluation\u002Freferences\u002Fpromptfoo_api.md)。\n\n**要求**：Node.js（通过 `npx promptfoo@latest` 使用 Promptfoo）\n\n---\n\n### 24. **iOS-APP-developer** - iOS 应用开发\n\n使用 XcodeGen、SwiftUI 和 Swift Package Manager 构建、配置和调试 iOS 应用。\n\n**适用场景：**\n- 设置 XcodeGen `project.yml`\n- 修复 SPM 依赖或嵌入问题\n- 处理代码签名和设备部署错误\n- 调试相机\u002FAVFoundation 相关问题\n\n**主要功能：**\n- XcodeGen 项目模板\n- SPM 动态框架嵌入修复\n- 代码签名和配置文件指导\n- 设备部署和故障排除检查清单\n\n**示例用法：**\n```bash\nxcodegen generate\nxcodebuild -destination 'platform=iOS Simulator,name=iPhone 17' build\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [iOS-APP-developer\u002Freferences\u002Fxcodegen-full.md](.\u002FiOS-APP-developer\u002Freferences\u002Fxcodegen-full.md)。\n\n**要求**：macOS + Xcode、XcodeGen\n\n---\n\n### 25. **twitter-reader** - Twitter\u002FX 内容抓取\n\n使用 Jina.ai API 抓取 Twitter\u002FX 帖子内容，无需认证即可绕过 JavaScript 限制。\n\n**适用场景：**\n- 获取推文内容用于分析或记录\n- 抓取线程回复和对话上下文\n- 提取帖子中的图片和媒体\n- 批量下载多条推文以供参考\n\n**主要功能：**\n- 无需 JavaScript 渲染或浏览器自动化\n- 无需 Twitter 认证\n- 返回包含元数据的 Markdown 格式内容\n- 支持单条和批量抓取\n- 包含作者、时间戳、帖子文本、图片和回复\n- 环境变量配置用于安全管理 API 密钥\n\n**示例用法：**\n```bash\n# 设置您的 Jina API 密钥（从 https:\u002F\u002Fjina.ai\u002F 获取）\nexport JINA_API_KEY=\"your_api_key_here\"\n\n# 抓取单条推文\ncurl \"https:\u002F\u002Fr.jina.ai\u002Fhttps:\u002F\u002Fx.com\u002FUSER\u002Fstatus\u002FTWEET_ID\" \\\n  -H \"Authorization: Bearer ${JINA_API_KEY}\"\n\n# 批量抓取多条推文\nscripts\u002Ffetch_tweets.sh \\\n  \"https:\u002F\u002Fx.com\u002Fuser\u002Fstatus\u002F123\" \\\n  \"https:\u002F\u002Fx.com\u002Fuser\u002Fstatus\u002F456\"\n\n# 使用 Python 脚本抓取并保存到文件\npython scripts\u002Ffetch_tweet.py https:\u002F\u002Fx.com\u002Fuser\u002Fstatus\u002F123 output.md\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [twitter-reader\u002FSKILL.md](.\u002Ftwitter-reader\u002FSKILL.md)，了解完整详情及 URL 格式支持。\n\n**要求**：\n- **Jina.ai API 密钥**（从 https:\u002F\u002Fjina.ai\u002F 获取——提供免费层级）\n- **curl**（大多数系统已预装）\n- **Python 3.6+**（用于 Python 脚本）\n\n---\n\n### 26. **macos-cleaner** - 智能 macOS 磁盘空间清理工具\n\n**在 macOS 上安全回收磁盘空间的最佳方式。** 通过智能分类和交互式清理，分析系统缓存、应用程序残留文件、大文件以及开发环境。\n\n**macos-cleaner 的独特之处：**\n- **安全第一理念**：绝不未经用户明确确认就删除任何内容。每项操作都会进行风险评估（🟢 安全 \u002F 🟡 谨慎 \u002F 🔴 保留）。\n- **智能优先于自动化**：先分析、充分解释，再由您决定。不同于一键清理工具的盲目删除，我们会帮助您理解将要移除的内容及其原因。\n- **开发者友好**：深度分析 Docker、Homebrew、npm、pip 缓存——这些是通用清理工具容易忽略的部分。\n- **透明且具有教育意义**：每条建议都包含文件的详细说明、是否安全的理由，以及删除后的影响。\n- **专业品质**：由深知误删重要文件痛苦的开发者打造。内置全面的安全检查及 Time Machine 备份建议。\n\n**设计原则：**\n1. **用户控制优先**：决策权在您手中，我们提供洞察力。\n2. **解释一切**：无神秘删除——完全透明地展示影响。\n3. **保守默认**：不确定时，宁可保留也不轻易删除。\n4. **开发者视角**：不仅关注系统文件，还深入理解开发工具缓存。\n5. **混合方法**：结合脚本的精准性与可视化工具（Mole 集成）。\n\n**适用场景：**\n- Mac 磁盘空间不足（已使用超过 80%）\n- 开发者拥有大量 Docker\u002Fnpm\u002Fpip\u002FHomebrew 缓存\n- 希望了解占用空间的具体内容，而非盲目删除\n- 需要清理已卸载应用的残留数据\n- 更倾向于理解而非自动化处理\n\n**核心功能：**\n- **智能缓存分析**：按安全级别分类系统缓存、应用缓存和日志。\n- **应用残留检测**：高置信度识别未卸载应用的遗留数据。\n- **大文件发现**：智能分类视频、压缩包、数据库、磁盘镜像、构建产物等。\n- **开发环境清理**：Docker（镜像、容器、卷、构建缓存）、Homebrew、npm、pip、旧 Git 仓库。\n- **交互式安全删除**：批量确认、选择性删除，并支持撤销操作（尽可能使用废纸篓）。\n- **清理前后报告**：提供详细的磁盘空间恢复情况。\n- **Mole 集成**：无缝对接可视化清理工具，满足 GUI 偏好。\n- **风险分类**：每个项目均标注安全级别及说明。\n- **Time Machine 提示**：建议在执行大规模删除（超过 10 GB）前进行备份。\n\n**我们的与众不同之处：**\n- ✅ **以透明赢得信任**：其他清理工具往往隐藏删除内容。而我们则会逐一展示并解释原因。\n- ✅ **开发者导向**：我们清理的是 Docker 缓存，而非仅浏览器缓存。我们理解 `.git` 目录、`node_modules` 和构建产物。\n- ✅ **内置安全检查**：防止误删系统文件、用户数据、凭据、正在使用的数据库或文件。\n- ✅ **教育性**：让您了解哪些内容可以安全删除以及原因，从而更自信地维护您的 Mac。\n- ❌ **非一键解决方案**：我们不会自动删除。如果您只想“立即清理所有内容”，请使用其他工具。我们专为希望掌控清理过程的用户设计。\n\n**使用示例：**\n```bash\n# 安装插件\nclaude plugin install macos-cleaner@daymade-skills\n\n# 请求 Claude Code 分析您的 Mac\n“我的 Mac 存储空间快满了，帮我分析一下是什么占用了空间。”\n\nClaude 将：\n# 1. 执行全面磁盘分析\n# 2. 展示分类结果及安全等级\n# 3. 解释每一类内容（缓存、残留、大文件、开发工具）\n# 4. 推荐清理方案\n# 5. 仅在您确认后执行清理\n\n示例分析输出：\n📊 磁盘空间分析\n━━━━━━━━━━━━━━━━━━━━━━━━\n总容量：     500 GB\n已用：      450 GB (90%)\n可用：      50 GB (10%)\n\n🟢 可安全清理（95 GB）：\n  - 系统缓存：     45 GB（应用可自动重新生成）\n  - Homebrew 缓存：     5 GB（需要时可重新安装）\n  - npm 缓存：          3 GB（可安全清除）\n  - 旧日志：           8 GB（仅用于诊断）\n  - 废纸篓：             34 GB（已标记为待删除）\n\n🟡 建议复查（62 GB）：\n  - 大型下载文件：   38 GB（可能包含重要文件）\n  - 应用残留：       8 GB（需确认应用是否已彻底卸载）\n  - Docker 镜像：     12 GB（可能正在使用中）\n  - 旧 .git 仓库：     4 GB（需确认项目是否已归档）\n\n🔴 除非确定，否则保留（0 GB）：\n  - 未检测到高风险项目\n\n建议：先从 🟢 安全项目开始（95 GB），再一起审查 🟡 项目。\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [macos-cleaner\u002Freferences\u002F](.\u002Fmacos-cleaner\u002Freferences\u002F) 获取：\n- `cleanup_targets.md` - 每个清理目标的详细说明\n- `mole_integration.md` - 如何将脚本与 Mole 可视化工具结合\n- `safety_rules.md` - 全面的安全指南及绝对不可删除的内容清单\n\n**要求**：\n- **Python 3.6+**（macOS 自带）\n- **macOS**（已在 macOS 10.15 及以上版本测试）\n- **可选**：[Mole](https:\u002F\u002Fgithub.com\u002Ftw93\u002FMole) 用于可视化清理界面\n\n---\n\n### 27. **fact-checker** - 文档事实核查工具\n\n利用网络搜索和官方来源验证文档中的事实性陈述，并在用户确认后提出修改建议。\n\n**适用场景：**\n- 核实文档内容的准确性\n- 验证 AI 模型规格和技术文档\n- 更新文档中的过时信息\n- 校验统计声明和基准数据\n- 检查 API 功能和版本号\n\n**核心功能：**\n- 集成权威来源的网络搜索\n- AI 模型规格验证\n- 技术文档准确性检查\n- 统计数据验证\n- 自动化修正报告，需用户确认\n- 支持一般事实陈述和技术性主张\n\n**使用示例：**\n```bash\n# 安装插件\nclaude plugin install fact-checker@daymade-skills\n\n# 核实文档内容\n“请核实这段关于 AI 模型能力的文字。”\n\n# 验证技术规格\n“请检查这些 Claude 模型规格是否仍然准确。”\n\n# 更新过时信息\n“请核实并更新这份文档中的版本号。”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [fact-checker\u002FSKILL.md](.\u002Ffact-checker\u002FSKILL.md) 了解完整工作流程和适用的声明类型。\n\n**要求**：\n- 可访问网络搜索（通过 Claude Code）\n\n---\n\n### 28. **skill-reviewer** - 技能质量评审与改进\n\n通过三种强大模式，依据官方最佳实践对 Claude Code 技能进行评审和优化。\n\n**适用场景：**\n- 在发布前验证自己的技能\n- 评估他人的技能仓库\n- 通过自动 PR 为开源技能贡献改进建议\n- 确保技能符合市场规范\n\n**核心功能：**\n- **自评模式**：通过技能创建者脚本运行自动化验证\n- **外部评审模式**：克隆、分析并生成改进建议报告\n- **自动 PR 模式**：分叉 → 改进 → 提交仅包含新增内容的 PR\n- **评估检查清单**：验证 frontmatter、说明文档及资源文件\n- **仅添加原则**：在为他人贡献时绝不删除任何文件\n- **PR 编写指南**：语气建议与专业模板\n- **自动安装依赖**：若缺少技能创建者工具，则自动安装\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install skill-reviewer@daymade-skills\n\n# 自我评审技能\n\"验证位于 ~\u002Fmy-skills\u002Fmy-awesome-skill 的我的技能\"\n\n# 评审外部技能仓库\n\"评审位于 https:\u002F\u002Fgithub.com\u002Fuser\u002Fskill-repo 的技能\"\n\n# 自动提交 PR 改进\n\"分叉、改进并为 https:\u002F\u002Fgithub.com\u002Fuser\u002Fskill-repo 提交 PR\"\n```\n\n**🎬 实时演示**\n\n*即将上线*\n\n📚 **文档**：请参阅 [skill-reviewer\u002Freferences\u002F](.\u002Fskill-reviewer\u002Freferences\u002F) 获取：\n- `evaluation_checklist.md` - 完整的技能评估标准\n- `pr_template.md` - 专业的 PR 描述模板\n- `marketplace_template.json` - 市场配置模板\n\n---\n\n### 29. **github-contributor** - GitHub 贡献策略\n\n成为高效 GitHub 贡献者并建立开源声誉的战略指南。\n\n**适用场景：**\n- 寻找可参与的项目\n- 学习贡献最佳实践\n- 打造个人 GitHub 影响力与声誉\n- 掌握如何撰写高质量 PR\n\n**核心功能：**\n- **四种贡献类型**：文档、代码质量、Bug 修复、功能开发\n- **项目选择标准**：哪些是适合初次参与的好项目，哪些需警惕\n- **PR 卓越流程**：提交前 → 过程中 → 提交后检查清单\n- **声誉提升阶梯**：文档 → Bug 修复 → 功能开发 → 维护者\n- **GitHub CLI 命令**：快速参考分叉、PR、问题操作\n- **Conventional Commit 格式**：类型、范围、描述结构\n- **常见错误**：应避免的行为及最佳实践\n\n**贡献类型详解：**\n```\n第一级：文档修正（门槛最低，影响巨大）\n    ↓（积累熟悉度）\n第二级：代码质量（中等投入，展现技术能力）\n    ↓（理解代码库）\n第三级：Bug 修复（高影响力，建立信任）\n    ↓（成为可信贡献者）\n第四级：功能添加（曝光度最高）\n    ↓（可能成为维护者）\n```\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install github-contributor@daymade-skills\n\n# 查找优质新手任务\n\"帮我找到 Python 领域适合新手参与的项目\"\n\n# 撰写高质量 PR\n\"指导我完成这个 Bug 修复的 PR 创建\"\n\n# 制定贡献策略\n\"帮我规划一个用于提升 GitHub 个人主页影响力的贡献策略\"\n```\n\n**🎬 实时演示**\n\n*即将上线*\n\n📚 **文档**：请参阅 [github-contributor\u002Freferences\u002F](.\u002Fgithub-contributor\u002Freferences\u002F) 获取：\n- `pr_checklist.md` - 完整的 PR 质量检查清单\n- `project_evaluation.md` - 如何评估适合参与的项目\n- `communication_templates.md` - 问题与 PR 沟通模板\n\n---\n\n### 31. **i18n-expert** - 国际化与本地化\n\n为 UI 代码库提供完整的国际化\u002F本地化设置与审计。配置 i18n 框架，将硬编码字符串替换为翻译键，确保 en-US 和 zh-CN 之间的语言环境一致性，并验证复数形式及格式化是否正确。\n\n**适用场景：**\n- 为新的 React\u002FNext.js\u002FVue 应用程序设置 i18n\n- 审计现有 i18n 实现，确保翻译键的完整性和一致性\n- 将硬编码字符串替换为翻译键\n- 确保错误码正确映射到本地化消息\n- 验证不同语言环境下复数形式、日期\u002F时间\u002F数字格式的一致性\n- 实现多语言切换及 SEO 元数据本地化\n\n**核心功能：**\n- 选择并设置库（react-i18next、next-intl、vue-i18n）\n- 键架构与语言文件组织（JSON、YAML、PO、XLIFF）\n- 翻译生成策略（AI、专业翻译、手动）\n- 路由与语言检测\u002F切换\n- SEO 与元数据本地化\n- 对适用语言的支持 RTL 布局\n- en-US 与 zh-CN 之间翻译键的一致性验证\n- 复数形式与格式化验证\n- 错误码到本地化消息的映射\n- 内置 i18n_audit.py 脚本用于提取键使用情况\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install i18n-expert@daymade-skills\n\n# 为新项目设置 i18n\n\"为我的 React 应用程序设置支持英语和中文的 i18n\"\n\n# 审计现有 i18n 实施\n\"审计当前的 i18n 设置，找出缺失的翻译键\"\n\n# 替换硬编码字符串\n\"将此组件中的所有硬编码字符串替换为 i18n 键\"\n```\n\n**🎬 实时演示**\n\n*即将上线*\n\n📚 **文档**：请参阅 [i18n-expert\u002FSKILL.md](.\u002Fi18n-expert\u002FSKILL.md) 获取完整的工作流程与架构指导。\n\n**要求：**\n- **Python 3.6+**（用于审计脚本）\n- **React\u002FNext.js\u002FVue**（特定框架的 i18n 库）\n\n---\n\n### 32. **claude-skills-troubleshooting** - 插件与技能故障排除\n\n诊断并解决 Claude Code 插件和技能配置问题。通过系统化的流程调试插件安装、启用及激活过程中出现的各种问题。\n\n**适用场景：**\n- 插件已安装但未显示在可用技能列表中\n- 技能虽已安装却未能正常激活\n- 调试 settings.json 中的 enabledPlugins 配置\n- 排查“插件无法工作”或“技能未显示”的问题\n- 理解插件状态架构及其生命周期\n\n**核心功能：**\n- 通过诊断脚本快速定位问题（检测已安装但未启用的情况）\n- 插件状态架构文档（installed_plugins.json 与 settings.json 的区别）\n- 市场缓存新鲜度检测及更新指南\n- 已知 GitHub 问题追踪（#17832、#19696、#17089、#13543、#16260）\n- 从市场批量启用缺失插件的脚本\n- 技能与命令架构解释\n- 全面的诊断命令参考\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install claude-skills-troubleshooting@daymade-skills\n\n# 运行诊断\npython3 scripts\u002Fdiagnose_plugins.py\n\n# 批量启用缺失的插件\npython3 scripts\u002Fenable_all_plugins.py daymade-skills\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：完整的故障排除流程和架构指南，请参阅 [claude-skills-troubleshooting\u002FSKILL.md](.\u002Fclaude-skills-troubleshooting\u002FSKILL.md)。\n\n**要求**：无（使用 Claude Code 内置 Python）\n\n---\n\n### 33. **meeting-minutes-taker** - 会议纪要生成器\n\n通过迭代式人工审核，将会议记录转换为高保真、结构化的会议纪要。\n\n**适用场景：**\n- 已提供会议记录并需要生成会议纪要\u002F笔记\u002F摘要\n- 需要合并多个版本的会议纪要且不丢失内容\n- 现有的会议纪要需要对照原始记录进行审查以确保完整性\n\n**核心功能：**\n- 多轮并行生成与 UNION 合并策略\n- 基于证据的记录方式，包含发言者引语\n- 适用于架构讨论的 Mermaid 流程图\n- 迭代式人机协作优化流程\n- 多 AI 对比以减少偏见\n- 完整性检查清单用于系统化审查\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install meeting-minutes-taker@daymade-skills\n\n# 然后提供会议记录并请求生成会议纪要\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：完整的流程和模板指导，请参阅 [meeting-minutes-taker\u002FSKILL.md](.\u002Fmeeting-minutes-taker\u002FSKILL.md)。\n\n**要求**：无\n\n---\n\n### 34. **deep-research** - 研究报告生成器\n\n生成格式规范的研究报告，并附带证据追踪和引用。\n\n**适用场景：**\n- 需要结构化的研究报告、文献综述或市场\u002F行业分析\n- 要求严格的章节格式或模板执行\n- 需要证据映射、引用及来源质量审查\n- 希望通过多轮综合避免遗漏关键发现\n\n**核心功能：**\n- 报告规格与格式契约工作流\n- 包含来源质量评估标准的证据表格\n- 多轮完整起草与 UNION 合并\n- 引用验证与冲突处理\n- 即用型报告模板和格式规范\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install deep-research@daymade-skills\n\n# 然后提供报告规格或模板并请求生成深度研究报告\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [deep-research\u002FSKILL.md](.\u002Fdeep-research\u002FSKILL.md) 和 [deep-research\u002Freferences\u002Fresearch_report_template.md](.\u002Fdeep-research\u002Freferences\u002Fresearch_report_template.md)，了解工作流程和结构。\n\n**要求**：无\n\n---\n\n### 35. **competitors-analysis** - 基于证据的竞争情报跟踪\n\n采用基于证据的方法分析竞争对手的代码库。所有分析必须基于实际克隆的代码，绝不能依赖假设。\n\n**适用场景：**\n- 跟踪和分析竞争对手的产品或技术\n- 创建基于证据的竞争对手档案\n- 生成竞争分析报告\n- 需要以引用来源的方式记录技术决策\n\n**核心功能：**\n- 分析前检查清单，确保代码库已本地克隆\n- 禁止使用推测性表述（如“推测…”、“可能…”、“应该…”）\n- 必须使用明确的引用格式（文件:行号形式）\n- 针对 Node.js、Python 和 Rust 项目的技栈分析指南\n- 用于有序竞争情报跟踪的目录结构规范\n- 内置模板：对手档案模板、分析检查清单\n- 批量克隆\u002F拉取\u002F状态管理脚本\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install competitors-analysis@daymade-skills\n\n# 然后请求 Claude 分析某个竞争对手\n“分析竞品 https:\u002F\u002Fgithub.com\u002Forg\u002Frepo”\n“将该竞品添加到 flowzero 产品的竞品列表”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [competitors-analysis\u002FSKILL.md](.\u002Fcompetitors-analysis\u002FSKILL.md) 和 [competitors-analysis\u002Freferences\u002F](.\u002Fcompetitors-analysis\u002Freferences\u002F) 获取相关模板。\n\n**要求**：Git（用于克隆代码库）\n\n---\n\n### 36. **tunnel-doctor** - Tailscale + 代理\u002FVPN 冲突修复工具\n\n诊断并修复在 macOS 上同时使用 Tailscale 与代理\u002FVPN 工具（Shadowrocket、Clash、Surge）时出现的冲突问题。涵盖四个独立的冲突层次，并针对 SSH 访问 WSL 实例提供具体指导。\n\n**适用场景：**\n- Tailscale ping 可以正常工作，但 SSH\u002FTCP 连接超时\n- 代理工具劫持了 Tailscale 的 CGNAT 地址范围（100.64.0.0\u002F10）\n- 浏览器返回 HTTP 503 错误，但 curl 和 SSH 正常工作\n- `git push\u002Fpull` 失败，提示“无法开始通过 HTTP 中继”\n- 设置 Tailscale SSH 到 WSL 时遇到“操作不允许”的错误\n- 需要在 macOS 上实现 Tailscale 与 Shadowrocket\u002FClash\u002FSurge 的共存\n\n**核心功能：**\n- 四层诊断模型：路由劫持、HTTP 环境变量、系统代理绕过、SSH ProxyCommand 双重隧道\n- 针对 Shadowrocket、Clash 和 Surge 的专用修复指南\n- SSH ProxyCommand 双重隧道检测与修复（解决 git push\u002Fpull 失败问题）\n- Tailscale SSH ACL 配置（check vs accept）\n- WSL snap 与 apt 版本 Tailscale 的安装差异（snap 沙盒会破坏 SSH）\n- 使用代理安全的 Makefile 模式进行远程开发的标准操作流程\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install tunnel-doctor@daymade-skills\n\n# 然后请求 Claude 进行诊断\n“Tailscale ping 可以正常工作，但 SSH 超时”\n“修复 Tailscale 和 Shadowrocket 在 macOS 上的路由冲突”\n“git push 失败，提示‘无法开始通过 HTTP 中继’”\n“设置 Tailscale SSH 到我的 WSL 实例”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：请参阅 [tunnel-doctor\u002Freferences\u002Fproxy_conflict_reference.md](.\u002Ftunnel-doctor\u002Freferences\u002Fproxy_conflict_reference.md)，了解各工具的具体配置及冲突架构。\n\n---\n\n### 37. **windows-remote-desktop-connection-doctor** - Windows 远程桌面连接质量诊断工具\n\n诊断 macOS 上 Windows 应用程序（Microsoft 远程桌面、Azure 虚拟桌面、W365）的连接质量问题，重点优化传输协议（UDP Shortpath 与 WebSocket 回退）。\n\n**适用场景：**\n- VDI 连接速度慢，RTT 较高（超过 100ms）\n- 传输协议显示为 WebSocket 而不是 UDP\n- RDP Shortpath 无法建立连接\n- 更改网络位置后连接质量下降\n- 需要识别 VPN\u002F代理对 STUN\u002FTURN 的干扰\n\n**核心功能：**\n- 五步诊断流程：从收集连接信息到验证修复效果\n- 传输协议分析（UDP Shortpath > TCP > WebSocket 层次）\n- VPN\u002F代理干扰检测（ShadowRocket TUN 模式、Tailscale 出口节点）\n- 解析 Windows 应用程序日志，查找健康检查失败、证书错误、FetchClientOptions 超时等问题\n- 通过 STUN 连通性检查测试 ISP 对 UDP 的限制\n- 针对中国 ISP 的特定指导，解决 UDP 被限流的问题\n- 工作与非工作日志对比方法论\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install windows-remote-desktop-connection-doctor@daymade-skills\n\n# 然后请 Claude 进行诊断\n“我的 VDI 连接显示 WebSocket 而不是 UDP，RTT 为 165 毫秒”\n“诊断 RDP Shortpath 为何无法正常工作”\n“Windows 应用程序传输协议卡在 WebSocket 上”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：有关日志分析模式和 AVD 传输协议详情，请参阅 [windows-remote-desktop-connection-doctor\u002Freferences\u002F](.\u002Fwindows-remote-desktop-connection-doctor\u002Freferences\u002F)。\n\n---\n\n### 38. **product-analysis** - 多路径产品分析与优化\n\n使用并行的 Claude Code 代理以及可选的 Codex CLI 并行化功能，运行可扩展、基于证据的产品审计。涵盖用户体验、API、架构及竞争基准工作流，并提供量化结果和优先级建议。\n\n**适用场景：**\n- 产品发布前的准备评审\n- 发布前对代码库和用户体验进行多角度审计\n- 检查 API 质量，包括端点和使用一致性审查\n- 对选定的竞争对手仓库进行竞争性基准测试\n\n**主要特性：**\n- 自动检测工具上下文（项目堆栈 + 可选的 `codex` 是否可用）\n- 在多个维度上并行分析：`full`、`ux`、`api`、`arch`、`compare`\n- 多代理综合分析，提供量化发现及 P0\u002FP1\u002FP2 建议\n- 内置与 `competitors-analysis` 的比较钩子\n- 交叉验证工作流，以减少单一模型视角带来的过拟合风险\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install product-analysis@daymade-skills\n\n# 然后请求 Claude 进行分析\n“以完整模式运行 product-analysis 进行发布审计”\n“进行 UX 审计并报告量化的导航发现”\n“运行 API 审计并识别未使用的端点”\n“将此产品与我们的顶级竞争对手进行比较”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：有关维度定义和工作流指导，请参阅 [product-analysis\u002FSKILL.md](.\u002Fproduct-analysis\u002FSKILL.md) 和 [product-analysis\u002Freferences\u002Fanalysis_dimensions.md](.\u002Fproduct-analysis\u002Freferences\u002Fanalysis_dimensions.md)。\n\n**要求**：可选的 `codex` CLI（用于多模型并行模式）。若未安装 `codex`，则仅能使用 Claude 单独运行该技能。\n\n---\n\n### 39. **financial-data-collector** - 美国股票金融数据采集\n\n从免费的公开数据源（yfinance）收集任何美国上市公司的实时财务数据。输出结构化的 JSON 格式数据，包含市场数据、历史财务报表（利润表、现金流量表、资产负债表）、WACC 输入以及分析师预测——可直接用于下游的 DCF 建模、可比公司分析或财报回顾。\n\n**适用场景：**\n- 在构建 DCF 或估值模型之前收集结构化的财务数据\n- 获取任何美股标的的市场数据（股价、流通股数、贝塔系数、市值）\n- 收集历史利润表、现金流量表和资产负债表数据\n- 获取无风险利率（10 年期国债收益率）和分析师一致预期\n\n**主要特性：**\n- 强健的 yfinance 字段映射与别名链（应对不同版本 API 的不稳定性）\n- NaN 年份检测及透明报告（绝不以估算值填充）\n- 9 项检查验证：字段完整性、市值交叉核验、资本支出符号约定、净债务一致性\n- 遵循“无回退”原则：缺失数据返回 `null` 并标注 `_source` 来源，绝不会使用默认值\n- FCF 定义不匹配标记（由于 SBC 的存在，yfinance 的 FCF 与投行的 FCF 不同）\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install financial-data-collector@daymade-skills\n\n# 然后请求 Claude 采集数据\n“为 META 采集财务数据”\n“为 AAPL 采集过去 3 年的财务数据”\n“为 NVDA 提取 DCF 所需的输入数据”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：有关详细信息，请参阅 [financial-data-collector\u002FSKILL.md](.\u002Ffinancial-data-collector\u002FSKILL.md)、[output-schema.md](.\u002Ffinancial-data-collector\u002Freferences\u002Foutput-schema.md) 和 [yfinance-pitfalls.md](.\u002Ffinancial-data-collector\u002Freferences\u002Fyfinance-pitfalls.md)。\n\n**要求**：Python 3.11+、`yfinance`、`pandas`（通过 uv 内联依赖自动安装）。\n\n---\n\n### 40. **excel-automation** - Excel 自动化：创建、解析与 macOS 控制\n\n创建专业格式的 Excel 文件，使用 stdlib XML\u002FZIP 工作流解析复杂的 `.xlsm` 模型，并通过 AppleScript 控制 macOS 上的 Microsoft Excel 窗口。\n\n**适用场景：**\n- 构建符合金融行业标准的格式统一的电子表格\n- 解析在 `openpyxl` 中失败的复杂银行\u002F券商 `.xlsm` 文件\n- 提取目标工作表\u002F单元格数据，而无需加载大型工作簿\n- 自动化 Excel 窗口操作（缩放、滚动、选择）于 macOS 系统\n\n**主要特性：**\n- 使用 `openpyxl` 生成格式化工作簿的生产模板\n- 利用 `zipfile` + `xml.etree` 解析复杂工作簿（无需重型依赖）\n- 针对问题文件的损坏 `definedNames` 修复流程\n- 经过验证的 AppleScript 命令模式，并配备超时保护机制\n- 搭配颜色、数字格式和表格样式的格式参考手册\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install excel-automation@daymade-skills\n\n# 然后请求 Claude 自动化 Excel 流程\n“创建一个格式化的估值模板工作簿”\n“解析这个 .xlsm 文件并提取 DCF 工作表”\n“生成一段 AppleScript 序列，在截图前先放大并滚动 Excel”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：有关详细信息，请参阅 [excel-automation\u002FSKILL.md](.\u002Fexcel-automation\u002FSKILL.md) 和 [formatting-reference.md](.\u002Fexcel-automation\u002Freferences\u002Fformatting-reference.md)。\n\n**要求**：Python 3.8+、`uv`、`openpyxl`（可通过 `uv run --with openpyxl` 自动安装），以及 macOS 系统以便使用 AppleScript 控制窗口。\n\n---\n\n### 41. **capture-screen** - macOS 程序化屏幕截图捕获\n\n通过 CGWindowID 捕获应用程序窗口，采用可靠的三步流程：利用 Swift 查找窗口 ID，通过 AppleScript 控制应用状态，最后使用 `screencapture` 截图。\n\n**适用场景：**\n- 自动化重复性的文档截图流程\n- 捕捉特定的应用程序窗口，而非全屏截图\n- 在脚本控制的滚动\u002F缩放操作后生成多张序列截图\n- 在 macOS 上构建可视化证据采集流水线\n\n**主要特性：**\n- 内置 Swift 脚本以准确解析窗口 ID（`CGWindowListCopyWindowInfo`）\n- 经过验证的 AppleScript 模式，用于激活应用程序和准备窗口\n- 针对特定窗口的捕获命令，支持静音模式、延迟设置及格式控制\n- 多次拍摄的工作流模式，可用于分段捕获\n- 清晰列出在 macOS 上会失效的方法及其反模式说明\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install capture-screen@daymade-skills\n\n# 然后请求 Claude 程序化捕获窗口\n“查找 Excel 窗口 ID 并静音截取”\n“为该工作簿创建一个多张截图的工作流”\n“通过脚本控制滚动，分段捕获 Chrome 窗口”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：有关详细信息，请参阅 [capture-screen\u002FSKILL.md](.\u002Fcapture-screen\u002FSKILL.md)。\n\n**要求**：macOS 系统（Swift + AppleScript + `screencapture`）。\n\n---\n\n### 42. **continue-claude-work** - 恢复中断的 Claude 工作\n\n从本地 `~\u002F.claude` 会话文件中恢复可操作的上下文，并在不重新打开旧交互式会话的情况下继续执行。该技能使用一个捆绑的 Python 脚本进行智能上下文提取。\n\n**适用场景：**\n- 用户提供了 Claude 会话 ID 并希望继续任务\n- 需要检查本地 `.claude` JSONL 文件，而不是运行 `claude --resume`\n- 前一个会话被中断，需要重建下一步具体步骤\n- 多智能体工作流被中断，需要了解哪些子智能体已完成\n\n**核心功能：**\n- 紧凑边界感知提取 — 以 Claude 自身的会话压缩摘要作为最高信噪比的上下文\n- 子智能体工作流恢复 — 报告已完成与中断的子智能体及其最后输出\n- 会话结束原因检测 — 分类为正常退出、中断（Ctrl-C）、错误级联或放弃\n- 大小自适应策略 — 对于小型（\u003C500KB）和大型（>5MB）会话采用不同的读取方式\n- 噪声过滤 — 跳过进度\u002F队列操作\u002FAPI 错误消息（占会话行数的 37%-53%）\n- 自会话排除、过时索引回退、MEMORY.md 集成、Git 工作区状态\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install continue-claude-work@daymade-skills\n\n# 然后让 Claude 从本地文件中恢复工作\n“从会话 123e4567-e89b-12d3-a456-426614174000 继续工作”\n“不要恢复，只需读取 .claude 文件并继续”\n“查看上一次会话我在做什么，并接着做下去”\n```\n\n📚 **文档**：参见 [continue-claude-work\u002FSKILL.md](.\u002Fcontinue-claude-work\u002FSKILL.md)。\n\n**要求**：Python 3.8+，以及用于工作区协调的 `git`。\n\n---\n\n### 43. **scrapling-skill** - 可靠的 Scrapling CLI 工作流\n\n安装、排查故障并使用 Scrapling CLI，提供经过验证的静态优先工作流程，用于从网页中提取 HTML、Markdown 或文本。包含诊断脚本，用于检查额外依赖是否安装正确、Playwright 浏览器运行时是否存在，以及对真实 URL 的冒烟测试。\n\n**适用场景：**\n- 用户提到 Scrapling、`uv tool install scrapling` 或 `scrapling extract`\n- 需要在静态抓取和基于浏览器的抓取之间做出选择\n- 需要从微信公众号页面（`mp.weixin.qq.com`）提取文章正文\n- Scrapling 安装部分成功，但在缺少额外依赖、浏览器运行时或 TLS 验证时失败\n\n**核心功能：**\n- 捆绑的 `diagnose_scrapling.py` 脚本，用于 CLI、浏览器运行时及实时 URL 冒烟测试\n- 经验证的默认路径：先尝试 `extract get`，仅在必要时升级到 `extract fetch`\n- 使用 `#js_content` 提取微信文章的纯净 Markdown 格式\n- 缺少 `click`、Playwright 运行时配置以及 `curl: (60)` 信任库失败等问题的故障排除指导\n- 输出验证工作流，通过文件大小和内容检查代替依赖退出码判断\n\n**使用示例：**\n```bash\n# 安装该技能\nclaude plugin install scrapling-skill@daymade-skills\n\n# 然后让 Claude 为你处理 Scrapling 相关任务\n“安装 Scrapling CLI 并验证设置”\n“用 Scrapling 将这篇微信文章提取为 Markdown”\n“判断这个页面是需要静态抓取还是基于浏览器的抓取”\n```\n\n**🎬 实时演示**\n\n*即将推出*\n\n📚 **文档**：参见 [scrapling-skill\u002FSKILL.md](.\u002Fscrapling-skill\u002FSKILL.md) 和 [scrapling-skill\u002Freferences\u002Ftroubleshooting.md](.\u002Fscrapling-skill\u002Freferences\u002Ftroubleshooting.md)。\n\n**要求**：Python 3.6+、`uv`、Scrapling CLI，以及用于基于浏览器抓取的 Playwright 浏览器运行时。\n\n---\n\n## 🎬 交互式演示图库\n\n想在一个地方查看所有演示，并支持点击放大吗？请访问我们的 [交互式演示图库](.\u002Fdemos\u002Findex.html) 或浏览 [演示目录](.\u002Fdemos\u002F)。\n\n## 🎯 使用场景\n\n### 用于 GitHub 工作流\n使用 **github-ops** 来简化 PR 创建、问题管理和 API 操作。\n\n### 用于文档编写\n结合 **doc-to-markdown** 进行文档转换和 **mermaid-tools** 生成图表，创建全面的文档。使用 **llm-icon-finder** 添加品牌图标。\n\n### 用于研究与分析\n使用 **deep-research** 生成格式规范的研究报告，包含证据表格和引用。可与 **fact-checker** 结合验证观点，或与 **twitter-reader** 结合收集社交来源信息。\n\n### 用于竞争情报\n使用 **competitors-analysis** 跟踪和分析竞争对手的代码仓库，基于证据的方法得出结论。所有发现均来自实际代码（文件:行号），避免推测。可与 **deep-research** 结合，生成全面的竞争态势报告。\n\n### 用于 PDF 和可打印文档\n使用 **pdf-creator** 将 Markdown 转换为适合打印的 PDF，支持中文字体，适用于正式文档和报告。\n\n### 用于团队沟通\n使用 **teams-channel-post-writer** 分享知识，使用 **statusline-generator** 跟踪工作成本。\n\n### 用于仓库管理与安全\n使用 **repomix-unmixer** 提取并验证 repomix 打包的技能或仓库。使用 **repomix-safe-mixer** 安全打包代码库，自动检测并阻止硬编码凭据在分发前泄露。\n\n### 用于技能开发\n使用 **skill-creator**（参见上方的“必备技能”章节）按照最佳实践构建、验证和打包你自己的 Claude Code 技能。\n\n### 用于演示与商务沟通\n使用 **ppt-creator** 生成专业的幻灯片，包含数据可视化、结构化叙事，并直接导出 PPTX 文件，适用于演讲、评审和主题报告。\n\n### 用于视频质量分析\n使用 **video-comparer** 分析压缩效果、评估编解码器性能，并生成交互式对比报告。可与 **youtube-downloader** 结合，比较不同质量的下载结果。\n\n### 用于媒体与内容下载\n使用 **youtube-downloader** 下载 YouTube 视频，并从视频中提取音频，自动绕过常见下载问题。\n\n### 用于转录与 ASR 修正\n使用 **transcript-fixer** 通过基于词典的规则和 AI 驱动的修正，自动学习并纠正会议记录、讲座和访谈中的语音转文字错误。\n\n### 用于金融数据与投资研究\n使用 **financial-data-collector** 提取任何美国上市公司的结构化财务数据，然后将 JSON 输出导入 DCF 建模、可比公司分析或财报审查工作流中。\n\n### 用于 Excel 与财务建模自动化\n使用 **excel-automation** 创建格式化的电子表格，解析复杂的 `.xlsm` 模型，并自动化 Excel 窗口操作，以减少分析师的重复性工作。\n\n### 用于 macOS 上的视觉捕获自动化\n使用 **capture-screen** 编写可重复的 App 窗口截图脚本。可与 **excel-automation** 结合，生成可用于报告的电子表格可视化内容。\n\n### 用于会议文档\n使用 **meeting-minutes-taker** 将原始会议记录转换为结构化、基于证据的会议纪要。结合 **transcript-fixer** 在生成纪要之前清理自动语音识别 (ASR) 错误。支持多轮生成，并采用 UNION 合并方式，以避免内容丢失。\n\n### 用于 QA 测试与质量保证\n使用 **qa-expert** 建立全面的 QA 测试基础设施，实现 LLM 自主执行、遵循 Google 测试标准以及 OWASP 安全测试。非常适合项目上线、第三方 QA 交接以及执行质量门控（100% 执行率、≥80% 通过率、0 个 P0 级别缺陷）。该主提示可使测试执行速度提升 100 倍，且无任何跟踪错误。\n\n### 用于提示工程与需求工程\n使用 **prompt-optimizer** 将模糊的功能需求转化为精确的 EARS 规范，并结合领域理论进行验证。非常适合编写产品需求文档、辅助 AI 编码以及学习提示工程最佳实践。可与 **skill-creator** 结合创建结构化的技能提示，或与 **ppt-creator** 配合确保演示文稿的内容需求清晰明确。\n\n### 用于会话历史与文件恢复\n使用 **claude-code-history-files-finder** 从之前的 Claude Code 会话中恢复已删除的文件，在整个对话历史中搜索特定实现，或追踪文件随时间的变化轨迹。对于恢复意外删除的代码，或找回虽记得但找不到的具体功能实现，这一工具至关重要。\n\n### 用于恢复中断的 Claude 会话\n使用 **continue-claude-work** 从本地 `~\u002F.claude` 文件中提取最后一次可操作的请求，并在不重新打开原会话的情况下继续实现。若需更广泛的跨会话搜索、统计信息或已删除文件的恢复，则可与 **claude-code-history-files-finder** 搭配使用。\n\n### 用于网页抓取与微信文章\n使用 **scrapling-skill** 安装并验证 Scrapling CLI，选择静态抓取或基于浏览器的抓取方式，从诸如 `mp.weixin.qq.com` 的网站中提取干净的 Markdown 格式内容。可与 **deep-research** 结合，将抓取到的资料转化为结构化报告；或与 **docs-cleaner** 配合，对捕获的文章内容进行规范化处理。\n\n### 用于文档维护\n使用 **docs-cleaner** 整合冗余文档，同时保留有价值的内容。非常适合在快速开发阶段后清理文档冗余，或将重叠文档合并为权威来源。\n\n### 用于优化 CLAUDE.md\n使用 **claude-md-progressive-disclosurer** 通过将详细章节移至参考部分来减少 CLAUDE.md 的臃肿，同时保持核心规则可见。\n\n### 用于技能发现与管理\n使用 **skills-search** 从 CCPM 注册表中查找、安装并管理 Claude Code 技能。非常适合为特定任务发现新技能、安装常用工作流的技能包，以及保持技能库的有序管理。\n\n### 用于 LLM 评估与模型比较\n使用 **promptfoo-evaluation** 设置提示测试、比较模型输出，并运行带有自定义断言的自动化评估。\n\n### 用于 iOS 应用开发\n使用 **iOS-APP-developer** 配置 XcodeGen 项目，解决 SPM 依赖问题，并排查代码签名或设备部署中的故障。\n\n### 用于 macOS 系统维护与磁盘空间回收\n使用 **macos-cleaner** 以安全优先的方式智能分析并回收 macOS 上的磁盘空间。不同于盲目删除的一键清理工具，macos-cleaner 会解释每个文件的用途，按风险等级（🟢\u002F🟡\u002F🔴）分类，并在任何删除操作前都需要明确确认。非常适合因 Docker\u002FHomebrew\u002Fnpm\u002Fpip 缓存膨胀而困扰的开发者、希望了解存储占用情况的用户，或重视透明性而非自动化的人群。该工具结合了脚本驱动的精准操作，并可选集成 Mole 可视化工具，实现混合工作流程。\n\n### 用于 Twitter\u002FX 内容研究\n使用 **twitter-reader** 在无需 JavaScript 渲染或身份验证的情况下抓取推文内容。非常适合记录社交媒体讨论、归档话题串、分析推文内容，或从 Twitter\u002FX 收集参考资料。可与 **doc-to-markdown** 结合，将抓取的内容转换为其他格式；或与 **repomix-safe-mixer** 配合，安全地打包研究资料集。\n\n### 用于技能质量与开源贡献\n使用 **skill-reviewer** 在发布前根据最佳实践验证自身技能，或审查并改进他人的技能库。可与 **github-contributor** 结合，寻找高影响力的开源项目，创建专业的 PR，并建立个人贡献者声誉。非常适合希望系统性地为 Claude Code 生态系统或其他 GitHub 项目做出贡献的开发者。\n\n### 用于国际化与本地化\n使用 **i18n-expert** 为 React\u002FNext.js\u002FVue 应用程序搭建完整的国际化基础设施，审计现有实现中是否存在遗漏的翻译键，并确保 en-US 和 zh-CN 之间的语言环境一致性。非常适合向全球市场推出产品的团队、维护多语言 UI 的团队，或需要将硬编码字符串替换为正确 i18n 键的场景。可与 **skill-creator** 结合创建支持多语言的技能，或与 **docs-cleaner** 配合整合多语言文档。\n\n### 用于网络与 VPN 故障排除\n使用 **tunnel-doctor** 诊断并解决 Tailscale 与 macOS 上代理\u002FVPN 工具之间的冲突，覆盖四个独立层面（路由劫持、HTTP 环境变量、系统代理、SSH ProxyCommand）。当 Tailscale ping 正常但 TCP 连接失败、git push 报错“无法通过 HTTP 开始中继”，或在 Shadowrocket、Clash 或 Surge 的基础上设置 Tailscale SSH 连接到 WSL 实例时，此工具不可或缺。\n\n### 用于产品审计\n使用 **product-analysis** 进行结构化的预发布和架构评审。它将 UX、API 和架构分析整合为可衡量的结果，并提供按优先级排序的建议。添加 `compare` 模式，可通过基于证据的报告与竞争对手的实现进行基准对比。\n\n### 用于远程桌面与 VDI 优化\n使用 **windows-remote-desktop-connection-doctor** 诊断 macOS 上 Azure Virtual Desktop \u002F W365 连接质量问题。当传输显示 WebSocket 而非 UDP Shortpath、RTT 出乎意料地高，或在网络位置变更后 RDP Shortpath 失败时，此工具尤为必要。它结合网络证据收集与 Windows 应用程序日志分析，以系统性地确定根本原因。\n\n### 用于插件与技能故障排除\n使用 **claude-skills-troubleshooting** 来诊断和解决 Claude Code 插件及技能配置问题。调试插件显示已安装但未出现在可用技能中的原因，理解 installed_plugins.json 与 settings.json 中 enabledPlugins 的架构，并从市场批量启用缺失的插件。这对于市场维护人员调试安装问题、开发者排查技能激活问题，或任何对 GitHub #17832 自动启用 bug 感到困惑的人来说都至关重要。\n\n## 📚 文档\n\n每个技能包含：\n- **SKILL.md**：核心说明与工作流程\n- **scripts\u002F**：可执行工具（Python\u002FBash）\n- **references\u002F**：详细文档\n- **assets\u002F**：模板与资源（如适用）\n\n### 快速链接\n\n- **github-ops**：请参阅 `github-ops\u002Freferences\u002Fapi_reference.md` 获取 API 文档\n- **doc-to-markdown**：请参阅 `doc-to-markdown\u002Freferences\u002Fconversion-examples.md` 查看转换场景\n- **mermaid-tools**：请参阅 `mermaid-tools\u002Freferences\u002Fsetup_and_troubleshooting.md` 获取设置指南\n- **statusline-generator**：请参阅 `statusline-generator\u002Freferences\u002Fcolor_codes.md` 进行自定义\n- **teams-channel-post-writer**：请参阅 `teams-channel-post-writer\u002Freferences\u002Fwriting-guidelines.md` 了解质量标准\n- **repomix-unmixer**：请参阅 `repomix-unmixer\u002Freferences\u002Frepomix-format.md` 查看格式规范\n- **skill-creator**：请参阅 `skill-creator\u002FSKILL.md` 了解完整的技能创建流程\n- **llm-icon-finder**：请参阅 `llm-icon-finder\u002Freferences\u002Ficons-list.md` 查看可用图标\n- **cli-demo-generator**：请参阅 `cli-demo-generator\u002Freferences\u002Fvhs_syntax.md` 了解 VHS 语法，以及 `cli-demo-generator\u002Freferences\u002Fbest_practices.md` 查看演示指南\n- **cloudflare-troubleshooting**：请参阅 `cloudflare-troubleshooting\u002Freferences\u002Fapi_overview.md` 获取 API 文档\n- **ui-designer**：请参阅 `ui-designer\u002FSKILL.md` 了解设计系统提取流程\n- **ppt-creator**：请参阅 `ppt-creator\u002Freferences\u002FWORKFLOW.md` 查看9阶段创作流程，以及 `ppt-creator\u002Freferences\u002FORCHESTRATION_OVERVIEW.md` 了解自动化内容\n- **youtube-downloader**：请参阅 `youtube-downloader\u002FSKILL.md` 查看使用示例及故障排除方法\n- **repomix-safe-mixer**：请参阅 `repomix-safe-mixer\u002Freferences\u002Fcommon_secrets.md` 查看检测到的凭证模式\n- **video-comparer**：请参阅 `video-comparer\u002Freferences\u002Fvideo_metrics.md` 解读质量指标，以及 `video-comparer\u002Freferences\u002Fconfiguration.md` 查看自定义选项\n- **transcript-fixer**：请参阅 `transcript-fixer\u002Freferences\u002Fworkflow_guide.md` 查看分步工作流程，以及 `transcript-fixer\u002Freferences\u002Fteam_collaboration.md` 查看协作模式\n- **qa-expert**：请参阅 `qa-expert\u002Freferences\u002Fmaster_qa_prompt.md` 了解自主执行方式（速度提升100倍），以及 `qa-expert\u002Freferences\u002Fgoogle_testing_standards.md` 查看 AAA 模式和 OWASP 测试内容\n- **prompt-optimizer**：请参阅 `prompt-optimizer\u002Freferences\u002Fears_syntax.md` 查看 EARS 转换模式，`prompt-optimizer\u002Freferences\u002Fdomain_theories.md` 查看理论目录，以及 `prompt-optimizer\u002Freferences\u002Fexamples.md` 查看完整转换案例\n- **claude-code-history-files-finder**：请参阅 `claude-code-history-files-finder\u002Freferences\u002Fsession_file_format.md` 查看 JSONL 结构，以及 `claude-code-history-files-finder\u002Freferences\u002Fworkflow_examples.md` 查看恢复流程\n- **docs-cleaner**：请参阅 `docs-cleaner\u002FSKILL.md` 查看整合工作流程\n- **deep-research**：请参阅 `deep-research\u002Freferences\u002Fresearch_report_template.md` 查看报告结构，以及 `deep-research\u002Freferences\u002Fsource_quality_rubric.md` 查看资料筛选标准\n- **pdf-creator**：请参阅 `pdf-creator\u002FSKILL.md` 查看 PDF 转换及字体设置\n- **claude-md-progressive-disclosurer**：请参阅 `claude-md-progressive-disclosurer\u002FSKILL.md` 查看 CLAUDE.md 优化流程\n- **skills-search**：请参阅 `skills-search\u002FSKILL.md` 查看 CCPM CLI 命令及注册表操作\n- **promptfoo-evaluation**：请参阅 `promptfoo-evaluation\u002Freferences\u002Fpromptfoo_api.md` 查看评估模式\n- **iOS-APP-developer**：请参阅 `iOS-APP-developer\u002Freferences\u002Fxcodegen-full.md` 查看 XcodeGen 选项及 project.yml 细节\n- **twitter-reader**：请参阅 `twitter-reader\u002FSKILL.md` 查看 API 密钥设置及 URL 格式支持\n- **macos-cleaner**：请参阅 `macos-cleaner\u002Freferences\u002Fcleanup_targets.md` 查看详细的清理目标说明，`macos-cleaner\u002Freferences\u002Fmole_integration.md` 查看 Mole 可视化工具集成，以及 `macos-cleaner\u002Freferences\u002Fsafety_rules.md` 查看全面的安全指南\n- **skill-reviewer**：请参阅 `skill-reviewer\u002Freferences\u002Fevaluation_checklist.md` 查看完整评估标准，`skill-reviewer\u002Freferences\u002Fpr_template.md` 查看 PR 模板，以及 `skill-reviewer\u002Freferences\u002Fmarketplace_template.json` 查看市场配置\n- **github-contributor**：请参阅 `github-contributor\u002Freferences\u002Fpr_checklist.md` 查看 PR 质量检查清单，`github-contributor\u002Freferences\u002Fproject_evaluation.md` 查看项目评估标准，以及 `github-contributor\u002Freferences\u002Fcommunication_templates.md` 查看问题\u002FPR 模板\n- **i18n-expert**：请参阅 `i18n-expert\u002FSKILL.md` 查看完整的 i18n 设置流程、键值架构指导及审计程序\n- **claude-skills-troubleshooting**：请参阅 `claude-skills-troubleshooting\u002FSKILL.md` 查看插件故障排除流程及架构\n- **fact-checker**：请参阅 `fact-checker\u002FSKILL.md` 查看事实核查流程及主张验证过程\n- **competitors-analysis**：请参阅 `competitors-analysis\u002FSKILL.md` 查看基于证据的分析流程，以及 `competitors-analysis\u002Freferences\u002Fprofile_template.md` 查看竞争对手档案模板\n- **windows-remote-desktop-connection-doctor**：请参阅 `windows-remote-desktop-connection-doctor\u002Freferences\u002Fwindows_app_log_analysis.md` 查看日志解析模式，以及 `windows-remote-desktop-connection-doctor\u002Freferences\u002Favd_transport_protocols.md` 查看传输协议详情\n- **product-analysis**：请参阅 `product-analysis\u002FSKILL.md` 查看工作流程，以及 `product-analysis\u002Freferences\u002Fsynthesis_methodology.md` 查看跨代理权重分配及推荐逻辑\n- **excel-automation**：请参阅 `excel-automation\u002FSKILL.md` 查看创建\u002F解析\u002F控制流程，以及 `excel-automation\u002Freferences\u002Fformatting-reference.md` 查看格式标准\n- **capture-screen**：请参阅 `capture-screen\u002FSKILL.md` 查看基于 CGWindowID 的 macOS 截图流程\n- **continue-claude-work**：请参阅 `continue-claude-work\u002FSKILL.md` 查看本地工件恢复、漂移检查及恢复工作流程\n- **scrapling-skill**：请参阅 `scrapling-skill\u002FSKILL.md` 查看 CLI 工作流程，以及 `scrapling-skill\u002Freferences\u002Ftroubleshooting.md` 查看已验证的 Scrapling 故障模式\n\n## 🛠️ 系统要求\n\n- **Claude Code** 2.0.13 或更高版本\n- **Python 3.6+**（用于多技能脚本）\n- **gh CLI**（用于 github-ops）\n- **markitdown**（用于 doc-to-markdown）\n- **mermaid-cli**（用于 mermaid-tools）\n- **yt-dlp**（用于 youtube-downloader）：`brew install yt-dlp` 或 `pip install yt-dlp`\n- **FFmpeg\u002FFFprobe**（用于 video-comparer）：`brew install ffmpeg`、`apt install ffmpeg` 或 `winget install ffmpeg`\n- **weasyprint、markdown**（用于 pdf-creator）\n- **VHS**（用于 cli-demo-generator）：`brew install vhs`\n- **Jina.ai API 密钥**（用于 twitter-reader）：可在 https:\u002F\u002Fjina.ai\u002F 获取免费层级\n- **asciinema**（可选，用于 cli-demo-generator 的交互式录制）\n- **ccusage**（可选，用于 statusline 成本跟踪）\n- **pandas 和 matplotlib**（可选，用于 ppt-creator 的图表生成）\n- **Marp CLI**（可选，用于 ppt-creator 的 Marp PPTX 导出）：`npm install -g @marp-team\u002Fmarp-cli`\n- **Mole**（可选，用于 macos-cleaner 的可视化清理）：可从 https:\u002F\u002Fgithub.com\u002Ftw93\u002FMole 下载\n- **repomix**（用于 repomix-safe-mixer）：`npm install -g repomix`\n- **CCPM CLI**（用于 skills-search）：`npm install -g @daymade\u002Fccpm`\n- **Promptfoo**（用于 promptfoo-evaluation）：`npx promptfoo@latest`\n- **macOS + Xcode、XcodeGen**（用于 iOS-APP-developer）\n- **Codex CLI**（可选，用于 product-analysis 多模型模式）\n- **uv + openpyxl**（用于 excel-automation）：`uv run --with openpyxl ...`\n- **macOS**（用于 capture-screen 和 excel-automation 的 AppleScript 控制工作流）\n- **Python 3.8+**（用于 continue-claude-work）：内置会话提取脚本（无外部依赖）\n- **uv + Scrapling CLI**（用于 scrapling-skill）：`uv tool install 'scrapling[shell]'` 并运行 `scrapling install` 进行浏览器支持的抓取操作\n\n## ❓ 常见问题解答\n\n### 我如何知道该安装哪些技能？\n\n如果您想创建自己的技能，请从 **skill-creator** 开始。否则，请浏览【其他可用技能】部分，根据您的工作流程选择合适的技能进行安装。\n\n### 我可以在没有 Claude Code 的情况下使用这些技能吗？\n\n不可以，这些技能是专门为 Claude Code 设计的。您需要 Claude Code 2.0.13 或更高版本。\n\n### 如何更新技能？\n\n使用相同的安装命令即可更新：\n```bash\nclaude plugin install skill-name@daymade-skills\n```\n\n### 我可以贡献自己的技能吗？\n\n当然可以！请参阅 [CONTRIBUTING.md](.\u002FCONTRIBUTING.md) 了解相关指南。我们建议使用 skill-creator 来确保您的技能符合质量标准。\n\n### 这些技能安全吗？\n\n是的，所有技能均为开源并经过审核。代码在此仓库中公开，可供检查。\n\n### 中国用户如何处理 API 访问？\n\n我们推荐使用 [CC-Switch](https:\u002F\u002Fgithub.com\u002Ffarion1231\u002Fcc-switch) 来管理 API 提供商配置。请参阅上方的【中文用户指南】部分。\n\n### skill-creator 与其他技能有什么区别？\n\n**skill-creator** 是一个元技能——它可以帮助您创建其他技能。而其他技能则是面向最终用户的技能，提供特定的功能（如 GitHub 操作、文档转换等）。如果您希望用自定义的工作流扩展 Claude Code，请从 skill-creator 开始。\n\n---\n\n## 🤝 贡献\n\n欢迎各位贡献！您可以：\n\n1. 打开议题报告错误或提出功能请求\n2. 提交拉取请求以改进功能\n3. 分享对技能质量的反馈\n\n### 技能质量标准\n\n本市场中的所有技能均遵循：\n- 命令式\u002F不定式写作风格\n- 渐进式披露模式\n- 合理的资源组织\n- 全面的文档说明\n- 经过测试和验证\n\n## 📄 许可证\n\n本市场采用 MIT 许可证授权——详情请参阅 [LICENSE](LICENSE) 文件。\n\n## ⭐ 支持\n\n如果您觉得这些技能有用，请：\n- ⭐ 星标本仓库\n- 🐛 报告问题\n- 💡 提出改进建议\n- 📢 分享给您的团队\n\n## 🔗 相关资源\n\n- [Claude Code 文档](https:\u002F\u002Fdocs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code)\n- [Agent Skills 指南](https:\u002F\u002Fdocs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code\u002Fskills)\n- [插件市场](https:\u002F\u002Fdocs.claude.com\u002Fen\u002Fdocs\u002Fclaude-code\u002Fplugin-marketplaces)\n- [Anthropic 技能库](https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills)\n\n## 📞 联系方式\n\n- **GitHub**：[@daymade](https:\u002F\u002Fgithub.com\u002Fdaymade)\n- **邮箱**：daymadev89@gmail.com\n- **仓库**：[daymade\u002Fclaude-code-skills](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills)\n\n---\n\n**使用 skill-creator 技能为 Claude Code 打造**\n\n最后更新：2026-01-22 | 市场版本 1.23.0","# Claude Code Skills Marketplace 快速上手指南\n\n## 🌟 简介\n**claude-code-skills** 是一个专业的 Claude Code 技能市场，提供 43+ 个生产级技能，旨在增强开发工作流。其中核心技能 `skill-creator` 允许你构建、验证和打包自己的专属技能。\n\n## 🛠️ 环境准备\n\n### 系统要求\n- **Claude Code**: 版本需为 `2.0.13+`\n- **操作系统**: macOS, Linux, 或 Windows (PowerShell)\n- **网络环境**: 需能访问 GitHub 及 Claude API\n\n### 前置依赖与推荐工具\n- **基础依赖**: 确保已安装并配置好 `claude` CLI 工具。\n- **国内用户特别推荐**: \n  建议使用 **[CC-Switch](https:\u002F\u002Fgithub.com\u002Ffarion1231\u002Fcc-switch)** 管理 API 提供商配置。\n  - 支持快速切换 DeepSeek, Qwen, GLM 等国内大模型接口。\n  - 自动测试节点延迟，管理 MCP 服务器配置。\n  - 支持跨平台（Windows\u002FmacOS\u002FLinux）及配置备份。\n\n## 🚀 安装步骤\n\n你可以选择以下任意一种方式进行安装：\n\n### 方式一：自动化脚本安装（推荐）\n这是最快捷的方式，脚本会自动处理市场注册和插件安装。\n\n**macOS \u002F Linux:**\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fdaymade\u002Fclaude-code-skills\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n```\n\n**Windows (PowerShell):**\n```powershell\niwr -useb https:\u002F\u002Fraw.githubusercontent.com\u002Fdaymade\u002Fclaude-code-skills\u002Fmain\u002Fscripts\u002Finstall.ps1 | iex\n```\n\n### 方式二：在 Claude Code 应用内安装\n如果你正在使用 Claude Code 交互式界面：\n\n1. 输入以下命令添加市场源：\n   ```text\n   \u002Fplugin marketplace add daymade\u002Fclaude-code-skills\n   ```\n2. 选择 **Browse and install plugins**。\n3. 选择 **daymade\u002Fclaude-code-skills**。\n4. 选择你想安装的技能（首选 `skill-creator`）。\n5. 点击 **Install now**。\n\n### 方式三：手动命令行安装\n如果需要精确控制安装的技能：\n\n1. **添加市场源** (市场名称为 `daymade-skills`)：\n   ```bash\n   claude plugin marketplace add https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\n   ```\n   > ⚠️ 注意：安装时使用 `@daymade-skills` 后缀，不要直接使用仓库路径。\n\n2. **安装核心技能 (skill-creator)**：\n   这是创建其他技能的基础，建议优先安装。\n   ```bash\n   claude plugin install skill-creator@daymade-skills\n   ```\n\n3. **安装其他常用技能** (按需选择)：\n   ```bash\n   # GitHub 操作套件\n   claude plugin install github-ops@daymade-skills\n   \n   # 文档转 Markdown\n   claude plugin install doc-to-markdown@daymade-skills\n   \n   # Mermaid 图表生成\n   claude plugin install mermaid-tools@daymade-skills\n   \n   # PPT 创建\n   claude plugin install ppt-creator@daymade-skills\n   \n   # PDF 生成 (支持中文字体)\n   claude plugin install pdf-creator@daymade-skills\n   ```\n\n## 💡 基本使用\n\n安装完成后，无需复杂配置，直接在 Claude Code 对话中调用即可。\n\n### 1. 使用核心技能：创建你自己的技能\n安装 `skill-creator` 后，你可以让 Claude 帮你开发新技能：\n\n```text\nCreate a new skill called my-awesome-skill in ~\u002Fmy-skills\n```\nClaude 将引导你完成从需求分析、代码编写到最终打包的全过程。\n\n验证或打包已有技能：\n```text\nValidate my skill at ~\u002Fmy-skills\u002Fmy-awesome-skill\nPackage my skill at ~\u002Fmy-skills\u002Fmy-awesome-skill for distribution\n```\n\n### 2. 使用功能型技能示例\n直接描述你的需求，Claude 会自动调用对应的技能插件：\n\n- **GitHub 操作**:\n  ```text\n  Create a pull request for the current branch with title \"Fix login bug\"\n  ```\n  *(自动调用 `github-ops`)*\n\n- **文档转换**:\n  ```text\n  Convert the report.docx in my Downloads folder to markdown\n  ```\n  *(自动调用 `doc-to-markdown`)*\n\n- **图表生成**:\n  ```text\n  Extract mermaid diagrams from README.md and save them as PNGs\n  ```\n  *(自动调用 `mermaid-tools`)*\n\n> 💡 **提示**: 所有技能均独立运行，请根据实际需求按需安装，保持环境轻量。","某全栈开发团队急需为内部运维系统定制一个能自动执行数据库备份与日志清理的专属 Claude 技能，以标准化日常维护流程。\n\n### 没有 claude-code-skills 时\n- 开发者仅凭官方简略文档摸索，缺乏对“何时复用现有 MCP、何时从头构建”的决策指引，导致前期技术选型反复试错。\n- 在交互式开发中容易丢失上下文，因缺少结构化的提问检查点，最终生成的技能逻辑断层，无法处理复杂的异常分支。\n- 完全依赖人工肉眼检查代码安全，极易遗漏硬编码密钥或敏感路径暴露等隐患，直到上线审计时才被发现。\n- 打包发布前缺乏严格的验证机制，常因 YAML 格式微瑕或路径引用错误导致技能在安装后直接崩溃，排查耗时极长。\n- 遇到架构选择难题（如 Inline 还是 Fork 模式）时无处参考，选错模式导致技能静默失败，严重打击团队信心。\n\n### 使用 claude-code-skills 后\n- 借助 `skill-creator` 内置的 8 通道搜索协议与决策矩阵，团队迅速确定了最佳技术路线，避免了重复造轮子。\n- 通过 9 个结构化的用户问答检查点，开发过程始终紧扣上下文，顺利构建出逻辑严密、能自动处理异常的专业技能。\n- 集成 `security_scan.py` 与 gitleaks 在打包前强制执行安全扫描，自动拦截了潜在的密钥泄露风险，确保生产环境安全。\n- 利用增强版验证器全面检查元数据字段与路径完整性，提前修复了所有格式隐患，实现了“一次构建，到处运行”。\n- 参考内置的架构决策指南与真实失败案例库，团队正确选择了 Fork 模式，一次性通过了所有功能测试。\n\nclaude-code-skills 将原本充满不确定性的技能开发过程，转化为一条拥有严格质量门禁与安全护航的工业化生产线。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fdaymade_claude-code-skills_fb1fe82d.png","daymade",null,"https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fdaymade_75354f86.png","资深借书专家","Shanghai","mailto:ZGF5bWFkZXY4OUBnbWFpbA==","https:\u002F\u002Fgithub.com\u002Fdaymade",[83,87,91,95,99,103,107],{"name":84,"color":85,"percentage":86},"Python","#3572A5",90.5,{"name":88,"color":89,"percentage":90},"HTML","#e34c26",5.9,{"name":92,"color":93,"percentage":94},"Shell","#89e051",1.8,{"name":96,"color":97,"percentage":98},"Swift","#F05138",0.6,{"name":100,"color":101,"percentage":102},"JavaScript","#f1e05a",0.5,{"name":104,"color":105,"percentage":106},"PowerShell","#012456",0.4,{"name":108,"color":109,"percentage":110},"CSS","#663399",0.3,779,119,"2026-04-05T17:49:42","MIT",1,"Linux, macOS, Windows","未说明",{"notes":119,"python":117,"dependencies":120},"该工具是 Claude Code 的技能（插件）市场，而非独立的 AI 模型，因此无需 GPU 或大量内存。核心依赖是安装 Claude Code CLI (v2.0.13+)。部分技能有特定系统要求：例如 'mermaid-tools' 在 Windows 上可能需要 WSL2 和 Chrome；'doc-to-markdown' 优化了 Windows\u002FWSL 路径处理。中国用户推荐使用 'CC-Switch' 工具来管理 API 提供商配置（如切换到 DeepSeek、Qwen 等国内模型）。安装可通过应用内命令 `\u002Fplugin` 或终端 `claude plugin` 完成，也提供了一键安装脚本。",[121,122,123,124],"Claude Code CLI (版本 2.0.13+)","gh CLI (用于 github-ops)","PyMuPDF (用于 doc-to-markdown)","Chrome\u002FPuppeteer (用于 mermaid-tools, WSL2 支持)",[15,36],"2026-03-27T02:49:30.150509","2026-04-06T11:30:58.537135",[],[130,135,140,145,150,155,160,165,170,175,180,185,190,195,200,205],{"id":131,"version":132,"summary_zh":133,"released_at":134},108815,"v1.37.0","## 新技能\n\n### excel-automation\n创建格式化的 Excel 工作簿，通过 stdlib 的 XML\u002FZIP 工作流解析复杂的 .xlsm 文件，并通过 AppleScript 在 macOS 上控制 Excel 窗口。\n\n安装：\n```bash\nclaude plugin install excel-automation@daymade-skills\n```\n\n### capture-screen\n使用 Swift CGWindowID 发现和 screencapture 窗口捕获模式，实现 macOS 截图的编程化工作流。\n\n安装：\n```bash\nclaude plugin install capture-screen@daymade-skills\n```\n\n## 改进\n\n- 修复了技能示例中引用的 `promptfoo-evaluation\u002Fscripts\u002Fmetrics.py` 文件缺失问题\n- 将 `promptfoo-evaluation` 插件版本升级至 `1.1.0`\n- 更新市场元数据至 `1.37.0`，并同步以下文档：\n  - README.md\n  - README.zh-CN.md\n  - CLAUDE.md\n  - CHANGELOG.md\n\n## 市场概览\n\n- 技能\u002F插件：41 个\n- 市场版本：1.37.0","2026-03-02T12:08:09",{"id":136,"version":137,"summary_zh":138,"released_at":139},108816,"v1.33.0","## tunnel-doctor v1.0.0 → v1.1.0\n\n### 新增：远程开发标准操作流程\n\n针对通过 Tailscale 使用代理工具进行远程开发的主动式设置指南：\n\n- **代理安全的 Makefile 模式** — 所有健康检查和预热的 `curl` 命令均使用 `--noproxy localhost`\n- **SSH 隧道 Makefile 目标** — `tunnel`（前台运行）和 `tunnel-bg`（后台运行，配合 autossh 自动重连）\n- **多端口隧道配置** — 可在一个隧道中同时转发开发服务器、S3 存储以及 API 网关\n- **SSH 非登录 Shell 设置** — 使用 `source ~\u002F.zshrc` 模式，并结合 Makefile 中的 `REMOTE_CMD` 宏\n- **端到端工作流** — 包括首次设置及日常开发流程\n- **飞行前检查清单** — 在开始远程开发之前需验证的 10 项内容\n\n### 新增诊断步骤\n\n- **步骤 2D**：通过 SSH 本地端口转发修复认证重定向问题（解决 `APP_URL=localhost` 导致的重定向错误）\n- **步骤 2E**：在 Makefile 和脚本中处理 localhost 代理拦截问题\n\n### 质量改进（经技能评审员审核）\n\n- 修正了步骤顺序：2A→2B→2C→2D→2E（原为 2A→2C→2D→2E→2B）\n- 根据技能最佳实践，将描述调整为第三人称语气\n- 将 5 个硬编码 IP 替换为 `\u003Ctailscale-ip>` 占位符\n- 去除重复的 SSH 非登录 Shell 内容（引用 proxy_fixes.md 文件）\n- 新增关键词：ssh-tunnel、autossh、makefile、remote-development\n\n### 参考资料更新\n\n- 新增 SSH 非登录 Shell 易错点说明\n- 新增 localhost 代理拦截说明\n- 强化了关于 `--data-binary` 与 `-d` 的警告提示（防止配置被破坏）","2026-02-15T18:27:46",{"id":141,"version":142,"summary_zh":143,"released_at":144},108817,"v1.32.1","## 更新技能：claude-md-progressive-disclosurer v1.2.0\n\n在 CLAUDE.md 优化过程中，加强了防止信息丢失的保障措施。\n\n### 新增内容\n\n- **“原样移动，不压缩”铁律** — 移至第 2 级的内容必须逐字复制，不得进行任何“附带性删减”\n- **反模式 6：移动时压缩** — 移动和简化是两个独立的操作，绝不能混为一谈\n- **反模式 7：将损失伪装成“有意删除”** — 每一次删除都必须事先有明确决策，并以规范来源为依据，而非事后找理由搪塞\n- **增强的第 5 步验证** — 包含三项必查内容：文件是否存在（5a）、使用 diff 脚本检查内容完整性（5b）、禁止统计行数（5c）\n- **全局禁止使用 `wc -l`** — 在所有工作流阶段均被禁止，包括最终总结环节\n- **真实案例研究 8 和 9** — 记录了因移动时压缩以及事后归类删除而导致信息丢失的实际事件\n\n### 安装方法\n\n```bash\nclaude plugin install claude-md-progressive-disclosurer@daymade-skills\n```\n\n🤖 由 [Claude Code](https:\u002F\u002Fclaude.com\u002Fclaude-code) 生成","2026-02-13T21:49:34",{"id":146,"version":147,"summary_zh":148,"released_at":149},108818,"v1.30.0","## 新技能：竞争对手分析\n\n基于证据的竞争对手跟踪与分析。**所有分析必须基于实际代码，绝不能依赖假设。**\n\n### 功能特性\n\n- **分析前检查清单**：确保在进行任何分析之前，仓库已本地克隆\n- **禁止使用模式**：防止出现假设性表述（如“推测…”、“可能…”、“应该…”）\n- **必需引用模式**：用于明确来源引用（文件:行号格式）\n- **技术栈分析指南**：适用于 Node.js、Python 和 Rust 项目\n- **目录结构规范**：用于有序管理竞争对手信息\n- **内置模板**：profile_template.md、analysis_checklist.md\n- **管理脚本**：update-competitors.sh（克隆\u002F拉取\u002F状态检查）\n\n### 安装步骤\n\n```bash\nclaude plugin marketplace update daymade-skills\nclaude plugin install competitors-analysis@daymade-skills\n```\n\n### 使用方法\n\n```bash\n# 然后请 Claude 分析某个竞争对手\n“分析竞品 https:\u002F\u002Fgithub.com\u002Forg\u002Frepo”\n“将该竞品添加到 flowzero 产品的竞品列表”\n```\n\n### 完整变更日志\n\n完整变更记录请参阅 [CHANGELOG.md](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\u002Fblob\u002Fmain\u002FCHANGELOG.md)。\n\n---\n\n🤖 由 [Claude Code](https:\u002F\u002Fclaude.ai\u002Fcode) 生成","2026-01-29T16:08:34",{"id":151,"version":152,"summary_zh":153,"released_at":154},108819,"v1.29.0","## 增强型技能：skill-creator v1.4.0\n\n本次发布基于社区贡献（PR #6，由 [@costa-marcello](https:\u002F\u002Fgithub.com\u002Fcosta-marcello) 提交），显著改进了 skill-creator 的文档。\n\n### 新特性\n\n- **完整的 YAML Frontmatter 参考**：全面的表格，记录了所有可用字段（`name`、`description`、`context`、`agent`、`disable-model-invocation`、`user-invocable`、`allowed-tools`、`model`、`argument-hint`、`hooks`）。\n\n- **`context: fork` 文档**：关键指南，用于创建可通过 Task 工具被子代理访问的技能。\n\n- **调用控制表**：清晰的对比表格，展示不同 frontmatter 组合如何影响技能的可访问性（用户可调用、Claude 可调用、子代理可访问）。\n\n- **`$ARGUMENTS` 占位符**：文档说明了技能内容如何通过 `\u002Fskill-name arguments` 接收用户输入。\n\n- **增强的示例**：\n  - `allowed-tools` 的通配符语法：`Bash(git *)`、`Bash(npm *)`、`Bash(docker compose *)`。\n  - 内联 `hooks` 配置示例。\n  - 基于 Task 的技能，支持子代理执行。\n  - 运行内联的参考技能。\n\n- **更新的 init_skill.py 模板**：新创建的技能现在包含带注释的可选 frontmatter 字段。\n\n### 安装\n\n```bash\nclaude plugin marketplace update daymade-skills\nclaude plugin install skill-creator@daymade-skills\n```\n\n### 贡献者\n\n- [@costa-marcello](https:\u002F\u002Fgithub.com\u002Fcosta-marcello) - PR #6：初始 frontmatter 文档。\n\n---\n\n🤖 由 [Claude Code](https:\u002F\u002Fclaude.com\u002Fclaude-code) 生成","2026-01-29T12:20:43",{"id":156,"version":157,"summary_zh":158,"released_at":159},108820,"v1.28.0","## 增强型技能：会议记录员 v1.1.0\n\n新增发言者识别功能及预处理流水线，以提升转录文本的处理效果。\n\n### 新特性\n\n**发言者识别**\n\n通过分析转录文本的各项特征来识别匿名发言者：\n\n| 特征         | 关注点                                       |\n|--------------|----------------------------------------------|\n| 词数         | 总词数（高 = 高级成员\u002F负责人，低 = 观察者）   |\n| 段落数量     | 发言频率（频繁 = 积极参与者）                |\n| 平均段落长度 | 每次发言的词数（长 = 主讲人，短 = 回应者）    |\n| 填充词比例   | 填充词所占百分比 - 低 = 准备充分的发言人      |\n\n**上下文文件模板**\n\n新增 `references\u002Fcontext_file_template.md`，用于团队成员信息映射：\n- 团队成员的角色与沟通风格\n- 项目术语及命名规范\n- 基于特征的自动发言者匹配\n\n**智能文件命名**\n\n自动生成输出文件名：`YYYY-MM-DD-\u003C主题>-\u003C类型>.md`\n\n示例：\n- `2026-01-25-order-api设计评审.md`\n- `2026-01-20 sprint计划会议.md`\n\n**预处理流水线**\n\n与其他技能集成：\n- `markdown-tools` - 先将 .docx\u002F.pdf 转换为 Markdown 格式\n- `transcript-fixer` - 在处理前修复 ASR\u002FSTT 错误\n\n### 完整变更日志\nhttps:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\u002Fblob\u002Fmain\u002FCHANGELOG.md","2026-01-25T13:57:37",{"id":161,"version":162,"summary_zh":163,"released_at":164},108821,"v1.27.0","## 增强技能：markdown-tools v1.2.0\n\n用于高质量文档转Markdown的多工具编排。\n\n### 新特性\n\n**双模式架构**\n| 模式 | 速度 | 质量 | 使用场景 |\n|------|-------|---------|----------|\n| 快速 | 快 | 良好 | 草稿、简单文档 |\n| 重型 | 较慢 | 最佳 | 最终文档、复杂布局 |\n\n**工具选择矩阵**\n| 格式 | 快速模式 | 重型模式 |\n|--------|------------|------------|\n| PDF | pymupdf4llm | pymupdf4llm + markitdown |\n| DOCX | pandoc | pandoc + markitdown |\n| PPTX | markitdown | markitdown + pandoc |\n\n**新脚本**\n- `convert.py` - 主编排脚本，支持快速\u002F重型模式\n- `merge_outputs.py` - 段落级多工具输出合并器\n- `validate_output.py` - 带HTML报告的质量验证工具\n\n**增强脚本**\n- `extract_pdf_images.py` - 现在包含元数据（页码、位置、尺寸）\n\n**质量指标**\n| 指标 | 合格 | 警告 | 不合格 |\n|--------|------|------|------|\n| 文本保留率 | >95% | 85-95% | \u003C85% |\n| 表格保留率 | 100% | 90-99% | \u003C90% |\n| 图片保留率 | 100% | 80-99% | \u003C80% |\n\n### 安装\n\n```bash\n# 安装依赖\npip install pymupdf4llm\nuv tool install \"markitdown[pdf]\"\nbrew install pandoc\n\n# 快速转换\nuv run --with pymupdf4llm --with markitdown scripts\u002Fconvert.py doc.pdf -o out.md\n\n# 重型模式（最佳质量）\nuv run --with pymupdf4llm --with markitdown scripts\u002Fconvert.py doc.pdf -o out.md --heavy\n\n# 质量验证\nuv run --with pymupdf scripts\u002Fvalidate_output.py doc.pdf out.md --report report.html\n```\n\n### 完整变更日志\nhttps:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\u002Fblob\u002Fmain\u002FCHANGELOG.md","2026-01-25T13:36:45",{"id":166,"version":167,"summary_zh":168,"released_at":169},108822,"v1.26.0","## 新技能：深度研究\n\n生成格式规范的研究报告，支持证据追踪、引用标注及迭代式审阅。\n\n特性：\n- 报告规格与格式契约工作流\n- 多轮并行撰写与 UNION 合并\n- 包含来源质量评估标准的证据表格\n- 引用验证与冲突处理\n- 捆绑式参考资料：报告模板、排版规范、研究计划检查清单、来源质量评估标准、完整性检查清单\n\n安装：\n```bash\nclaude plugin install deep-research@daymade-skills\n```\n\n更新日志：完整详情请参阅 CHANGELOG.md。\n","2026-01-25T07:46:10",{"id":171,"version":172,"summary_zh":173,"released_at":174},108823,"v1.25.0","## 新技能：会议记录员\n\n通过迭代式的人工审核，将会议记录转换为高保真、结构化的会议纪要。\n\n**功能：**\n- 多轮并行生成，采用 UNION 合并策略\n- 基于证据的记录方式，包含发言者引用\n- 用于架构讨论的 Mermaid 图表\n- 迭代式的人机协作优化流程\n- 跨 AI 比较以减少偏差\n- 完整性检查清单，便于系统性审查\n\n**安装：**\n```bash\nclaude plugin install meeting-minutes-taker@daymade-skills\n```\n\n## skill-creator v1.3.0\n\n新增了从商业项目中提取技能的 **第 5 步：内容净化审核（可选）**：\n- 需要净化的 8 类内容（产品名称、人名、实体、路径、行话等）\n- 自动化 grep 扫描命令，用于检测敏感内容\n- 三阶段净化流程，并附验证步骤\n- 新增 `references\u002Fsanitization_checklist.md` 文件，提供详细指导\n\n## 完整更新日志\n- 新技能：会议记录员 v1.0.0\n- skill-creator 更新：v1.2.2 → v1.3.0\n- 市场更新：v1.24.0 → v1.25.0\n- 技能总数：33 项","2026-01-24T15:16:13",{"id":176,"version":177,"summary_zh":178,"released_at":179},108824,"v1.24.0","## v1.24.0 (2026-01-22)\n\n### 新增\n- **新技能**: claude-skills-troubleshooting - 诊断并解决 Claude Code 插件及技能配置问题\n  - 插件安装与启用调试\n  - installed_plugins.json 与 settings.json 中 enabledPlugins 的对比诊断\n  - 市场缓存新鲜度检测\n  - 插件状态架构文档\n  - 捆绑诊断脚本 (diagnose_plugins.py)\n  - 用于批量启用缺失插件的脚本 (enable_all_plugins.py)\n  - 已知 GitHub 问题跟踪 (#17832, #19696, #17089, #13543, #16260)\n  - 技能与命令架构说明\n\n### 变更\n- 更新市场技能数量从 31 个至 32 个\n- 更新市场版本从 1.23.0 至 1.24.0\n- 更新 README.md 中的徽章（技能数量、版本）\n- 更新 README.md，将 claude-skills-troubleshooting 加入技能列表\n- 更新 README.zh-CN.md 中的徽章（技能数量、版本）\n- 更新 README.zh-CN.md，将 claude-skills-troubleshooting 加入技能列表\n- 更新 CLAUDE.md 中的技能数量，从 31 个至 32 个\n- 在 README.md 中新增 claude-skills-troubleshooting 使用场景章节\n- 在 README.zh-CN.md 中新增 claude-skills-troubleshooting 使用场景章节","2026-01-22T15:08:24",{"id":181,"version":182,"summary_zh":183,"released_at":184},108825,"v1.21.1","## Updated Skill: macos-cleaner v1.1.0\n\nMajor improvements based on real-world usage experience with tmux + Mole deep exploration workflow.\n\n### New Principles\n- **Value Over Vanity**: Goal is identifying truly useless items, not maximizing cleanup numbers\n- **Network Environment Awareness**: Consider slow internet (especially in China) when recommending cache deletion\n- **Impact Analysis Required**: Every cleanup recommendation must explain consequences\n\n### New Sections\n- **Anti-Patterns**: Comprehensive guide on what NOT to delete (Xcode DerivedData, npm _cacache, uv cache, Playwright, iOS DeviceSupport, Docker stopped containers, AI model caches)\n- **Multi-Layer Deep Exploration**: Complete tmux + Mole TUI navigation workflow with recommended exploration path\n- **High-Quality Report Template**: Proven 3-tier classification report format (🟢 Absolutely Safe \u002F 🟡 Trade-off Required \u002F 🔴 Do Not Delete)\n- **Report Quality Checklist**: 8-point verification before presenting findings\n\n### Safety Improvements\n- Explicit prohibition of `docker volume prune -f` - must confirm per-project\n- Updated safety principles to emphasize cache value over cleanup metrics\n\n## Installation\n\n```bash\nclaude plugin marketplace update daymade-skills\nclaude plugin install macos-cleaner@daymade-skills\n```\n\n---\n\n🤖 Generated with [Claude Code](https:\u002F\u002Fclaude.ai\u002Fcode)","2026-01-11T09:51:41",{"id":186,"version":187,"summary_zh":188,"released_at":189},108826,"v1.19.0","## 🎉 New Skill: Fact-Checker v1.0.0\n\nComprehensive fact-checking skill that verifies claims using web search and official sources, then proposes corrections with user confirmation.\n\n### ✨ Features\n\n- **5-Step Workflow**: Identify → Search → Compare → Report → Apply\n- **Multi-Domain Support**: AI models, technical docs, statistics, general facts\n- **Source Evaluation**: Prioritizes official documentation and authoritative sources\n- **User Approval Gates**: Never applies changes without explicit confirmation\n- **Temporal Context**: Adds date markers to prevent information decay\n\n### 🎯 Use Cases\n\n- Update outdated AI model specifications\n- Verify technical documentation claims\n- Validate statistical data and benchmarks\n- Check version numbers and release dates\n\n### 📝 Real-World Example\n\nSuccessfully updated AI model context window specifications:\n- Claude 3.5 Sonnet → Claude Sonnet 4.5\n- GPT-4o (128K) → GPT-5.2 (400K)\n- Gemini 1.5 Pro (2M) → Gemini 3 Pro (1M)\n\n### 🚀 Installation\n\n\\`\\`\\`bash\nccpm install @daymade-skills\u002Ffact-checker\n\\`\\`\\`\n\n### 🔑 Trigger Keywords\n\n- \"fact-check this document\"\n- \"verify these claims\"\n- \"check if this is accurate\"\n- \"update outdated information\"\n\n### 📦 What's Changed\n\n**New:**\n- fact-checker skill v1.0.0 with comprehensive workflow\n- Source evaluation framework\n- Auto-correction with approval gates\n\n**Updated:**\n- Marketplace version bumped to 1.19.0\n- Metadata description updated\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\u002Fcompare\u002Fv1.18.1...v1.19.0","2026-01-05T15:43:15",{"id":191,"version":192,"summary_zh":193,"released_at":194},108827,"v1.10.0","## 🎉 New Skill: qa-expert\n\nComprehensive QA testing infrastructure with autonomous LLM execution, Google Testing Standards, and OWASP security best practices.\n\n### 💡 Key Innovation: Autonomous Execution\n\nThe **master prompt** enables LLM to auto-execute entire test suites **100x faster** than manual execution, with zero human error in tracking. Perfect for third-party QA handoffs - just provide the master prompt and they can start testing immediately.\n\n### ✨ Key Features\n\n- **One-command initialization**: Complete QA infrastructure with templates, CSVs, and documentation\n- **Autonomous execution**: Master prompt enables LLM to auto-execute all tests, auto-track results, auto-file bugs\n- **Google Testing Standards**: AAA pattern compliance, 90% coverage targets, fail-fast validation\n- **OWASP security testing**: 90% Top 10 coverage with specific attack vectors\n- **Quality gates enforcement**: 100% execution, ≥80% pass rate, 0 P0 bugs, ≥80% code coverage\n- **Ground Truth Principle**: Prevents doc\u002FCSV sync issues (test docs = authoritative source)\n- **Bug tracking**: P0-P4 classification with detailed repro steps\n- **Day 1 onboarding**: 5-hour guide for new QA engineers\n- **30+ LLM prompts**: Ready-to-use prompts for specific QA tasks\n- **Metrics dashboard**: Test execution progress, pass rate, bug analysis, quality gates status\n\n### 📦 Installation\n\n```bash\nclaude plugin marketplace add daymade\u002Fclaude-code-skills\nclaude plugin install qa-expert@daymade\u002Fclaude-code-skills\n```\n\n### 🚀 Quick Start\n\n```bash\n# Initialize QA project (creates full infrastructure)\npython3 scripts\u002Finit_qa_project.py my-app .\u002F\n\n# Calculate quality metrics and gates status\npython3 scripts\u002Fcalculate_metrics.py tests\u002FTEST-EXECUTION-TRACKING.csv\n\n# For autonomous execution, copy master prompt from:\n# references\u002Fmaster_qa_prompt.md → paste to LLM → auto-executes tests\n```\n\n### 📚 Documentation\n\nSee [qa-expert\u002Freferences\u002F](.\u002Fqa-expert\u002Freferences\u002F) for:\n- `master_qa_prompt.md` - Single command for autonomous execution (100x speedup)\n- `google_testing_standards.md` - AAA pattern, coverage thresholds, OWASP testing\n- `day1_onboarding.md` - 5-hour onboarding timeline for new QA engineers\n- `ground_truth_principle.md` - Preventing doc\u002FCSV sync issues\n- `llm_prompts_library.md` - 30+ ready-to-use QA prompts\n\n---\n\n## 🔧 SOP Improvements\n\nEnhanced \"Adding a New Skill to Marketplace\" workflow in CLAUDE.md:\n\n- **Added mandatory Step 7**: Update README.zh-CN.md (Chinese documentation)\n- **Added 6 new checklist items**: Chinese documentation verification\n- **Updated Common Mistakes**: 8 comprehensive error reminders\n- **Made Chinese docs MANDATORY**: README.zh-CN.md is now required\n- **Added sync verification commands**: Ensure EN\u002FZH versions match\n\n---\n\n## 📊 Marketplace Status\n\n- **Total Skills**: 17 production-ready skills\n- **Version**: v1.10.0\n- **Categories**: developer-tools, document-conversion, documentation, customization, communication, utilities, assets, design, productivity, security, media\n\nSee full [CHANGELOG](.\u002FCHANGELOG.md) for detailed changes.","2025-11-09T17:54:47",{"id":196,"version":197,"summary_zh":198,"released_at":199},108828,"v1.9.0","## 🎬 New Skill: video-comparer v1.0.0\n\nA specialized agent for comparing videos and analyzing compression quality with interactive HTML reports.\n\n### Features\n- Compare original and compressed videos with visual quality analysis\n- Calculate objective quality metrics (PSNR, SSIM) for compression evaluation\n- Generate frame-by-frame comparisons with three viewing modes:\n  - **Slider**: Interactive overlay comparison\n  - **Side-by-side**: Synchronized dual view\n  - **Grid**: Multi-frame comparison\n- Extract comprehensive video metadata (codec, resolution, bitrate, duration, file size)\n- Self-contained HTML output with embedded frames (no server required)\n- Bundled security-hardened Python script with path validation and resource limits\n\n### Installation\n```bash\nclaude plugin install video-comparer@daymade\u002Fclaude-code-skills\n```\n\n### Requirements\n- FFmpeg (multi-platform installation instructions included)\n- Python 3.6+ (for standalone script usage)\n\n---\n\n## 🔧 transcript-fixer Enhancements\n\nMajor feature additions to improve performance, scalability, and reliability:\n\n### New Features\n- **Async AI processor**: Parallel processing for faster transcription corrections\n- **Connection pool management**: Efficient database connection handling\n- **Concurrency manager**: Control concurrent operations with rate limiting\n- **Audit log retention**: Automatic cleanup with configurable retention periods\n- **Database migrations**: Schema versioning and migration framework\n- **Health check system**: Monitor service health and dependencies\n- **Metrics monitoring**: Track performance and usage statistics\n- **Enhanced security**: Domain and path validators with comprehensive validation rules\n\n### Testing\n- 8 new comprehensive test suites added\n- Tests cover: audit logs, connection pool, domain validator, error recovery, learning engine, path validator\n\n---\n\n## 📦 Marketplace Updates\n\n- Updated marketplace version: **1.8.0 → 1.9.0**\n- Total skills: **16** (previously 15)\n- Updated documentation across README.md, CLAUDE.md, and CHANGELOG.md\n\n---\n\n## 📚 Available Skills\n\nThis marketplace now includes 16 production-ready skills:\nskill-creator ⭐, github-ops, markdown-tools, mermaid-tools, statusline-generator, teams-channel-post-writer, repomix-unmixer, llm-icon-finder, cli-demo-generator, cloudflare-troubleshooting, ui-designer, ppt-creator, youtube-downloader, repomix-safe-mixer, transcript-fixer, **video-comparer** ✨\n\n---\n\n## 🚀 Getting Started\n\n```bash\n# Install the entire marketplace\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002Fdaymade\u002Fclaude-code-skills\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n\n# Or install specific skills\nclaude plugin marketplace add daymade\u002Fclaude-code-skills\nclaude plugin install video-comparer@daymade\u002Fclaude-code-skills\n```\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\u002Fblob\u002Fmain\u002FCHANGELOG.md","2025-10-29T16:41:14",{"id":201,"version":202,"summary_zh":203,"released_at":204},108829,"v1.5.0","## 🎉 New Skill: ppt-creator\n\nThis release adds **ppt-creator**, a comprehensive skill for creating professional, persuasive presentation decks with data-driven visualizations and dual-format PPTX output.\n\n### ✨ Key Features\n\n- **Structured Storytelling**: Pyramid Principle (conclusion → reasons → evidence)\n- **Assertion-Evidence Framework**: Every slide heading is a testable assertion\n- **Automatic Data Synthesis**: Generate CSV data from specifications\n- **Chart Generation**: matplotlib-powered visualizations (180 DPI, presentation-quality)\n- **Dual-Path PPTX Output**:\n  - Marp CLI export (native Marp styling)\n  - document-skills:pptx (reveal.js styling)\n- **Complete Orchestration**: End-to-end automation from topic → complete PPTX with charts\n- **Quality Scoring**: 100-point rubric with auto-refinement (target: 75+)\n- **Speaker Notes**: 45-60 second notes per slide\n\n### 📦 What's New\n\n**Marketplace:**\n- Version bumped to v1.5.0 (12 skills total)\n- Added ppt-creator v1.0.0 to plugin registry\n\n**Skills:**\n- ✅ skill-creator: Added versioning principle (SKILL.md should not contain versions)\n- ✅ ppt-creator: New skill with 4,916 lines across 13 files\n\n**Documentation:**\n- Updated README badges (skills: 11→12, version: 1.4.0→1.5.0)\n- Added ppt-creator demo GIF (cli-demo-generator)\n- Added \\\"Presentations & Business Communication\\\" use case\n- Added requirements: pandas\u002Fmatplotlib, Marp CLI\n\n### 📚 ppt-creator Structure\n\n```\nppt-creator\u002F\n├── SKILL.md (170 lines)\n├── scripts\u002Fchartkit.py\n└── references\u002F\n    ├── INTAKE.md (10-item questionnaire)\n    ├── WORKFLOW.md (9-stage process)\n    ├── TEMPLATES.md (slide patterns)\n    ├── VIS-GUIDE.md (chart selection)\n    ├── STYLE-GUIDE.md (visual standards)\n    ├── RUBRIC.md (quality scoring)\n    ├── CHECKLIST.md (pre-flight)\n    ├── EXAMPLES.md (usage examples)\n    ├── ORCHESTRATION_OVERVIEW.md (251 lines)\n    ├── ORCHESTRATION_DATA_CHARTS.md (141 lines)\n    └── ORCHESTRATION_PPTX.md (656 lines)\n```\n\n### 🚀 Installation\n\n```bash\n\u002Fplugin marketplace add daymade\u002Fclaude-code-skills\n\u002Fplugin marketplace install daymade\u002Fclaude-code-skills#ppt-creator\n```\n\n### 💡 Usage Examples\n\n**Simple request:**\n```\n\"Create a presentation about renewable energy for a board meeting\"\n```\n\n**With data:**\n```\n\"Generate complete PPTX from these Q3 sales data files [uploads CSVs]\"\n```\n\n**Orchestration mode (automatic):**\n- Triggers on phrases: \"complete PPTX\", \"final deliverable\", \"presentation-ready\"\n- Delivers TWO complete versions (Marp + document-skills styling)\n- Duration: 4-6 minutes (parallel execution)\n\n### 🔧 Dependencies (Optional)\n\n- **pandas & matplotlib**: For chart generation\n- **Marp CLI**: For Marp PPTX export (`npm install -g @marp-team\u002Fmarp-cli`)\n- **document-skills:pptx**: Alternative PPTX path (Anthropic skill)\n\n### 📖 Best Practices Improvements\n\n**skill-creator updates:**\n- Added versioning principle: SKILL.md should NOT contain version history\n- Versions tracked in marketplace.json only (`plugins[].version`)\n- SKILL.md should be timeless content focused on functionality\n\n### 🛠️ Technical Details\n\n**Compliance Score**: 8.0\u002F10 (from initial 6.5\u002F10)\n- ✅ BLOCKER #1 resolved: Path references (resources\u002F → references\u002F)\n- ✅ BLOCKER #2 resolved: File length (ORCHESTRATION.md split into 3 files)\n- ✅ All cross-references updated\n- ✅ Validated with quick_validate.py\n\n**Architecture:**\n- Progressive disclosure: SKILL.md (170 lines) → 9 reference files → scripts\n- Dual-path orchestration: Marp + document-skills:pptx in parallel\n- Quality gates at each stage (8b→8c→8d→8e)\n\n### 📊 Marketplace Stats\n\n- **Total Skills**: 12\n- **Version**: 1.5.0\n- **Package Size**: ppt-creator.zip (72KB)\n- **Lines of Code**: 4,916 (ppt-creator)\n\n### 🙏 Acknowledgments\n\nBuilt following Anthropic's Agent Skills best practices and verified against official skills repository structure.\n\n---\n\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\u002Fcompare\u002Fv1.4.0...v1.5.0","2025-10-26T00:46:16",{"id":206,"version":207,"summary_zh":208,"released_at":209},108830,"v1.4.0","## 🎉 New Skills\n\nThis release adds two powerful new skills to the marketplace:\n\n### 1. 🔧 cloudflare-troubleshooting\n**Category:** Developer Tools  \n**Purpose:** API-driven Cloudflare diagnostics and issue resolution\n\n**Features:**\n- Systematic investigation of SSL errors, DNS issues, and redirect loops\n- Direct Cloudflare API integration for evidence-based troubleshooting\n- Bundled Python scripts for automated config checking and SSL mode fixes\n- Comprehensive reference documentation for SSL modes, API overview, and common issues\n\n**Use Cases:**\n- Debugging `ERR_TOO_MANY_REDIRECTS` errors\n- SSL\u002FTLS certificate issues\n- DNS propagation problems\n- Cloudflare configuration audits\n\n**Installation:**\n\\`\\`\\`bash\n\u002Fplugin marketplace install daymade\u002Fclaude-code-skills#cloudflare-troubleshooting\n\\`\\`\\`\n\n---\n\n### 2. 🎨 ui-designer\n**Category:** Design  \n**Purpose:** Extract design systems from UI mockups and generate implementation-ready prompts\n\n**Features:**\n- Automated design system extraction from screenshots\u002Fmockups\n- Color palette, typography, and spacing analysis\n- Design system documentation generation\n- PRD and implementation prompt creation\n- Bundled templates for consistent design patterns\n\n**Use Cases:**\n- Building MVP UIs matching reference designs\n- Creating design system documentation from existing apps\n- Generating UI implementation prompts for developers\n- Maintaining consistent design across multiple projects\n\n**Installation:**\n\\`\\`\\`bash\n\u002Fplugin marketplace install daymade\u002Fclaude-code-skills#ui-designer\n\\`\\`\\`\n\n---\n\n## 📦 Marketplace Updates\n\n- **Total skills:** 11 (was 9)\n- **Version:** 1.4.0 (from 1.3.0)\n- **New categories:** Design (ui-designer)\n- **Enhanced DevOps capabilities:** Cloudflare troubleshooting\n\n## 🔧 Other Improvements\n\n- Enhanced `.gitignore` patterns for archives and build artifacts\n- Updated marketplace metadata to reflect new capabilities\n- Improved documentation structure for bundled resources\n\n## 📚 Full Skill List\n\n1. **skill-creator** - Meta-skill for creating Claude Code skills\n2. **github-ops** - GitHub operations via gh CLI\n3. **markdown-tools** - Document conversion to markdown\n4. **mermaid-tools** - Diagram generation and extraction\n5. **statusline-generator** - Claude Code statusline customization\n6. **teams-channel-post-writer** - Microsoft Teams communication\n7. **repomix-unmixer** - Extract files from repomix packages\n8. **llm-icon-finder** - AI\u002FLLM brand icon access\n9. **cli-demo-generator** - Animated CLI demo creation\n10. **cloudflare-troubleshooting** ⭐ NEW\n11. **ui-designer** ⭐ NEW\n\n## 🚀 Quick Start\n\n\\`\\`\\`bash\n# Install all skills\n\u002Fplugin marketplace add daymade\u002Fclaude-code-skills\n\n# Install specific skills\n\u002Fplugin marketplace install daymade\u002Fclaude-code-skills#cloudflare-troubleshooting\n\u002Fplugin marketplace install daymade\u002Fclaude-code-skills#ui-designer\n\\`\\`\\`\n\n---\n\n**What's Changed:** [v1.3.0...v1.4.0](https:\u002F\u002Fgithub.com\u002Fdaymade\u002Fclaude-code-skills\u002Fcompare\u002Fv1.3.0...v1.4.0)","2025-10-25T07:33:42"]