[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-github--spec-kit":3,"tool-github--spec-kit":62},[4,18,26,36,46,54],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":17},4358,"openclaw","openclaw\u002Fopenclaw","OpenClaw 是一款专为个人打造的本地化 AI 助手，旨在让你在自己的设备上拥有完全可控的智能伙伴。它打破了传统 AI 助手局限于特定网页或应用的束缚，能够直接接入你日常使用的各类通讯渠道，包括微信、WhatsApp、Telegram、Discord、iMessage 等数十种平台。无论你在哪个聊天软件中发送消息，OpenClaw 都能即时响应，甚至支持在 macOS、iOS 和 Android 设备上进行语音交互，并提供实时的画布渲染功能供你操控。\n\n这款工具主要解决了用户对数据隐私、响应速度以及“始终在线”体验的需求。通过将 AI 部署在本地，用户无需依赖云端服务即可享受快速、私密的智能辅助，真正实现了“你的数据，你做主”。其独特的技术亮点在于强大的网关架构，将控制平面与核心助手分离，确保跨平台通信的流畅性与扩展性。\n\nOpenClaw 非常适合希望构建个性化工作流的技术爱好者、开发者，以及注重隐私保护且不愿被单一生态绑定的普通用户。只要具备基础的终端操作能力（支持 macOS、Linux 及 Windows WSL2），即可通过简单的命令行引导完成部署。如果你渴望拥有一个懂你",349277,3,"2026-04-06T06:32:30",[13,14,15,16],"Agent","开发框架","图像","数据工具","ready",{"id":19,"name":20,"github_repo":21,"description_zh":22,"stars":23,"difficulty_score":10,"last_commit_at":24,"category_tags":25,"status":17},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,"2026-04-05T11:01:52",[14,15,13],{"id":27,"name":28,"github_repo":29,"description_zh":30,"stars":31,"difficulty_score":32,"last_commit_at":33,"category_tags":34,"status":17},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",159267,2,"2026-04-17T11:29:14",[14,13,35],"语言模型",{"id":37,"name":38,"github_repo":39,"description_zh":40,"stars":41,"difficulty_score":42,"last_commit_at":43,"category_tags":44,"status":17},8272,"opencode","anomalyco\u002Fopencode","OpenCode 是一款开源的 AI 编程助手（Coding Agent），旨在像一位智能搭档一样融入您的开发流程。它不仅仅是一个代码补全插件，而是一个能够理解项目上下文、自主规划任务并执行复杂编码操作的智能体。无论是生成全新功能、重构现有代码，还是排查难以定位的 Bug，OpenCode 都能通过自然语言交互高效完成，显著减少开发者在重复性劳动和上下文切换上的时间消耗。\n\n这款工具专为软件开发者、工程师及技术研究人员设计，特别适合希望利用大模型能力来提升编码效率、加速原型开发或处理遗留代码维护的专业人群。其核心亮点在于完全开源的架构，这意味着用户可以审查代码逻辑、自定义行为策略，甚至私有化部署以保障数据安全，彻底打破了传统闭源 AI 助手的“黑盒”限制。\n\n在技术体验上，OpenCode 提供了灵活的终端界面（Terminal UI）和正在测试中的桌面应用程序，支持 macOS、Windows 及 Linux 全平台。它兼容多种包管理工具，安装便捷，并能无缝集成到现有的开发环境中。无论您是追求极致控制权的资深极客，还是渴望提升产出的独立开发者，OpenCode 都提供了一个透明、可信",144296,1,"2026-04-16T14:50:03",[13,45],"插件",{"id":47,"name":48,"github_repo":49,"description_zh":50,"stars":51,"difficulty_score":32,"last_commit_at":52,"category_tags":53,"status":17},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",108322,"2026-04-10T11:39:34",[14,15,13],{"id":55,"name":56,"github_repo":57,"description_zh":58,"stars":59,"difficulty_score":32,"last_commit_at":60,"category_tags":61,"status":17},6121,"gemini-cli","google-gemini\u002Fgemini-cli","gemini-cli 是一款由谷歌推出的开源 AI 命令行工具，它将强大的 Gemini 大模型能力直接集成到用户的终端环境中。对于习惯在命令行工作的开发者而言，它提供了一条从输入提示词到获取模型响应的最短路径，无需切换窗口即可享受智能辅助。\n\n这款工具主要解决了开发过程中频繁上下文切换的痛点，让用户能在熟悉的终端界面内直接完成代码理解、生成、调试以及自动化运维任务。无论是查询大型代码库、根据草图生成应用，还是执行复杂的 Git 操作，gemini-cli 都能通过自然语言指令高效处理。\n\n它特别适合广大软件工程师、DevOps 人员及技术研究人员使用。其核心亮点包括支持高达 100 万 token 的超长上下文窗口，具备出色的逻辑推理能力；内置 Google 搜索、文件操作及 Shell 命令执行等实用工具；更独特的是，它支持 MCP（模型上下文协议），允许用户灵活扩展自定义集成，连接如图像生成等外部能力。此外，个人谷歌账号即可享受免费的额度支持，且项目基于 Apache 2.0 协议完全开源，是提升终端工作效率的理想助手。",100752,"2026-04-10T01:20:03",[45,13,15,14],{"id":63,"github_repo":64,"name":65,"description_en":66,"description_zh":67,"ai_summary_zh":67,"readme_en":68,"readme_zh":69,"quickstart_zh":70,"use_case_zh":71,"hero_image_url":72,"owner_login":73,"owner_name":74,"owner_avatar_url":75,"owner_bio":76,"owner_company":77,"owner_location":77,"owner_email":77,"owner_twitter":77,"owner_website":78,"owner_url":79,"languages":80,"stars":93,"forks":94,"last_commit_at":95,"license":96,"difficulty_score":32,"env_os":97,"env_gpu":98,"env_ram":98,"env_deps":99,"category_tags":105,"github_topics":106,"view_count":114,"oss_zip_url":77,"oss_zip_packed_at":77,"status":17,"created_at":115,"updated_at":116,"faqs":117,"releases":148},8553,"github\u002Fspec-kit","spec-kit","💫 Toolkit to help you get started with Spec-Driven Development","Spec Kit 是一款专为提升软件开发效率而设计的开源工具包，旨在帮助团队快速落地“规格驱动开发”（Spec-Driven Development）模式。传统开发中，需求文档往往与代码实现脱节，导致沟通成本高且结果不可控；而 Spec Kit 通过将规格说明书转化为可执行的指令，让 AI 直接依据明确的业务场景生成高质量代码，从而减少从零开始的随意编码，确保产出结果的可预测性。\n\n该工具特别适合希望利用 AI 辅助编程的开发者、技术负责人及初创团队。无论是启动全新项目还是在现有工程中引入规范化流程，用户只需通过简单的命令行操作，即可初始化项目并集成主流的 AI 编程助手。其核心技术亮点在于“规格即代码”的理念，支持社区扩展与预设模板，允许用户根据特定技术栈定制开发流程。此外，Spec Kit 强调官方维护的安全性，提供稳定的版本管理，帮助开发者在享受 AI 红利的同时，依然牢牢掌握架构设计的主动权，真正实现从“凭感觉写代码”到“按规格建系统”的转变。","\u003Cdiv align=\"center\">\n \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgithub_spec-kit_readme_7b06b649a35a.webp\" alt=\"Spec Kit Logo\" width=\"200\" height=\"200\"\u002F>\n \u003Ch1>🌱 Spec Kit\u003C\u002Fh1>\n \u003Ch3>\u003Cem>Build high-quality software faster.\u003C\u002Fem>\u003C\u002Fh3>\n\u003C\u002Fdiv>\n\n\u003Cp align=\"center\">\n \u003Cstrong>An open source toolkit that allows you to focus on product scenarios and predictable outcomes instead of vibe coding every piece from scratch.\u003C\u002Fstrong>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Freleases\u002Flatest\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fgithub\u002Fspec-kit\" alt=\"Latest Release\"\u002F>\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fstargazers\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgithub\u002Fspec-kit?style=social\" alt=\"GitHub stars\"\u002F>\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fgithub\u002Fspec-kit\" alt=\"License\"\u002F>\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-GitHub_Pages-blue\" alt=\"Documentation\"\u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\n## Table of Contents\n\n- [🤔 What is Spec-Driven Development?](#-what-is-spec-driven-development)\n- [⚡ Get Started](#-get-started)\n- [📽️ Video Overview](#️-video-overview)\n- [🧩 Community Extensions](#-community-extensions)\n- [🎨 Community Presets](#-community-presets)\n- [🚶 Community Walkthroughs](#-community-walkthroughs)\n- [🛠️ Community Friends](#️-community-friends)\n- [🤖 Supported AI Coding Agent Integrations](#-supported-ai-coding-agent-integrations)\n- [🔧 Specify CLI Reference](#-specify-cli-reference)\n- [🧩 Making Spec Kit Your Own: Extensions & Presets](#-making-spec-kit-your-own-extensions--presets)\n- [📚 Core Philosophy](#-core-philosophy)\n- [🌟 Development Phases](#-development-phases)\n- [🎯 Experimental Goals](#-experimental-goals)\n- [🔧 Prerequisites](#-prerequisites)\n- [📖 Learn More](#-learn-more)\n- [📋 Detailed Process](#-detailed-process)\n- [🔍 Troubleshooting](#-troubleshooting)\n- [💬 Support](#-support)\n- [🙏 Acknowledgements](#-acknowledgements)\n- [📄 License](#-license)\n\n## 🤔 What is Spec-Driven Development?\n\nSpec-Driven Development **flips the script** on traditional software development. For decades, code has been king — specifications were just scaffolding we built and discarded once the \"real work\" of coding began. Spec-Driven Development changes this: **specifications become executable**, directly generating working implementations rather than just guiding them.\n\n## ⚡ Get Started\n\n### 1. Install Specify CLI\n\nChoose your preferred installation method:\n\n> **Important:** The only official, maintained packages for Spec Kit are published from this GitHub repository. Any packages with the same name on PyPI are **not** affiliated with this project and are not maintained by the Spec Kit maintainers. Always install directly from GitHub as shown below.\n\n#### Option 1: Persistent Installation (Recommended)\n\nInstall once and use everywhere. Pin a specific release tag for stability (check [Releases](https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Freleases) for the latest):\n\n```bash\n# Install a specific stable release (recommended — replace vX.Y.Z with the latest tag)\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z\n\n# Or install latest from main (may include unreleased changes)\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git\n```\n\nThen verify the correct version is installed:\n\n```bash\nspecify version\n```\n\nAnd use the tool directly:\n\n```bash\n# Create new project\nspecify init \u003CPROJECT_NAME>\n\n# Or initialize in existing project\nspecify init . --ai copilot\n# or\nspecify init --here --ai copilot\n\n# Check installed tools\nspecify check\n```\n\nTo upgrade Specify, see the [Upgrade Guide](.\u002Fdocs\u002Fupgrade.md) for detailed instructions. Quick upgrade:\n\n```bash\nuv tool install specify-cli --force --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z\n```\n\n#### Option 2: One-time Usage\n\nRun directly without installing:\n\n```bash\n# Create new project (pinned to a stable release — replace vX.Y.Z with the latest tag)\nuvx --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z specify init \u003CPROJECT_NAME>\n\n# Or initialize in existing project\nuvx --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z specify init . --ai copilot\n# or\nuvx --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z specify init --here --ai copilot\n```\n\n**Benefits of persistent installation:**\n\n- Tool stays installed and available in PATH\n- No need to create shell aliases\n- Better tool management with `uv tool list`, `uv tool upgrade`, `uv tool uninstall`\n- Cleaner shell configuration\n\n#### Option 3: Enterprise \u002F Air-Gapped Installation\n\nIf your environment blocks access to PyPI or GitHub, see the [Enterprise \u002F Air-Gapped Installation](.\u002Fdocs\u002Finstallation.md#enterprise--air-gapped-installation) guide for step-by-step instructions on using `pip download` to create portable, OS-specific wheel bundles on a connected machine.\n\n### 2. Establish project principles\n\nLaunch your AI assistant in the project directory. Most agents expose spec-kit as `\u002Fspeckit.*` slash commands; Codex CLI in skills mode uses `$speckit-*` instead.\n\nUse the **`\u002Fspeckit.constitution`** command to create your project's governing principles and development guidelines that will guide all subsequent development.\n\n```bash\n\u002Fspeckit.constitution Create principles focused on code quality, testing standards, user experience consistency, and performance requirements\n```\n\n### 3. Create the spec\n\nUse the **`\u002Fspeckit.specify`** command to describe what you want to build. Focus on the **what** and **why**, not the tech stack.\n\n```bash\n\u002Fspeckit.specify Build an application that can help me organize my photos in separate photo albums. Albums are grouped by date and can be re-organized by dragging and dropping on the main page. Albums are never in other nested albums. Within each album, photos are previewed in a tile-like interface.\n```\n\n### 4. Create a technical implementation plan\n\nUse the **`\u002Fspeckit.plan`** command to provide your tech stack and architecture choices.\n\n```bash\n\u002Fspeckit.plan The application uses Vite with minimal number of libraries. Use vanilla HTML, CSS, and JavaScript as much as possible. Images are not uploaded anywhere and metadata is stored in a local SQLite database.\n```\n\n### 5. Break down into tasks\n\nUse **`\u002Fspeckit.tasks`** to create an actionable task list from your implementation plan.\n\n```bash\n\u002Fspeckit.tasks\n```\n\n### 6. Execute implementation\n\nUse **`\u002Fspeckit.implement`** to execute all tasks and build your feature according to the plan.\n\n```bash\n\u002Fspeckit.implement\n```\n\nFor detailed step-by-step instructions, see our [comprehensive guide](.\u002Fspec-driven.md).\n\n## 📽️ Video Overview\n\nWant to see Spec Kit in action? Watch our [video overview](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=a9eR1xsfvHg&pp=0gcJCckJAYcqIYzv)!\n\n[![Spec Kit video header](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgithub_spec-kit_readme_8e05e17e2af4.jpg)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=a9eR1xsfvHg&pp=0gcJCckJAYcqIYzv)\n\n## 🧩 Community Extensions\n\n> [!NOTE]\n> Community extensions are independently created and maintained by their respective authors. GitHub and the Spec Kit maintainers may review pull requests that add entries to the community catalog for formatting, catalog structure, or policy compliance, but they do **not review, audit, endorse, or support the extension code itself**. The Community Extensions website is also a third-party resource. Review extension source code before installation and use at your own discretion.\n\n🔍 **Browse and search community extensions on the [Community Extensions website](https:\u002F\u002Fspeckit-community.github.io\u002Fextensions\u002F).**\n\nThe following community-contributed extensions are available in [`catalog.community.json`](extensions\u002Fcatalog.community.json):\n\n**Categories:**\n\n- `docs` — reads, validates, or generates spec artifacts\n- `code` — reviews, validates, or modifies source code\n- `process` — orchestrates workflow across phases\n- `integration` — syncs with external platforms\n- `visibility` — reports on project health or progress\n\n**Effect:**\n\n- `Read-only` — produces reports without modifying files\n- `Read+Write` — modifies files, creates artifacts, or updates specs\n\n| Extension | Purpose | Category | Effect | URL |\n|-----------|---------|----------|--------|-----|\n| Agent Assign | Assign specialized Claude Code agents to spec-kit tasks for targeted execution | `process` | Read+Write | [spec-kit-agent-assign](https:\u002F\u002Fgithub.com\u002Fxymelon\u002Fspec-kit-agent-assign) |\n| AI-Driven Engineering (AIDE) | A structured 7-step workflow for building new projects from scratch with AI assistants — from vision through implementation | `process` | Read+Write | [aide](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Faide) |\n| Architect Impact Previewer | Predicts architectural impact, complexity, and risks of proposed changes before implementation. | `visibility` | Read-only | [spec-kit-architect-preview](https:\u002F\u002Fgithub.com\u002FUmmeHabiba1312\u002Fspec-kit-architect-preview) |\n| Archive Extension | Archive merged features into main project memory. | `docs` | Read+Write | [spec-kit-archive](https:\u002F\u002Fgithub.com\u002Fstn1slv\u002Fspec-kit-archive) |\n| Azure DevOps Integration | Sync user stories and tasks to Azure DevOps work items using OAuth authentication | `integration` | Read+Write | [spec-kit-azure-devops](https:\u002F\u002Fgithub.com\u002Fpragya247\u002Fspec-kit-azure-devops) |\n| Branch Convention | Configurable branch and folder naming conventions for \u002Fspecify with presets and custom patterns | `process` | Read+Write | [spec-kit-branch-convention](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-branch-convention) |\n| Brownfield Bootstrap | Bootstrap spec-kit for existing codebases — auto-discover architecture and adopt SDD incrementally | `process` | Read+Write | [spec-kit-brownfield](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-brownfield) |\n| Bugfix Workflow | Structured bugfix workflow — capture bugs, trace to spec artifacts, and patch specs surgically | `process` | Read+Write | [spec-kit-bugfix](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-bugfix) |\n| Canon | Adds canon-driven (baseline-driven) workflows: spec-first, code-first, spec-drift. Requires Canon Core preset installation. | `process` | Read+Write | [spec-kit-canon](https:\u002F\u002Fgithub.com\u002Fmaximiliamus\u002Fspec-kit-canon\u002Ftree\u002Fmaster\u002Fextension) |\n| Catalog CI | Automated validation for spec-kit community catalog entries — structure, URLs, diffs, and linting | `process` | Read-only | [spec-kit-catalog-ci](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-catalog-ci) |\n| CI Guard | Spec compliance gates for CI\u002FCD — verify specs exist, check drift, and block merges on gaps | `process` | Read-only | [spec-kit-ci-guard](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-ci-guard) |\n| Checkpoint Extension | Commit the changes made during the middle of the implementation, so you don't end up with just one very large commit at the end | `code` | Read+Write | [spec-kit-checkpoint](https:\u002F\u002Fgithub.com\u002Faaronrsun\u002Fspec-kit-checkpoint) |\n| Cleanup Extension | Post-implementation quality gate that reviews changes, fixes small issues (scout rule), creates tasks for medium issues, and generates analysis for large issues | `code` | Read+Write | [spec-kit-cleanup](https:\u002F\u002Fgithub.com\u002Fdsrednicki\u002Fspec-kit-cleanup) |\n| Conduct Extension | Orchestrates spec-kit phases via sub-agent delegation to reduce context pollution. | `process` | Read+Write | [spec-kit-conduct-ext](https:\u002F\u002Fgithub.com\u002Ftwbrandon7\u002Fspec-kit-conduct-ext) |\n| Confluence Extension | Create a doc in Confluence summarizing the specifications and planning files | `integration` | Read+Write | [spec-kit-confluence](https:\u002F\u002Fgithub.com\u002Faaronrsun\u002Fspec-kit-confluence) |\n| DocGuard — CDD Enforcement | Canonical-Driven Development enforcement. Validates, scores, and traces project documentation with automated checks, AI-driven workflows, and spec-kit hooks. Zero NPM runtime dependencies. | `docs` | Read+Write | [spec-kit-docguard](https:\u002F\u002Fgithub.com\u002Fraccioly\u002Fdocguard) |\n| Extensify | Create and validate extensions and extension catalogs | `process` | Read+Write | [extensify](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Fextensify) |\n| Fix Findings | Automated analyze-fix-reanalyze loop that resolves spec findings until clean | `code` | Read+Write | [spec-kit-fix-findings](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-fix-findings) |\n| FixIt Extension | Spec-aware bug fixing — maps bugs to spec artifacts, proposes a plan, applies minimal changes | `code` | Read+Write | [spec-kit-fixit](https:\u002F\u002Fgithub.com\u002Fspeckit-community\u002Fspec-kit-fixit) |\n| Fleet Orchestrator | Orchestrate a full feature lifecycle with human-in-the-loop gates across all SpecKit phases | `process` | Read+Write | [spec-kit-fleet](https:\u002F\u002Fgithub.com\u002Fsharathsatish\u002Fspec-kit-fleet) |\n| GitHub Issues Integration 1 | Generate spec artifacts from GitHub Issues - import issues, sync updates, and maintain bidirectional traceability | `integration` | Read+Write | [spec-kit-github-issues](https:\u002F\u002Fgithub.com\u002FFatima367\u002Fspec-kit-github-issues) |\n| GitHub Issues Integration 2 | Creates and syncs local specs from an existing GitHub issue | `integration` | Read+Write | [spec-kit-issue](https:\u002F\u002Fgithub.com\u002Faaronrsun\u002Fspec-kit-issue) |\n| Iterate | Iterate on spec documents with a two-phase define-and-apply workflow — refine specs mid-implementation and go straight back to building | `docs` | Read+Write | [spec-kit-iterate](https:\u002F\u002Fgithub.com\u002Fimviancagrace\u002Fspec-kit-iterate) |\n| Jira Integration | Create Jira Epics, Stories, and Issues from spec-kit specifications and task breakdowns with configurable hierarchy and custom field support | `integration` | Read+Write | [spec-kit-jira](https:\u002F\u002Fgithub.com\u002Fmbachorik\u002Fspec-kit-jira) |\n| Learning Extension | Generate educational guides from implementations and enhance clarifications with mentoring context | `docs` | Read+Write | [spec-kit-learn](https:\u002F\u002Fgithub.com\u002Fimviancagrace\u002Fspec-kit-learn) |\n| MAQA — Multi-Agent & Quality Assurance | Coordinator → feature → QA agent workflow with parallel worktree-based implementation. Language-agnostic. Auto-detects installed board plugins. Optional CI gate. | `process` | Read+Write | [spec-kit-maqa-ext](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-ext) |\n| MAQA Azure DevOps Integration | Azure DevOps Boards integration for MAQA — syncs User Stories and Task children as features progress | `integration` | Read+Write | [spec-kit-maqa-azure-devops](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-azure-devops) |\n| MAQA CI\u002FCD Gate | Auto-detects GitHub Actions, CircleCI, GitLab CI, and Bitbucket Pipelines. Blocks QA handoff until pipeline is green. | `process` | Read+Write | [spec-kit-maqa-ci](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-ci) |\n| MAQA GitHub Projects Integration | GitHub Projects v2 integration for MAQA — syncs draft issues and Status columns as features progress | `integration` | Read+Write | [spec-kit-maqa-github-projects](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-github-projects) |\n| MAQA Jira Integration | Jira integration for MAQA — syncs Stories and Subtasks as features progress through the board | `integration` | Read+Write | [spec-kit-maqa-jira](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-jira) |\n| MAQA Linear Integration | Linear integration for MAQA — syncs issues and sub-issues across workflow states as features progress | `integration` | Read+Write | [spec-kit-maqa-linear](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-linear) |\n| MAQA Trello Integration | Trello board integration for MAQA — populates board from specs, moves cards, real-time checklist ticking | `integration` | Read+Write | [spec-kit-maqa-trello](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-trello) |\n| MemoryLint | Agent memory governance tool: Automatically audits and fixes boundary conflicts between AGENTS.md and the constitution. | `process` | Read+Write | [memorylint](https:\u002F\u002Fgithub.com\u002FRbBtSn0w\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Fmemorylint) |\n| Onboard | Contextual onboarding and progressive growth for developers new to spec-kit projects. Explains specs, maps dependencies, validates understanding, and guides the next step | `process` | Read+Write | [spec-kit-onboard](https:\u002F\u002Fgithub.com\u002Fdmux\u002Fspec-kit-onboard) |\n| Optimize | Audit and optimize AI governance for context efficiency — token budgets, rule health, interpretability, compression, coherence, and echo detection | `process` | Read+Write | [spec-kit-optimize](https:\u002F\u002Fgithub.com\u002FsakitA\u002Fspec-kit-optimize) |\n| Plan Review Gate | Require spec.md and plan.md to be merged via MR\u002FPR before allowing task generation | `process` | Read-only | [spec-kit-plan-review-gate](https:\u002F\u002Fgithub.com\u002Fluno\u002Fspec-kit-plan-review-gate) |\n| PR Bridge | Auto-generate pull request descriptions, checklists, and summaries from spec artifacts | `process` | Read-only | [spec-kit-pr-bridge-](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-pr-bridge-) |\n| Presetify | Create and validate presets and preset catalogs | `process` | Read+Write | [presetify](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Fpresetify) |\n| Product Forge | Full product lifecycle: research → product spec → SpecKit → implement → verify → test | `process` | Read+Write | [speckit-product-forge](https:\u002F\u002Fgithub.com\u002FVaiYav\u002Fspeckit-product-forge) |\n| Project Health Check | Diagnose a Spec Kit project and report health issues across structure, agents, features, scripts, extensions, and git | `visibility` | Read-only | [spec-kit-doctor](https:\u002F\u002Fgithub.com\u002FKhawarHabibKhan\u002Fspec-kit-doctor) |\n| Project Status | Show current SDD workflow progress — active feature, artifact status, task completion, workflow phase, and extensions summary | `visibility` | Read-only | [spec-kit-status](https:\u002F\u002Fgithub.com\u002FKhawarHabibKhan\u002Fspec-kit-status) |\n| QA Testing Extension | Systematic QA testing with browser-driven or CLI-based validation of acceptance criteria from spec | `code` | Read-only | [spec-kit-qa](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-qa) |\n| Ralph Loop | Autonomous implementation loop using AI agent CLI | `code` | Read+Write | [spec-kit-ralph](https:\u002F\u002Fgithub.com\u002FRubiss\u002Fspec-kit-ralph) |\n| Reconcile Extension | Reconcile implementation drift by surgically updating feature artifacts. | `docs` | Read+Write | [spec-kit-reconcile](https:\u002F\u002Fgithub.com\u002Fstn1slv\u002Fspec-kit-reconcile) |\n| Repository Index | Generate index for existing repo for overview, architecture and module level. | `docs` | Read-only | [spec-kit-repoindex](https:\u002F\u002Fgithub.com\u002Fliuyiyu\u002Fspec-kit-repoindex) |\n| Retro Extension | Sprint retrospective analysis with metrics, spec accuracy assessment, and improvement suggestions | `process` | Read+Write | [spec-kit-retro](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-retro) |\n| Retrospective Extension | Post-implementation retrospective with spec adherence scoring, drift analysis, and human-gated spec updates | `docs` | Read+Write | [spec-kit-retrospective](https:\u002F\u002Fgithub.com\u002Femi-dm\u002Fspec-kit-retrospective) |\n| Review Extension | Post-implementation comprehensive code review with specialized agents for code quality, comments, tests, error handling, type design, and simplification | `code` | Read-only | [spec-kit-review](https:\u002F\u002Fgithub.com\u002FismaelJimenez\u002Fspec-kit-review) |\n| SDD Utilities | Resume interrupted workflows, validate project health, and verify spec-to-task traceability | `process` | Read+Write | [speckit-utils](https:\u002F\u002Fgithub.com\u002Fmvanhorn\u002Fspeckit-utils) |\n| Security Review | Comprehensive security audit of codebases using AI-powered DevSecOps analysis | `code` | Read-only | [spec-kit-security-review](https:\u002F\u002Fgithub.com\u002FDyanGalih\u002Fspec-kit-security-review) |\n| SFSpeckit | Enterprise Salesforce SDLC with 18 commands for the full SDD lifecycle. | `process` | Read+Write | [spec-kit-sf](https:\u002F\u002Fgithub.com\u002Fysumanth06\u002Fspec-kit-sf) |\n| Ship Release Extension | Automates release pipeline: pre-flight checks, branch sync, changelog generation, CI verification, and PR creation | `process` | Read+Write | [spec-kit-ship](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-ship) |\n| Spec Critique Extension | Dual-lens critical review of spec and plan from product strategy and engineering risk perspectives | `docs` | Read-only | [spec-kit-critique](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-critique) |\n| Spec Diagram | Auto-generate Mermaid diagrams of SDD workflow state, feature progress, and task dependencies | `visibility` | Read-only | [spec-kit-diagram-](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-diagram-) |\n| Spec Refine | Update specs in-place, propagate changes to plan and tasks, and diff impact across artifacts | `process` | Read+Write | [spec-kit-refine](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-refine) |\n| Spec Sync | Detect and resolve drift between specs and implementation. AI-assisted resolution with human approval | `docs` | Read+Write | [spec-kit-sync](https:\u002F\u002Fgithub.com\u002Fbgervin\u002Fspec-kit-sync) |\n| SpecTest | Auto-generate test scaffolds from spec criteria, map coverage, and find untested requirements | `code` | Read+Write | [spec-kit-spectest](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-spectest) |\n| Staff Review Extension | Staff-engineer-level code review that validates implementation against spec, checks security, performance, and test coverage | `code` | Read-only | [spec-kit-staff-review](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-staff-review) |\n| Status Report | Project status, feature progress, and next-action recommendations for spec-driven workflows | `visibility` | Read-only | [Open-Agent-Tools\u002Fspec-kit-status](https:\u002F\u002Fgithub.com\u002FOpen-Agent-Tools\u002Fspec-kit-status) |\n| Superpowers Bridge | Orchestrates obra\u002Fsuperpowers skills within the spec-kit SDD workflow across the full lifecycle (clarification, TDD, review, verification, critique, debugging, branch completion) | `process` | Read+Write | [superpowers-bridge](https:\u002F\u002Fgithub.com\u002FRbBtSn0w\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Fsuperpowers-bridge) |\n| TinySpec | Lightweight single-file workflow for small tasks — skip the heavy multi-step SDD process | `process` | Read+Write | [spec-kit-tinyspec](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-tinyspec) |\n| V-Model Extension Pack | Enforces V-Model paired generation of development specs and test specs with full traceability | `docs` | Read+Write | [spec-kit-v-model](https:\u002F\u002Fgithub.com\u002Fleocamello\u002Fspec-kit-v-model) |\n| Verify Extension | Post-implementation quality gate that validates implemented code against specification artifacts | `code` | Read-only | [spec-kit-verify](https:\u002F\u002Fgithub.com\u002FismaelJimenez\u002Fspec-kit-verify) |\n| Verify Tasks Extension | Detect phantom completions: tasks marked [X] in tasks.md with no real implementation | `code` | Read-only | [spec-kit-verify-tasks](https:\u002F\u002Fgithub.com\u002Fdatastone-inc\u002Fspec-kit-verify-tasks) |\n| What-if Analysis | Preview the downstream impact (complexity, effort, tasks, risks) of requirement changes before committing to them | `visibility` | Read-only | [spec-kit-whatif](https:\u002F\u002Fgithub.com\u002FDevAbdullah90\u002Fspec-kit-whatif) |\n| Worktree Isolation | Spawn isolated git worktrees for parallel feature development without checkout switching | `process` | Read+Write | [spec-kit-worktree](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-worktree) |\n| Worktrees | Default-on worktree isolation for parallel agents — sibling or nested layout | `process` | Read+Write | [spec-kit-worktree-parallel](https:\u002F\u002Fgithub.com\u002Fdango85\u002Fspec-kit-worktree-parallel) |\n\nTo submit your own extension, see the [Extension Publishing Guide](extensions\u002FEXTENSION-PUBLISHING-GUIDE.md).\n\n## 🎨 Community Presets\n\n> [!NOTE]\n> Community presets are independently created and maintained by their respective authors. GitHub and the Spec Kit maintainers may review pull requests that add entries to the community catalog for formatting, catalog structure, or policy compliance, but they do **not review, audit, endorse, or support the preset code itself**. Review preset source code before installation and use at your own discretion.\n\nThe following community-contributed presets customize how Spec Kit behaves — overriding templates, commands, and terminology without changing any tooling. Presets are available in [`catalog.community.json`](presets\u002Fcatalog.community.json):\n\n| Preset | Purpose | Provides | Requires | URL |\n|--------|---------|----------|----------|-----|\n| AIDE In-Place Migration | Adapts the AIDE extension workflow for in-place technology migrations (X → Y pattern) — adds migration objectives, verification gates, knowledge documents, and behavioral equivalence criteria | 2 templates, 8 commands | AIDE extension | [spec-kit-presets](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-presets) |\n| Canon Core | Adapts original Spec Kit workflow to work together with Canon extension | 2 templates, 8 commands | — | [spec-kit-canon](https:\u002F\u002Fgithub.com\u002Fmaximiliamus\u002Fspec-kit-canon) |\n| Explicit Task Dependencies | Adds explicit `(depends on T###)` dependency declarations and an Execution Wave DAG to tasks.md for parallel scheduling | 1 template, 1 command | — | [spec-kit-preset-explicit-task-dependencies](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-preset-explicit-task-dependencies) |\n| Fiction Book Writing | It adapts the Spec-Driven Development workflow for storytelling: features become story elements, specs become story briefs, plans become story structures, and tasks become scene-by-scene writing tasks. Supports single and multi-POV, all major plot structure frameworks, and two style modes, author voice sample or humanized AI prose. | 21 templates, 17 commands | — | [spec-kit-preset-fiction-book-writing](https:\u002F\u002Fgithub.com\u002Fadaumann\u002Fspeckit-preset-fiction-book-writing) |\n| Multi-Repo Branching | Coordinates feature branch creation across multiple git repositories (independent repos and submodules) during plan and tasks phases | 2 commands | — | [spec-kit-preset-multi-repo-branching](https:\u002F\u002Fgithub.com\u002FsakitA\u002Fspec-kit-preset-multi-repo-branching) |\n| Pirate Speak (Full) | Transforms all Spec Kit output into pirate speak — specs become \"Voyage Manifests\", plans become \"Battle Plans\", tasks become \"Crew Assignments\" | 6 templates, 9 commands | — | [spec-kit-presets](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-presets) |\n| Table of Contents Navigation | Adds a navigable Table of Contents to generated spec.md, plan.md, and tasks.md documents | 3 templates, 3 commands | — | [spec-kit-preset-toc-navigation](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-preset-toc-navigation) |\n| VS Code Ask Questions | Enhances the clarify command to use `vscode\u002FaskQuestions` for batched interactive questioning. | 1 command | — | [spec-kit-presets](https:\u002F\u002Fgithub.com\u002Ffdcastel\u002Fspec-kit-presets) |\n\nTo build and publish your own preset, see the [Presets Publishing Guide](presets\u002FPUBLISHING.md).\n\n## 🚶 Community Walkthroughs\n\n> [!NOTE]\n> Community walkthroughs are independently created and maintained by their respective authors. They are **not reviewed, nor endorsed, nor supported by GitHub**. Review their content before following along and use at your own discretion.\n\nSee Spec-Driven Development in action across different scenarios with these community-contributed walkthroughs:\n\n- **[Greenfield .NET CLI tool](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-dotnet-cli-demo)** — Builds a Timezone Utility as a .NET single-binary CLI tool from a blank directory, covering the full spec-kit workflow: constitution, specify, plan, tasks, and multi-pass implement using GitHub Copilot agents.\n\n- **[Greenfield Spring Boot + React platform](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-spring-react-demo)** — Builds an LLM performance analytics platform (REST API, graphs, iteration tracking) from scratch using Spring Boot, embedded React, PostgreSQL, and Docker Compose, with a clarify step and a cross-artifact consistency analysis pass included.\n\n- **[Brownfield ASP.NET CMS extension](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-aspnet-brownfield-demo)** — Extends an existing open-source .NET CMS (CarrotCakeCMS-Core, ~307,000 lines of C#, Razor, SQL, JavaScript, and config files) with two new features — cross-platform Docker Compose infrastructure and a token-authenticated headless REST API — demonstrating how spec-kit fits into existing codebases without prior specs or a constitution.\n\n- **[Brownfield Java runtime extension](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-java-brownfield-demo)** — Extends an existing open-source Jakarta EE runtime (Piranha, ~420,000 lines of Java, XML, JSP, HTML, and config files across 180 Maven modules) with a password-protected Server Admin Console, demonstrating spec-kit on a large multi-module Java project with no prior specs or constitution.\n\n- **[Brownfield Go \u002F React dashboard demo](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-go-brownfield-demo)** — Demonstrates spec-kit driven entirely from the **terminal using GitHub Copilot CLI**. Extends NASA's open-source Hermes ground support system (Go) with a lightweight React-based web telemetry dashboard, showing that the full constitution → specify → plan → tasks → implement workflow works from the terminal.\n\n- **[Greenfield Spring Boot MVC with a custom preset](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-pirate-speak-preset-demo)** — Builds a Spring Boot MVC application from scratch using a custom pirate-speak preset, demonstrating how presets can reshape the entire spec-kit experience: specifications become \"Voyage Manifests,\" plans become \"Battle Plans,\" and tasks become \"Crew Assignments\" — all generated in full pirate vernacular without changing any tooling.\n\n- **[Greenfield Spring Boot + React with a custom extension](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-aide-extension-demo)** — Walks through the **AIDE extension**, a community extension that adds an alternative spec-driven workflow to spec-kit with high-level specs (vision) and low-level specs (work items) organized in a 7-step iterative lifecycle: vision → roadmap → progress tracking → work queue → work items → execution → feedback loops. Uses a family trading platform (Spring Boot 4, React 19, PostgreSQL, Docker Compose) as the scenario to illustrate how the extension mechanism lets you plug in a different style of spec-driven development without changing any core tooling — truly utilizing the \"Kit\" in Spec Kit.\n\n## 🛠️ Community Friends\n\n> [!NOTE]\n> Community projects listed here are independently created and maintained by their respective authors. They are **not reviewed, nor endorsed, nor supported by GitHub**. Review their source code before installation and use at your own discretion.\n\nCommunity projects that extend, visualize, or build on Spec Kit:\n\n- **[cc-spex](https:\u002F\u002Fgithub.com\u002Frhuss\u002Fcc-spex)** - A Claude Code plugin that adds composable traits on top of Spec Kit with [Superpowers](https:\u002F\u002Fgithub.com\u002Fobra\u002Fsuperpowers)-based quality gates, spec\u002Fcode review, git worktree isolation, and parallel implementation via agent teams.\n\n- **[Spec Kit Assistant](https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=rfsales.speckit-assistant)** — A VS Code extension that provides a visual orchestrator for the full SDD workflow (constitution → specification → planning → tasks → implementation) with phase status visualization, an interactive task checklist, DAG visualization, and support for Claude, Gemini, GitHub Copilot, and OpenAI backends. Requires the `specify` CLI in your PATH.\n\n- **[SpecKit Companion](https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=alfredoperez.speckit-companion)** — A VS Code extension that brings a visual GUI to Spec Kit. Browse specs in a rich markdown viewer with clickable file references, create specifications with image attachments, comment and refine each step inline (GitHub-style review), track your progress through the SDD workflow with a visual phase stepper, and manage steering documents like constitutions and templates.\n\n## 🤖 Supported AI Coding Agent Integrations\n\nSpec Kit works with 30+ AI coding agents — both CLI tools and IDE-based assistants. See the full list with notes and usage details in the [Supported AI Coding Agent Integrations](https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002Freference\u002Fintegrations.html) guide.\n\nRun `specify integration list` to see all available integrations in your installed version.\n\n## Available Slash Commands\n\nAfter running `specify init`, your AI coding agent will have access to these slash commands for structured development. If you pass `--ai \u003Cagent> --ai-skills`, Spec Kit installs agent skills instead of slash-command prompt files; `--ai-skills` requires `--ai`.\n\n#### Core Commands\n\nEssential commands for the Spec-Driven Development workflow:\n\n| Command | Agent Skill | Description |\n| ------------------------ | ---------------------- | -------------------------------------------------------------------------- |\n| `\u002Fspeckit.constitution` | `speckit-constitution` | Create or update project governing principles and development guidelines |\n| `\u002Fspeckit.specify` | `speckit-specify` | Define what you want to build (requirements and user stories) |\n| `\u002Fspeckit.plan` | `speckit-plan` | Create technical implementation plans with your chosen tech stack |\n| `\u002Fspeckit.tasks` | `speckit-tasks` | Generate actionable task lists for implementation |\n| `\u002Fspeckit.taskstoissues` | `speckit-taskstoissues`| Convert generated task lists into GitHub issues for tracking and execution |\n| `\u002Fspeckit.implement` | `speckit-implement` | Execute all tasks to build the feature according to the plan |\n\n#### Optional Commands\n\nAdditional commands for enhanced quality and validation:\n\n| Command | Agent Skill | Description |\n| -------------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------ |\n| `\u002Fspeckit.clarify` | `speckit-clarify` | Clarify underspecified areas (recommended before `\u002Fspeckit.plan`; formerly `\u002Fquizme`) |\n| `\u002Fspeckit.analyze` | `speckit-analyze` | Cross-artifact consistency & coverage analysis (run after `\u002Fspeckit.tasks`, before `\u002Fspeckit.implement`) |\n| `\u002Fspeckit.checklist` | `speckit-checklist` | Generate custom quality checklists that validate requirements completeness, clarity, and consistency (like \"unit tests for English\") |\n\n## 🔧 Specify CLI Reference\n\nFor full command details, options, and examples, see the [CLI Reference](https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002Freference\u002Foverview.html).\n\n## 🧩 Making Spec Kit Your Own: Extensions & Presets\n\nSpec Kit can be tailored to your needs through two complementary systems — **extensions** and **presets** — plus project-local overrides for one-off adjustments:\n\n| Priority | Component Type | Location |\n| -------: | ------------------------------------------------- | -------------------------------- |\n| ⬆ 1 | Project-Local Overrides | `.specify\u002Ftemplates\u002Foverrides\u002F` |\n| 2 | Presets — Customize core & extensions | `.specify\u002Fpresets\u002Ftemplates\u002F` |\n| 3 | Extensions — Add new capabilities | `.specify\u002Fextensions\u002Ftemplates\u002F` |\n| ⬇ 4 | Spec Kit Core — Built-in SDD commands & templates | `.specify\u002Ftemplates\u002F` |\n\n- **Templates** are resolved at **runtime** — Spec Kit walks the stack top-down and uses the first match.\n- Project-local overrides (`.specify\u002Ftemplates\u002Foverrides\u002F`) let you make one-off adjustments for a single project without creating a full preset.\n- **Extension\u002Fpreset commands** are applied at **install time** — when you run `specify extension add` or `specify preset add`, command files are written into agent directories (e.g., `.claude\u002Fcommands\u002F`).\n- If multiple presets or extensions provide the same command, the highest-priority version wins. On removal, the next-highest-priority version is restored automatically.\n- If no overrides or customizations exist, Spec Kit uses its core defaults.\n\n### Extensions — Add New Capabilities\n\nUse **extensions** when you need functionality that goes beyond Spec Kit's core. Extensions introduce new commands and templates — for example, adding domain-specific workflows that are not covered by the built-in SDD commands, integrating with external tools, or adding entirely new development phases. They expand *what Spec Kit can do*.\n\n```bash\n# Search available extensions\nspecify extension search\n\n# Install an extension\nspecify extension add \u003Cextension-name>\n```\n\nFor example, extensions could add Jira integration, post-implementation code review, V-Model test traceability, or project health diagnostics.\n\nSee the [Extensions reference](https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002Freference\u002Fextensions.html) for the full command guide. Browse the [community extensions](#-community-extensions) above for what's available.\n\n### Presets — Customize Existing Workflows\n\nUse **presets** when you want to change *how* Spec Kit works without adding new capabilities. Presets override the templates and commands that ship with the core *and* with installed extensions — for example, enforcing a compliance-oriented spec format, using domain-specific terminology, or applying organizational standards to plans and tasks. They customize the artifacts and instructions that Spec Kit and its extensions produce.\n\n```bash\n# Search available presets\nspecify preset search\n\n# Install a preset\nspecify preset add \u003Cpreset-name>\n```\n\nFor example, presets could restructure spec templates to require regulatory traceability, adapt the workflow to fit the methodology you use (e.g., Agile, Kanban, Waterfall, jobs-to-be-done, or domain-driven design), add mandatory security review gates to plans, enforce test-first task ordering, or localize the entire workflow to a different language. The [pirate-speak demo](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-pirate-speak-preset-demo) shows just how deep the customization can go. Multiple presets can be stacked with priority ordering.\n\nSee the [Presets reference](https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002Freference\u002Fpresets.html) for the full command guide, including resolution order and priority stacking.\n\n### When to Use Which\n\n| Goal | Use |\n| --- | --- |\n| Add a brand-new command or workflow | Extension |\n| Customize the format of specs, plans, or tasks | Preset |\n| Integrate an external tool or service | Extension |\n| Enforce organizational or regulatory standards | Preset |\n| Ship reusable domain-specific templates | Either — presets for template overrides, extensions for templates bundled with new commands |\n\n## 📚 Core Philosophy\n\nSpec-Driven Development is a structured process that emphasizes:\n\n- **Intent-driven development** where specifications define the \"*what*\" before the \"*how*\"\n- **Rich specification creation** using guardrails and organizational principles\n- **Multi-step refinement** rather than one-shot code generation from prompts\n- **Heavy reliance** on advanced AI model capabilities for specification interpretation\n\n## 🌟 Development Phases\n\n| Phase | Focus | Key Activities |\n| ---------------------------------------- | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| **0-to-1 Development** (\"Greenfield\") | Generate from scratch | \u003Cul>\u003Cli>Start with high-level requirements\u003C\u002Fli>\u003Cli>Generate specifications\u003C\u002Fli>\u003Cli>Plan implementation steps\u003C\u002Fli>\u003Cli>Build production-ready applications\u003C\u002Fli>\u003C\u002Ful> |\n| **Creative Exploration** | Parallel implementations | \u003Cul>\u003Cli>Explore diverse solutions\u003C\u002Fli>\u003Cli>Support multiple technology stacks & architectures\u003C\u002Fli>\u003Cli>Experiment with UX patterns\u003C\u002Fli>\u003C\u002Ful> |\n| **Iterative Enhancement** (\"Brownfield\") | Brownfield modernization | \u003Cul>\u003Cli>Add features iteratively\u003C\u002Fli>\u003Cli>Modernize legacy systems\u003C\u002Fli>\u003Cli>Adapt processes\u003C\u002Fli>\u003C\u002Ful> |\n\n## 🎯 Experimental Goals\n\nOur research and experimentation focus on:\n\n### Technology independence\n\n- Create applications using diverse technology stacks\n- Validate the hypothesis that Spec-Driven Development is a process not tied to specific technologies, programming languages, or frameworks\n\n### Enterprise constraints\n\n- Demonstrate mission-critical application development\n- Incorporate organizational constraints (cloud providers, tech stacks, engineering practices)\n- Support enterprise design systems and compliance requirements\n\n### User-centric development\n\n- Build applications for different user cohorts and preferences\n- Support various development approaches (from vibe-coding to AI-native development)\n\n### Creative & iterative processes\n\n- Validate the concept of parallel implementation exploration\n- Provide robust iterative feature development workflows\n- Extend processes to handle upgrades and modernization tasks\n\n## 🔧 Prerequisites\n\n- **Linux\u002FmacOS\u002FWindows**\n- [Supported](#-supported-ai-coding-agent-integrations) AI coding agent.\n- [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F) for package management\n- [Python 3.11+](https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)\n- [Git](https:\u002F\u002Fgit-scm.com\u002Fdownloads)\n\nIf you encounter issues with an agent, please open an issue so we can refine the integration.\n\n## 📖 Learn More\n\n- **[Complete Spec-Driven Development Methodology](.\u002Fspec-driven.md)** - Deep dive into the full process\n- **[Detailed Walkthrough](#-detailed-process)** - Step-by-step implementation guide\n\n---\n\n## 📋 Detailed Process\n\n\u003Cdetails>\n\u003Csummary>Click to expand the detailed step-by-step walkthrough\u003C\u002Fsummary>\n\nYou can use the Specify CLI to bootstrap your project, which will bring in the required artifacts in your environment. Run:\n\n```bash\nspecify init \u003Cproject_name>\n```\n\nOr initialize in the current directory:\n\n```bash\nspecify init .\n# or use the --here flag\nspecify init --here\n# Skip confirmation when the directory already has files\nspecify init . --force\n# or\nspecify init --here --force\n```\n\n![Specify CLI bootstrapping a new project in the terminal](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgithub_spec-kit_readme_6f451003b826.gif)\n\nYou will be prompted to select the AI agent you are using. You can also proactively specify it directly in the terminal:\n\n```bash\nspecify init \u003Cproject_name> --ai copilot\nspecify init \u003Cproject_name> --ai gemini\nspecify init \u003Cproject_name> --ai copilot\n\n# Or in current directory:\nspecify init . --ai copilot\nspecify init . --ai codex --ai-skills\n\n# or use --here flag\nspecify init --here --ai copilot\nspecify init --here --ai codex --ai-skills\n\n# Force merge into a non-empty current directory\nspecify init . --force --ai copilot\n\n# or\nspecify init --here --force --ai copilot\n```\n\nThe CLI will check if you have Claude Code, Gemini CLI, Cursor CLI, Qwen CLI, opencode, Codex CLI, Qoder CLI, Tabnine CLI, Kiro CLI, Pi, Forge, Goose, or Mistral Vibe installed. If you do not, or you prefer to get the templates without checking for the right tools, use `--ignore-agent-tools` with your command:\n\n```bash\nspecify init \u003Cproject_name> --ai copilot --ignore-agent-tools\n```\n\n### **STEP 1:** Establish project principles\n\nGo to the project folder and run your AI agent. In our example, we're using `claude`.\n\n![Bootstrapping Claude Code environment](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgithub_spec-kit_readme_be9bceb0148f.gif)\n\nYou will know that things are configured correctly if you see the `\u002Fspeckit.constitution`, `\u002Fspeckit.specify`, `\u002Fspeckit.plan`, `\u002Fspeckit.tasks`, and `\u002Fspeckit.implement` commands available.\n\nThe first step should be establishing your project's governing principles using the `\u002Fspeckit.constitution` command. This helps ensure consistent decision-making throughout all subsequent development phases:\n\n```text\n\u002Fspeckit.constitution Create principles focused on code quality, testing standards, user experience consistency, and performance requirements. Include governance for how these principles should guide technical decisions and implementation choices.\n```\n\nThis step creates or updates the `.specify\u002Fmemory\u002Fconstitution.md` file with your project's foundational guidelines that the AI agent will reference during specification, planning, and implementation phases.\n\n### **STEP 2:** Create project specifications\n\nWith your project principles established, you can now create the functional specifications. Use the `\u002Fspeckit.specify` command and then provide the concrete requirements for the project you want to develop.\n\n> [!IMPORTANT]\n> Be as explicit as possible about *what* you are trying to build and *why*. **Do not focus on the tech stack at this point**.\n\nAn example prompt:\n\n```text\nDevelop Taskify, a team productivity platform. It should allow users to create projects, add team members,\nassign tasks, comment and move tasks between boards in Kanban style. In this initial phase for this feature,\nlet's call it \"Create Taskify,\" let's have multiple users but the users will be declared ahead of time, predefined.\nI want five users in two different categories, one product manager and four engineers. Let's create three\ndifferent sample projects. Let's have the standard Kanban columns for the status of each task, such as \"To Do,\"\n\"In Progress,\" \"In Review,\" and \"Done.\" There will be no login for this application as this is just the very\nfirst testing thing to ensure that our basic features are set up. For each task in the UI for a task card,\nyou should be able to change the current status of the task between the different columns in the Kanban work board.\nYou should be able to leave an unlimited number of comments for a particular card. You should be able to, from that task\ncard, assign one of the valid users. When you first launch Taskify, it's going to give you a list of the five users to pick\nfrom. There will be no password required. When you click on a user, you go into the main view, which displays the list of\nprojects. When you click on a project, you open the Kanban board for that project. You're going to see the columns.\nYou'll be able to drag and drop cards back and forth between different columns. You will see any cards that are\nassigned to you, the currently logged in user, in a different color from all the other ones, so you can quickly\nsee yours. You can edit any comments that you make, but you can't edit comments that other people made. You can\ndelete any comments that you made, but you can't delete comments anybody else made.\n```\n\nAfter this prompt is entered, you should see Claude Code kick off the planning and spec drafting process. Claude Code will also trigger some of the built-in scripts to set up the repository.\n\nOnce this step is completed, you should have a new branch created (e.g., `001-create-taskify`), as well as a new specification in the `specs\u002F001-create-taskify` directory.\n\nThe produced specification should contain a set of user stories and functional requirements, as defined in the template.\n\nAt this stage, your project folder contents should resemble the following:\n\n```text\n└── .specify\n ├── memory\n │ └── constitution.md\n ├── scripts\n │ ├── check-prerequisites.sh\n │ ├── common.sh\n │ ├── create-new-feature.sh\n │ ├── setup-plan.sh\n │ └── update-claude-md.sh\n ├── specs\n │ └── 001-create-taskify\n │ └── spec.md\n └── templates\n ├── plan-template.md\n ├── spec-template.md\n └── tasks-template.md\n```\n\n### **STEP 3:** Functional specification clarification (required before planning)\n\nWith the baseline specification created, you can go ahead and clarify any of the requirements that were not captured properly within the first shot attempt.\n\nYou should run the structured clarification workflow **before** creating a technical plan to reduce rework downstream.\n\nPreferred order:\n\n1. Use `\u002Fspeckit.clarify` (structured) – sequential, coverage-based questioning that records answers in a Clarifications section.\n2. Optionally follow up with ad-hoc free-form refinement if something still feels vague.\n\nIf you intentionally want to skip clarification (e.g., spike or exploratory prototype), explicitly state that so the agent doesn't block on missing clarifications.\n\nExample free-form refinement prompt (after `\u002Fspeckit.clarify` if still needed):\n\n```text\nFor each sample project or project that you create there should be a variable number of tasks between 5 and 15\ntasks for each one randomly distributed into different states of completion. Make sure that there's at least\none task in each stage of completion.\n```\n\nYou should also ask Claude Code to validate the **Review & Acceptance Checklist**, checking off the things that are validated\u002Fpass the requirements, and leave the ones that are not unchecked. The following prompt can be used:\n\n```text\nRead the review and acceptance checklist, and check off each item in the checklist if the feature spec meets the criteria. Leave it empty if it does not.\n```\n\nIt's important to use the interaction with Claude Code as an opportunity to clarify and ask questions around the specification - **do not treat its first attempt as final**.\n\n### **STEP 4:** Generate a plan\n\nYou can now be specific about the tech stack and other technical requirements. You can use the `\u002Fspeckit.plan` command that is built into the project template with a prompt like this:\n\n```text\nWe are going to generate this using .NET Aspire, using Postgres as the database. The frontend should use\nBlazor server with drag-and-drop task boards, real-time updates. There should be a REST API created with a projects API,\ntasks API, and a notifications API.\n```\n\nThe output of this step will include a number of implementation detail documents, with your directory tree resembling this:\n\n```text\n.\n├── CLAUDE.md\n├── memory\n│ └── constitution.md\n├── scripts\n│ ├── check-prerequisites.sh\n│ ├── common.sh\n│ ├── create-new-feature.sh\n│ ├── setup-plan.sh\n│ └── update-claude-md.sh\n├── specs\n│ └── 001-create-taskify\n│ ├── contracts\n│ │ ├── api-spec.json\n│ │ └── signalr-spec.md\n│ ├── data-model.md\n│ ├── plan.md\n│ ├── quickstart.md\n│ ├── research.md\n│ └── spec.md\n└── templates\n ├── CLAUDE-template.md\n ├── plan-template.md\n ├── spec-template.md\n └── tasks-template.md\n```\n\nCheck the `research.md` document to ensure that the right tech stack is used, based on your instructions. You can ask Claude Code to refine it if any of the components stand out, or even have it check the locally-installed version of the platform\u002Fframework you want to use (e.g., .NET).\n\nAdditionally, you might want to ask Claude Code to research details about the chosen tech stack if it's something that is rapidly changing (e.g., .NET Aspire, JS frameworks), with a prompt like this:\n\n```text\nI want you to go through the implementation plan and implementation details, looking for areas that could\nbenefit from additional research as .NET Aspire is a rapidly changing library. For those areas that you identify that\nrequire further research, I want you to update the research document with additional details about the specific\nversions that we are going to be using in this Taskify application and spawn parallel research tasks to clarify\nany details using research from the web.\n```\n\nDuring this process, you might find that Claude Code gets stuck researching the wrong thing - you can help nudge it in the right direction with a prompt like this:\n\n```text\nI think we need to break this down into a series of steps. First, identify a list of tasks\nthat you would need to do during implementation that you're not sure of or would benefit\nfrom further research. Write down a list of those tasks. And then for each one of these tasks,\nI want you to spin up a separate research task so that the net results is we are researching\nall of those very specific tasks in parallel. What I saw you doing was it looks like you were\nresearching .NET Aspire in general and I don't think that's gonna do much for us in this case.\nThat's way too untargeted research. The research needs to help you solve a specific targeted question.\n```\n\n> [!NOTE]\n> Claude Code might be over-eager and add components that you did not ask for. Ask it to clarify the rationale and the source of the change.\n\n### **STEP 5:** Have Claude Code validate the plan\n\nWith the plan in place, you should have Claude Code run through it to make sure that there are no missing pieces. You can use a prompt like this:\n\n```text\nNow I want you to go and audit the implementation plan and the implementation detail files.\nRead through it with an eye on determining whether or not there is a sequence of tasks that you need\nto be doing that are obvious from reading this. Because I don't know if there's enough here. For example,\nwhen I look at the core implementation, it would be useful to reference the appropriate places in the implementation\ndetails where it can find the information as it walks through each step in the core implementation or in the refinement.\n```\n\nThis helps refine the implementation plan and helps you avoid potential blind spots that Claude Code missed in its planning cycle. Once the initial refinement pass is complete, ask Claude Code to go through the checklist once more before you can get to the implementation.\n\nYou can also ask Claude Code (if you have the [GitHub CLI](https:\u002F\u002Fdocs.github.com\u002Fen\u002Fgithub-cli\u002Fgithub-cli) installed) to go ahead and create a pull request from your current branch to `main` with a detailed description, to make sure that the effort is properly tracked.\n\n> [!NOTE]\n> Before you have the agent implement it, it's also worth prompting Claude Code to cross-check the details to see if there are any over-engineered pieces (remember - it can be over-eager). If over-engineered components or decisions exist, you can ask Claude Code to resolve them. Ensure that Claude Code follows the [constitution](base\u002Fmemory\u002Fconstitution.md) as the foundational piece that it must adhere to when establishing the plan.\n\n### **STEP 6:** Generate task breakdown with \u002Fspeckit.tasks\n\nWith the implementation plan validated, you can now break down the plan into specific, actionable tasks that can be executed in the correct order. Use the `\u002Fspeckit.tasks` command to automatically generate a detailed task breakdown from your implementation plan:\n\n```text\n\u002Fspeckit.tasks\n```\n\nThis step creates a `tasks.md` file in your feature specification directory that contains:\n\n- **Task breakdown organized by user story** - Each user story becomes a separate implementation phase with its own set of tasks\n- **Dependency management** - Tasks are ordered to respect dependencies between components (e.g., models before services, services before endpoints)\n- **Parallel execution markers** - Tasks that can run in parallel are marked with `[P]` to optimize development workflow\n- **File path specifications** - Each task includes the exact file paths where implementation should occur\n- **Test-driven development structure** - If tests are requested, test tasks are included and ordered to be written before implementation\n- **Checkpoint validation** - Each user story phase includes checkpoints to validate independent functionality\n\nThe generated tasks.md provides a clear roadmap for the `\u002Fspeckit.implement` command, ensuring systematic implementation that maintains code quality and allows for incremental delivery of user stories.\n\n### **STEP 7:** Implementation\n\nOnce ready, use the `\u002Fspeckit.implement` command to execute your implementation plan:\n\n```text\n\u002Fspeckit.implement\n```\n\nThe `\u002Fspeckit.implement` command will:\n\n- Validate that all prerequisites are in place (constitution, spec, plan, and tasks)\n- Parse the task breakdown from `tasks.md`\n- Execute tasks in the correct order, respecting dependencies and parallel execution markers\n- Follow the TDD approach defined in your task plan\n- Provide progress updates and handle errors appropriately\n\n> [!IMPORTANT]\n> The AI agent will execute local CLI commands (such as `dotnet`, `npm`, etc.) - make sure you have the required tools installed on your machine.\n\nOnce the implementation is complete, test the application and resolve any runtime errors that may not be visible in CLI logs (e.g., browser console errors). You can copy and paste such errors back to your AI agent for resolution.\n\n\u003C\u002Fdetails>\n\n---\n\n## 🔍 Troubleshooting\n\n### Git Credential Manager on Linux\n\nIf you're having issues with Git authentication on Linux, you can install Git Credential Manager:\n\n```bash\n#!\u002Fusr\u002Fbin\u002Fenv bash\nset -e\necho \"Downloading Git Credential Manager v2.6.1...\"\nwget https:\u002F\u002Fgithub.com\u002Fgit-ecosystem\u002Fgit-credential-manager\u002Freleases\u002Fdownload\u002Fv2.6.1\u002Fgcm-linux_amd64.2.6.1.deb\necho \"Installing Git Credential Manager...\"\nsudo dpkg -i gcm-linux_amd64.2.6.1.deb\necho \"Configuring Git to use GCM...\"\ngit config --global credential.helper manager\necho \"Cleaning up...\"\nrm gcm-linux_amd64.2.6.1.deb\n```\n\n## 💬 Support\n\nFor support, please open a [GitHub issue](https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fissues\u002Fnew). We welcome bug reports, feature requests, and questions about using Spec-Driven Development.\n\n## 🙏 Acknowledgements\n\nThis project is heavily influenced by and based on the work and research of [John Lam](https:\u002F\u002Fgithub.com\u002Fjflam).\n\n## 📄 License\n\nThis project is licensed under the terms of the MIT open source license. Please refer to the [LICENSE](.\u002FLICENSE) file for the full terms.\n","\u003Cdiv align=\"center\">\n \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgithub_spec-kit_readme_7b06b649a35a.webp\" alt=\"Spec Kit Logo\" width=\"200\" height=\"200\"\u002F>\n \u003Ch1>🌱 Spec Kit\u003C\u002Fh1>\n \u003Ch3>\u003Cem>更快地构建高质量软件。\u003C\u002Fem>\u003C\u002Fh3>\n\u003C\u002Fdiv>\n\n\u003Cp align=\"center\">\n \u003Cstrong>一个开源工具包，让你专注于产品场景和可预测的结果，而不是从头开始为每个部分进行凭感觉编码。\u003C\u002Fstrong>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Freleases\u002Flatest\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fgithub\u002Fspec-kit\" alt=\"最新版本\"\u002F>\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fstargazers\">\u003Cimg src=\"https.:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fgithub\u002Fspec-kit?style=social\" alt=\"GitHub 星标\"\u002F>\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fgithub\u002Fspec-kit\" alt=\"许可证\"\u002F>\u003C\u002Fa>\n \u003Ca href=\"https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-GitHub_Pages-blue\" alt=\"文档\"\u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\n---\n\n## 目录\n\n- [🤔 什么是规范驱动开发？](#-what-is-spec-driven-development)\n- [⚡ 开始使用](#-get-started)\n- [📽️ 视频概览](#️-video-overview)\n- [🧩 社区扩展](#-community-extensions)\n- [🎨 社区预设](#-community-presets)\n- [🚶 社区教程](#-community-walkthroughs)\n- [🛠️ 社区伙伴](#️-community-friends)\n- [🤖 支持的 AI 编码助手集成](#-supported-ai-coding-agent-integrations)\n- [🔧 Specify CLI 参考](#-specify-cli-reference)\n- [🧩 让 Spec Kit 更符合你的需求：扩展与预设](#-making-spec-kit-your-own-extensions--presets)\n- [📚 核心理念](#-core-philosophy)\n- [🌟 开发阶段](#-development-phases)\n- [🎯 实验目标](#-experimental-goals)\n- [🔧 前置条件](#-prerequisites)\n- [📖 了解更多](#-learn-more)\n- [📋 详细流程](#-detailed-process)\n- [🔍 故障排除](#-troubleshooting)\n- [💬 支持](#-support)\n- [🙏 致谢](#-acknowledgements)\n- [📄 许可证](#-license)\n\n## 🤔 什么是规范驱动开发？\n\n规范驱动开发**颠覆了传统软件开发的模式**。几十年来，代码一直被视为核心——而规格说明只是我们在开始“真正”的编码工作之前搭建并丢弃的脚手架。规范驱动开发则改变了这一点：**规格说明可以直接执行**，从而直接生成可用的实现，而不仅仅是作为指导。\n\n## ⚡ 开始使用\n\n### 1. 安装 Specify CLI\n\n选择你喜欢的安装方式：\n\n> **重要提示：** Spec Kit 的官方维护包仅从此 GitHub 仓库发布。任何在 PyPI 上同名的包都**与本项目无关**，且不由 Spec Kit 维护人员维护。请务必按照下方所示直接从 GitHub 安装。\n\n#### 选项 1：持久化安装（推荐）\n\n只需安装一次，即可在任何地方使用。为了稳定性，请固定某个特定的发布标签（查看 [Releases](https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Freleases) 获取最新版本）：\n\n```bash\n# 安装特定稳定版（推荐 — 将 vX.Y.Z 替换为最新标签）\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z\n\n# 或者从 main 分支安装最新版本（可能包含未发布的更改）\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git\n```\n\n然后验证是否已正确安装：\n\n```bash\nspecify version\n```\n\n接着可以直接使用该工具：\n\n```bash\n# 创建新项目\nspecify init \u003CPROJECT_NAME>\n\n# 或在现有项目中初始化\nspecify init . --ai copilot\n# 或\nspecify init --here --ai copilot\n\n# 检查已安装的工具\nspecify check\n```\n\n要升级 Specify，请参阅[升级指南](.\u002Fdocs\u002Fupgrade.md)，获取详细说明。快速升级方法如下：\n\n```bash\nuv tool install specify-cli --force --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z\n```\n\n#### 选项 2：一次性使用\n\n无需安装，直接运行：\n\n```bash\n# 创建新项目（固定到稳定版 — 将 vX.Y.Z 替换为最新标签）\nuvx --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z specify init \u003CPROJECT_NAME>\n\n# 或在现有项目中初始化\nuvx --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z specify init . --ai copilot\n# 或\nuvx --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z specify init --here --ai copilot\n```\n\n**持久化安装的优势：**\n\n- 工具会一直安装在系统路径中，随时可用\n- 无需创建 shell 别名\n- 可以更好地管理工具，例如使用 `uv tool list`、`uv tool upgrade` 和 `uv tool uninstall`\n- Shell 配置更简洁\n\n#### 选项 3：企业级 \u002F 离线环境安装\n\n如果您的环境无法访问 PyPI 或 GitHub，请参阅[企业级 \u002F 离线环境安装](.\u002Fdocs\u002Finstallation.md#enterprise--air-gapped-installation)指南，了解如何使用 `pip download` 在联网机器上创建适用于不同操作系统的便携式 wheel 包的分步说明。\n\n### 2. 确立项目原则\n\n在项目目录中启动你的 AI 助手。大多数助手将 spec-kit 作为 `\u002Fspeckit.*` 斜杠命令暴露出来；而 Codex CLI 在技能模式下则使用 `$speckit-*` 命令。\n\n使用 **`\u002Fspeckit.constitution`** 命令来制定项目的治理原则和发展指南，这些原则将指导后续的所有开发工作。\n\n```bash\n\u002Fspeckit.constitution 制定以代码质量、测试标准、用户体验一致性及性能要求为核心的项目原则\n```\n\n### 3. 创建规范\n\n使用 **`\u002Fspeckit.specify`** 命令描述你想要构建的内容。重点关注**做什么**和**为什么做**，而不是技术栈。\n\n```bash\n\u002Fspeckit.specify 构建一个应用程序，帮助我将照片整理到不同的相册中。相册按日期分组，可以在主页面上通过拖放重新排序。相册之间不会嵌套。每个相册内的照片将以平铺式界面预览。\n```\n\n### 4. 制定技术实现计划\n\n使用 **`\u002Fspeckit.plan`** 命令提供你的技术栈和架构选择。\n\n```bash\n\u002Fspeckit.plan 应用程序使用 Vite，并尽量减少库的数量。尽可能使用原生 HTML、CSS 和 JavaScript。图片不会上传到任何地方，元数据将存储在本地 SQLite 数据库中。\n```\n\n### 5. 分解任务\n\n使用 **`\u002Fspeckit.tasks`** 从你的实施计划中创建一份可执行的任务清单。\n\n```bash\n\u002Fspeckit.tasks\n```\n\n### 6. 执行实现\n\n使用 **`\u002Fspeckit.implement`** 执行所有任务，并按照计划构建你的功能。\n\n```bash\n\u002Fspeckit.implement\n```\n\n有关详细的分步说明，请参阅我们的[全面指南](.\u002Fspec-driven.md)。\n\n## 📽️ 视频概览\n\n想亲眼看看 Spec Kit 的实际效果吗？观看我们的[视频概览](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=a9eR1xsfvHg&pp=0gcJCckJAYcqIYzv)吧！\n\n[![Spec Kit 视频封面](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgithub_spec-kit_readme_8e05e17e2af4.jpg)](https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=a9eR1xsfvHg&pp=0gcJCckJAYcqIYzv)\n\n## 🧩 社区扩展\n\n> [!NOTE]\n> 社区扩展由各自的作者独立创建和维护。GitHub 和 Spec Kit 维护者可能会对向社区目录添加条目的拉取请求进行格式、目录结构或政策合规性的审查，但他们**不会审查、审计、认可或支持扩展代码本身**。社区扩展网站也是一个第三方资源。请在安装和使用前自行审阅扩展的源代码，并根据自身判断决定是否使用。\n\n🔍 **在[社区扩展网站](https:\u002F\u002Fspeckit-community.github.io\u002Fextensions\u002F)上浏览和搜索社区扩展。**\n\n以下由社区贡献的扩展可在 [`catalog.community.json`](extensions\u002Fcatalog.community.json) 中找到：\n\n**分类：**\n\n- `docs` — 读取、验证或生成规范相关工件\n- `code` — 审查、验证或修改源代码\n- `process` — 协调跨阶段的工作流\n- `integration` — 与外部平台同步\n- `visibility` — 报告项目健康状况或进展\n\n**作用：**\n\n- `只读` — 生成报告而不修改文件\n- `读写` — 修改文件、创建工件或更新规范\n\n| 扩展 | 用途 | 类别 | 影响 | URL |\n|-----------|---------|----------|--------|-----|\n| 代理分配 | 将专门的 Claude Code 代理分配给 spec-kit 任务，以实现目标执行 | `process` | 读+写 | [spec-kit-agent-assign](https:\u002F\u002Fgithub.com\u002Fxymelon\u002Fspec-kit-agent-assign) |\n| AI 驱动工程 (AIDE) | 一种结构化的 7 步工作流，用于借助 AI 助手从零开始构建新项目——从愿景到实施 | `process` | 读+写 | [aide](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Faide) |\n| 架构影响预览器 | 在实施之前预测拟议更改的架构影响、复杂性及风险。 | `visibility` | 只读 | [spec-kit-architect-preview](https:\u002F\u002Fgithub.com\u002FUmmeHabiba1312\u002Fspec-kit-architect-preview) |\n| 归档扩展 | 将已合并的功能归档到主项目存储中。 | `docs` | 读+写 | [spec-kit-archive](https:\u002F\u002Fgithub.com\u002Fstn1slv\u002Fspec-kit-archive) |\n| Azure DevOps 集成 | 使用 OAuth 认证将用户故事和任务同步到 Azure DevOps 工作项 | `integration` | 读+写 | [spec-kit-azure-devops](https:\u002F\u002Fgithub.com\u002Fpragya247\u002Fspec-kit-azure-devops) |\n| 分支规范 | 可配置的分支和文件夹命名规范，支持预设和自定义模式 | `process` | 读+写 | [spec-kit-branch-convention](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-branch-convention) |\n| 现有代码库启动 | 为现有代码库启动 spec-kit——自动发现架构并逐步采用 SDD | `process` | 读+写 | [spec-kit-brownfield](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-brownfield) |\n| Bugfix 工作流 | 结构化的 Bugfix 工作流——捕获 bug、追溯到规范工件，并对规范进行精准修复 | `process` | 读+写 | [spec-kit-bugfix](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-bugfix) |\n| Canon | 添加基于规范（基线）的工作流：规范优先、代码优先、规范漂移。需要安装 Canon Core 预设。 | `process` | 读+写 | [spec-kit-canon](https:\u002F\u002Fgithub.com\u002Fmaximiliamus\u002Fspec-kit-canon\u002Ftree\u002Fmaster\u002Fextension) |\n| 目录 CI | 自动验证 spec-kit 社区目录条目——结构、URL、差异及语法检查 | `process` | 只读 | [spec-kit-catalog-ci](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-catalog-ci) |\n| CI 守护 | CI\u002FCD 中的规范合规门控——验证规范是否存在、检查漂移，并在存在差距时阻止合并 | `process` | 只读 | [spec-kit-ci-guard](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-ci-guard) |\n| 检查点扩展 | 在实施过程中提交所做的更改，以免最后只有一份非常大的提交 | `code` | 读+写 | [spec-kit-checkpoint](https:\u002F\u002Fgithub.com\u002Faaronrsun\u002Fspec-kit-checkpoint) |\n| 清理扩展 | 实施后的质量门，审查更改、修复小问题（侦察规则）、为中等问题创建任务，并对大问题生成分析报告 | `code` | 读+写 | [spec-kit-cleanup](https:\u002F\u002Fgithub.com\u002Fdsrednicki\u002Fspec-kit-cleanup) |\n| 协调扩展 | 通过子代理委派来协调 spec-kit 各阶段，以减少上下文污染。 | `process` | 读+写 | [spec-kit-conduct-ext](https:\u002F\u002Fgithub.com\u002Ftwbrandon7\u002Fspec-kit-conduct-ext) |\n| Confluence 扩展 | 在 Confluence 中创建文档，总结规范和计划文件 | `integration` | 读+写 | [spec-kit-confluence](https:\u002F\u002Fgithub.com\u002Faaronrsun\u002Fspec-kit-confluence) |\n| DocGuard — CDD 强制执行 | 基于规范驱动开发的强制执行。通过自动化检查、AI 驱动的工作流和 spec-kit 钩子来验证、评分并追踪项目文档。无 NPM 运行时依赖。 | `docs` | 读+写 | [spec-kit-docguard](https:\u002F\u002Fgithub.com\u002Fraccioly\u002Fdocguard) |\n| 扩展化 | 创建并验证扩展及其目录 | `process` | 读+写 | [extensify](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Fextensify) |\n| 修复发现 | 自动化的分析-修复-重新分析循环，持续解决规范发现的问题直至清零 | `code` | 读+写 | [spec-kit-fix-findings](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-fix-findings) |\n| FixIt 扩展 | 规范感知的 bug 修复——将 bug 映射到规范工件，提出方案并应用最小限度的更改 | `code` | 读+写 | [spec-kit-fixit](https:\u002F\u002Fgithub.com\u002Fspeckit-community\u002Fspec-kit-fixit) |\n| 舰队编排器 | 在所有 SpecKit 阶段中，通过人工介入的门控来编排完整的功能生命周期 | `process` | 读+写 | [spec-kit-fleet](https:\u002F\u002Fgithub.com\u002Fsharathsatish\u002Fspec-kit-fleet) |\n| GitHub Issues 集成 1 | 从 GitHub Issues 生成规范工件——导入问题、同步更新并保持双向可追溯性 | `integration` | 读+写 | [spec-kit-github-issues](https:\u002F\u002Fgithub.com\u002FFatima367\u002Fspec-kit-github-issues) |\n| GitHub Issues 集成 2 | 从现有的 GitHub 问题创建并同步本地规范 | `integration` | 读+写 | [spec-kit-issue](https:\u002F\u002Fgithub.com\u002Faaronrsun\u002Fspec-kit-issue) |\n| 迭代 | 通过两阶段的定义与应用工作流迭代规范文档——在实施过程中细化规范，然后直接返回构建 | `docs` | 读+写 | [spec-kit-iterate](https:\u002F\u002Fgithub.com\u002Fimviancagrace\u002Fspec-kit-iterate) |\n| Jira 集成 | 根据 spec-kit 规范和任务分解创建 Jira Epic、Story 和 Issue，支持可配置的层级结构和自定义字段 | `integration` | 读+写 | [spec-kit-jira](https:\u002F\u002Fgithub.com\u002Fmbachorik\u002Fspec-kit-jira) |\n| 学习扩展 | 从实施中生成教育指南，并结合指导上下文增强说明 | `docs` | 读+写 | [spec-kit-learn](https:\u002F\u002Fgithub.com\u002Fimviancagrace\u002Fspec-kit-learn) |\n| MAQA — 多代理与质量保证 | 协调员 → 功能 → QA 代理的工作流，采用并行的工作树式实施。语言无关。自动检测已安装的看板插件。可选 CI 门控。 | `process` | 读+写 | [spec-kit-maqa-ext](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-ext) |\n| MAQA Azure DevOps 集成 | MAQA 的 Azure DevOps 看板集成——随着功能进展同步用户故事和任务子项 | `integration` | 读+写 | [spec-kit-maqa-azure-devops](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-azure-devops) |\n| MAQA CI\u002FCD 门控 | 自动检测 GitHub Actions、CircleCI、GitLab CI 和 Bitbucket Pipelines。在流水线未通过前阻止 QA 移交。 | `process` | 读+写 | [spec-kit-maqa-ci](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-ci) |\n| MAQA GitHub 项目集成 | MAQA 的 GitHub 项目 v2 集成——随着功能进展同步草稿问题和状态列 | `integration` | 读+写 | [spec-kit-maqa-github-projects](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-github-projects) |\n| MAQA Jira 集成 | MAQA 的 Jira 集成——随着功能在看板上推进同步 Story 和 Subtask | `integration` | 读+写 | [spec-kit-maqa-jira](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-jira) |\n| MAQA Linear 集成 | MAQA 的 Linear 集成——随着功能进展同步工作流状态中的问题和子问题 | `integration` | 读+写 | [spec-kit-maqa-linear](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-linear) |\n| MAQA Trello 集成 | MAQA 的 Trello 看板集成——从规范填充看板、移动卡片、实时勾选清单 | `integration` | 读+写 | [spec-kit-maqa-trello](https:\u002F\u002Fgithub.com\u002FGenieRobot\u002Fspec-kit-maqa-trello) |\n| MemoryLint | 代理内存治理工具：自动审计并修复 AGENTS.md 与宪法之间的边界冲突。 | `process` | 读+写 | [memorylint](https:\u002F\u002Fgithub.com\u002FRbBtSn0w\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Fmemorylint) |\n| 入职 | 为新加入 spec-kit 项目的开发者提供情境化入职和渐进式成长。解释规范、映射依赖关系、验证理解并指导下一步行动 | `process` | 读+写 | [spec-kit-onboard](https:\u002F\u002Fgithub.com\u002Fdmux\u002Fspec-kit-onboard) |\n| 优化 | 审计并优化 AI 治理以提高上下文效率——包括令牌预算、规则健康度、可解释性、压缩、连贯性和回声检测 | `process` | 读+写 | [spec-kit-optimize](https:\u002F\u002Fgithub.com\u002FsakitA\u002Fspec-kit-optimize) |\n| 计划评审门控 | 要求在允许生成任务之前，必须通过 MR\u002FPR 合并 spec.md 和 plan.md | `process` | 只读 | [spec-kit-plan-review-gate](https:\u002F\u002Fgithub.com\u002Fluno\u002Fspec-kit-plan-review-gate) |\n| PR 桥 | 自动从规范工件生成拉取请求描述、检查清单和摘要 | `process` | 只读 | [spec-kit-pr-bridge-](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-pr-bridge-) |\n| 预设化 | 创建并验证预设及其目录 | `process` | 读+写 | [presetify](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Fpresetify) |\n| 产品锻造 | 完整的产品生命周期：研究 → 产品规格 → SpecKit → 实施 → 验证 → 测试 | `process` | 读+写 | [speckit-product-forge](https:\u002F\u002Fgithub.com\u002FVaiYav\u002Fspeckit-product-forge) |\n| 项目健康检查 | 诊断 Spec Kit 项目，并报告结构、代理、功能、脚本、扩展和 git 方面的健康问题 | `visibility` | 只读 | [spec-kit-doctor](https:\u002F\u002Fgithub.com\u002FKhawarHabibKhan\u002Fspec-kit-doctor) |\n| 项目状态 | 显示当前 SDD 工作流的进度——活跃功能、工件状态、任务完成情况、工作流阶段以及扩展摘要 | `visibility` | 只读 | [spec-kit-status](https:\u002F\u002Fgithub.com\u002FKhawarHabibKhan\u002Fspec-kit-status) |\n| QA 测试扩展 | 通过浏览器驱动或基于 CLI 的验收标准验证，进行系统的 QA 测试 | `code` | 只读 | [spec-kit-qa](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-qa) |\n| Ralph 循环 | 使用 AI 代理 CLI 的自主实施循环 | `code` | 读+写 | [spec-kit-ralph](https:\u002F\u002Fgithub.com\u002FRubiss\u002Fspec-kit-ralph) |\n| 调解扩展 | 通过手术式更新功能工件来纠正实施偏差。 | `docs` | 读+写 | [spec-kit-reconcile](https:\u002F\u002Fgithub.com\u002Fstn1slv\u002Fspec-kit-reconcile) |\n| 仓库索引 | 为现有仓库生成索引，用于概览、架构和模块级别分析。 | `docs` | 只读 | [spec-kit-repoindex](https:\u002F\u002Fgithub.com\u002Fliuyiyu\u002Fspec-kit-repoindex) |\n| 回顾扩展 | 包含指标、规范准确度评估和改进建议的冲刺回顾分析 | `process` | 读+写 | [spec-kit-retro](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-retro) |\n| 回顾扩展（二） | 实施后的回顾，包含规范遵循评分、漂移分析以及人工审核的规范更新 | `docs` | 读+写 | [spec-kit-retrospective](https:\u002F\u002Fgithub.com\u002Femi-dm\u002Fspec-kit-retrospective) |\n| 评审扩展 | 实施后的全面代码评审，由专业代理负责代码质量、注释、测试、错误处理、类型设计和简化 | `code` | 只读 | [spec-kit-review](https:\u002F\u002Fgithub.com\u002FismaelJimenez\u002Fspec-kit-review) |\n| SDD 工具 | 恢复中断的工作流、验证项目健康状况，并确认规范到任务的可追溯性 | `process` | 读+写 | [speckit-utils](https:\u002F\u002Fgithub.com\u002Fmvanhorn\u002Fspeckit-utils) |\n| 安全审查 | 使用 AI 驱动的 DevSecOps 分析对代码库进行全面的安全审计 | `code` | 只读 | [spec-kit-security-review](https:\u002F\u002Fgithub.com\u002FDyanGalih\u002Fspec-kit-security-review) |\n| SFSpeckit | 企业 Salesforce SDLC，包含 18 条命令，覆盖完整的 SDD 生命周期。 | `process` | 读+写 | [spec-kit-sf](https:\u002F\u002Fgithub.com\u002Fysumanth06\u002Fspec-kit-sf) |\n| 发布扩展 | 自动化发布流程：飞行前检查、分支同步、变更日志生成、CI 验证和 PR 创建 | `process` | 读+写 | [spec-kit-ship](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-ship) |\n| 规范批评扩展 | 从产品战略和工程风险的角度对规范和计划进行双重视角的批判性审查 | `docs` | 只读 | [spec-kit-critique](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-critique) |\n| 规范图 | 自动生成 Mermaid 图表，展示 SDD 工作流状态、功能进展和任务依赖关系 | `visibility` | 只读 | [spec-kit-diagram-](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-diagram-) |\n| 规范精炼 | 就地更新规范，将更改传播到计划和任务中，并比较不同工件之间的影响 | `process` | 读+写 | [spec-kit-refine](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-refine) |\n| 规范同步 | 检测并解决规范与实施之间的偏差。在人工批准下进行 AI 辅助的修正 | `docs` | 读+写 | [spec-kit-sync](https:\u002F\u002Fgithub.com\u002Fbgervin\u002Fspec-kit-sync) |\n| 规范测试 | 根据规范标准自动生成测试脚手架，绘制覆盖率地图，并找出未被测试的需求 | `code` | 读+写 | [spec-kit-spectest](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-spectest) |\n| 员工评审扩展 | 由工程师级别的员工进行代码评审，验证实施是否符合规范，同时检查安全性、性能和测试覆盖率 | `code` | 只读 | [spec-kit-staff-review](https:\u002F\u002Fgithub.com\u002Farunt14\u002Fspec-kit-staff-review) |\n| 状态报告 | 规范驱动工作流的项目状态、功能进展以及下一步行动建议 | `visibility` | 只读 | [Open-Agent-Tools\u002Fspec-kit-status](https:\u002F\u002Fgithub.com\u002FOpen-Agent-Tools\u002Fspec-kit-status) |\n| 超能力桥 | 在整个生命周期内（澄清、TDD、评审、验证、批评、调试、分支完成）协调 obra\u002F超能力技能在 spec-kit SDD 工作流中的运用 | `process` | 读+写 | [superpowers-bridge](https:\u002F\u002Fgithub.com\u002FRbBtSn0w\u002Fspec-kit-extensions\u002Ftree\u002Fmain\u002Fsuperpowers-bridge) |\n| TinySpec | 针对小型任务的轻量级单文件工作流——跳过繁重的多步骤 SDD 流程 | `process` | 读+写 | [spec-kit-tinyspec](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-tinyspec) |\n| V 模型扩展包 | 强制执行 V 模型配对生成开发规范和测试规范，并实现完全可追溯 | `docs` | 读+写 | [spec-kit-v-model](https:\u002F\u002Fgithub.com\u002Fleocamello\u002Fspec-kit-v-model) |\n| 验证扩展 | 实施后的质量门，验证已实施的代码是否符合规范工件 | `code` | 只读 | [spec-kit-verify](https:\u002F\u002Fgithub.com\u002FismaelJimenez\u002Fspec-kit-verify) |\n| 验证任务扩展 | 检测幽灵完成：tasks.md 中标记了 [X] 但实际并未实施的任务 | `code` | 只读 | [spec-kit-verify-tasks](https:\u002F\u002Fgithub.com\u002Fdatastone-inc\u002Fspec-kit-verify-tasks) |\n| 如果假设分析 | 在承诺实施需求变更之前，预览其下游影响（复杂性、工作量、任务和风险） | `visibility` | 只读 | [spec-kit-whatif](https:\u002F\u002Fgithub.com\u002FDevAbdullah90\u002Fspec-kit-whatif) |\n| 工作树隔离 | 为并行功能开发生成隔离的 Git 工作树，无需切换检出 | `process` | 读+写 | [spec-kit-worktree](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-worktree) |\n| 工作树 | 默认启用的工作树隔离，用于并行代理——兄弟布局或嵌套布局 | `process` | 读+写 | [spec-kit-worktree-parallel](https:\u002F\u002Fgithub.com\u002Fdango85\u002Fspec-kit-worktree-parallel) |\n\n要提交您自己的扩展，请参阅[扩展发布指南](extensions\u002FEXTENSION-PUBLISHING-GUIDE.md)。\n\n\n\n## 🎨 社区预设\n\n> [!NOTE]\n> 社区预设由其各自作者独立创建和维护。GitHub 和 Spec Kit 维护者可能会审查向社区目录添加条目的拉取请求，以确保格式、目录结构或政策合规性，但他们**不会审查、审计、认可或支持预设代码本身**。请在安装和使用前自行审阅预设源代码。\n\n以下由社区贡献的预设可自定义 Spec Kit 的行为——覆盖模板、命令和术语，而无需更改任何工具。预设可在 [`catalog.community.json`](presets\u002Fcatalog.community.json) 中找到：\n\n| 预设 | 用途 | 提供 | 需求 | URL |\n|--------|---------|----------|----------|-----|\n| AIDE 就地迁移 | 为就地技术迁移（X → Y 模式）调整 AIDE 扩展的工作流程——添加迁移目标、验证关卡、知识文档和行为等价性标准 | 2 个模板，8 个命令 | AIDE 扩展 | [spec-kit-presets](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-presets) |\n| Canon Core | 调整原始 Spec Kit 工作流程，使其与 Canon 扩展协同工作 | 2 个模板，8 个命令 | — | [spec-kit-canon](https:\u002F\u002Fgithub.com\u002Fmaximiliamus\u002Fspec-kit-canon) |\n| 显式任务依赖 | 在 tasks.md 中添加显式的 `(depends on T###)` 依赖声明以及执行波次 DAG，以便进行并行调度 | 1 个模板，1 个命令 | — | [spec-kit-preset-explicit-task-dependencies](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-preset-explicit-task-dependencies) |\n| 小说写作 | 将规范驱动开发的工作流程调整用于故事创作：功能变为故事元素，规范变为故事梗概，计划变为故事结构，任务则变为逐场景的写作任务。支持单视角和多视角叙事、所有主要的情节结构框架，以及两种写作风格模式——作者风格示例或拟人化的人工智能文风。 | 21 个模板，17 个命令 | — | [spec-kit-preset-fiction-book-writing](https:\u002F\u002Fgithub.com\u002Fadaumann\u002Fspeckit-preset-fiction-book-writing) |\n| 多仓库分支管理 | 在计划和任务阶段协调多个 Git 仓库（独立仓库和子模块）之间的特性分支创建 | 2 个命令 | — | [spec-kit-preset-multi-repo-branching](https:\u002F\u002Fgithub.com\u002FsakitA\u002Fspec-kit-preset-multi-repo-branching) |\n| 海盗语（完整版） | 将 Spec Kit 的所有输出转换为海盗语——规范变为“航行清单”，计划变为“作战计划”，任务变为“船员分配” | 6 个模板，9 个命令 | — | [spec-kit-presets](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-presets) |\n| 目录导航 | 为生成的 spec.md、plan.md 和 tasks.md 文档添加可导航的目录 | 3 个模板，3 个命令 | — | [spec-kit-preset-toc-navigation](https:\u002F\u002Fgithub.com\u002FQuratulain-bilal\u002Fspec-kit-preset-toc-navigation) |\n| VS Code 提问 | 增强 clarify 命令，使其使用 `vscode\u002FaskQuestions` 进行批量交互式提问。 | 1 个命令 | — | [spec-kit-presets](https:\u002F\u002Fgithub.com\u002Ffdcastel\u002Fspec-kit-presets) |\n\n要构建并发布您自己的预设，请参阅[预设发布指南](presets\u002FPUBLISHING.md)。\n\n## 🚶 社区教程\n\n> [!NOTE]\n> 社区教程由其各自作者独立创建和维护。它们**未经过 GitHub 审查、认可或支持**。请在跟随操作前自行审阅内容，并根据自身判断使用。\n\n通过这些由社区贡献的教程，您可以了解规范驱动开发在不同场景下的实际应用：\n\n- **[从零开始的 .NET CLI 工具](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-dotnet-cli-demo)** — 从一个空目录开始构建一个时区实用工具作为 .NET 单一二进制 CLI 工具，涵盖完整的 Spec Kit 工作流程：制定章程、明确需求、制定计划、分解任务，并利用 GitHub Copilot 代理进行多轮实现。\n\n- **[从零开始的 Spring Boot + React 平台](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-spring-react-demo)** — 使用 Spring Boot、嵌入式 React、PostgreSQL 和 Docker Compose 从头构建一个 LLM 性能分析平台（REST API、图表、迭代跟踪），其中包含澄清步骤和跨构件一致性分析环节。\n\n- **[ASP.NET CMS 的改造项目](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-aspnet-brownfield-demo)** — 在现有的开源 .NET CMS（CarrotCakeCMS-Core，约 307,000 行 C#、Razor、SQL、JavaScript 和配置文件）中新增两项功能——跨平台 Docker Compose 基础设施和基于令牌认证的无头 REST API——展示 Spec Kit 如何融入现有代码库，即使没有预先的规范或章程。\n\n- **[Java 运行时的改造项目](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-java-brownfield-demo)** — 在现有的开源 Jakarta EE 运行时（Piranha，约 420,000 行 Java、XML、JSP、HTML 和配置文件，分布在 180 个 Maven 模块中）中新增一个受密码保护的服务器管理控制台，演示 Spec Kit 在大型多模块 Java 项目中的应用，且该项目此前既无规范也无章程。\n\n- **[Go \u002F React 仪表盘的改造项目](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-go-brownfield-demo)** — 完全通过**终端并使用 GitHub Copilot CLI**演示 Spec Kit。在 NASA 开源的 Hermes 地面支持系统（Go）基础上，新增一个轻量级的基于 React 的网络遥测仪表盘，证明从章程到明确需求、制定计划、分解任务再到实施的完整流程完全可以在终端中运行。\n\n- **[使用自定义预设的 Spring Boot MVC 应用程序](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-pirate-speak-preset-demo)** — 使用自定义的海盗语预设从零开始构建一个 Spring Boot MVC 应用程序，展示预设如何重塑整个 Spec Kit 的体验：规范变为“航行清单”，计划变为“作战计划”，任务则变为“船员分配”——所有内容均以纯正的海盗方言生成，且无需更改任何工具。\n\n- **[使用 AIDE 扩展的 Spring Boot + React 应用程序](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-aide-extension-demo)** — 演示**AIDE 扩展**，这是一种社区扩展，为 Spec Kit 添加了一种替代的规范驱动工作流程，采用高层规范（愿景）和低层规范（工作项），并按 7 步迭代生命周期组织：愿景 → 路线图 → 进度跟踪 → 工作队列 → 工作项 → 执行 → 反馈循环。以一个家庭交易平台（Spring Boot 4、React 19、PostgreSQL、Docker Compose）为例，说明扩展机制允许您接入不同风格的规范驱动开发，而无需更改任何核心工具——真正体现了 Spec Kit 中的“Kit”。\n\n## 🛠️ 社区伙伴\n\n> [!NOTE]\n> 此处列出的社区项目由各自作者独立创建和维护。它们**未经过 GitHub 审核、认可或支持**。请在安装和使用前自行审查其源代码，并根据自身判断决定是否使用。\n\n以下是一些扩展、可视化或基于 Spec Kit 构建的社区项目：\n\n- **[cc-spex](https:\u002F\u002Fgithub.com\u002Frhuss\u002Fcc-spex)** — 一个 Claude Code 插件，它在 Spec Kit 的基础上添加了可组合的特性，结合了基于 [Superpowers](https:\u002F\u002Fgithub.com\u002Fobra\u002Fsuperpowers) 的质量门控、规范\u002F代码评审、Git 工作树隔离以及通过代理团队实现并行开发等功能。\n\n- **[Spec Kit Assistant](https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=rfsales.speckit-assistant)** — 一款 VS Code 扩展，为完整的 SDD 流程（章程 → 规范 → 计划 → 任务 → 实现）提供可视化编排工具，包括阶段状态可视化、交互式任务清单、DAG 可视化，以及对 Claude、Gemini、GitHub Copilot 和 OpenAI 后端的支持。需要在 PATH 中包含 `specify` CLI。\n\n- **[SpecKit Companion](https:\u002F\u002Fmarketplace.visualstudio.com\u002Fitems?itemName=alfredoperez.speckit-companion)** — 一款 VS Code 扩展，为 Spec Kit 提供了一个可视化的 GUI 界面。用户可以在功能丰富的 Markdown 查看器中浏览规范，点击文件引用；可以附带图片创建规范；以 GitHub 风格的评论方式逐条在线修改和完善；通过可视化阶段推进器跟踪 SDD 流程的进度；还可以管理章程和模板等指导性文档。\n\n## 🤖 支持的 AI 编码代理集成\n\nSpec Kit 支持 30 多种 AI 编码代理，包括 CLI 工具和基于 IDE 的助手。完整列表及使用说明，请参阅 [支持的 AI 编码代理集成](https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002Freference\u002Fintegrations.html) 指南。\n\n运行 `specify integration list` 可查看当前安装版本中所有可用的集成。\n\n## 可用的斜杠命令\n\n运行 `specify init` 后，您的 AI 编码代理将可以使用这些用于结构化开发的斜杠命令。如果您传递 `--ai \u003Cagent> --ai-skills`，Spec Kit 将安装代理技能而非斜杠命令提示文件；`--ai-skills` 参数必须与 `--ai` 一起使用。\n\n#### 核心命令\n\n用于规范驱动开发流程的基本命令：\n\n| 命令 | 代理技能 | 描述 |\n| ------------------------ | ---------------------- | -------------------------------------------------------------------------- |\n| `\u002Fspeckit.constitution` | `speckit-constitution` | 创建或更新项目治理原则和开发指南 |\n| `\u002Fspeckit.specify` | `speckit-specify` | 定义您想要构建的内容（需求和用户故事） |\n| `\u002Fspeckit.plan` | `speckit-plan` | 使用您选择的技术栈制定技术实现计划 |\n| `\u002Fspeckit.tasks` | `speckit-tasks` | 生成用于实施的可操作任务列表 |\n| `\u002Fspeckit.taskstoissues` | `speckit-taskstoissues`| 将生成的任务列表转换为 GitHub 问题，以便跟踪和执行 |\n| `\u002Fspeckit.implement` | `speckit-implement` | 按照计划执行所有任务以构建功能 |\n\n#### 可选命令\n\n用于提升质量和验证的附加命令：\n\n| 命令 | 代理技能 | 描述 |\n| -------------------- | ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------ |\n| `\u002Fspeckit.clarify` | `speckit-clarify` | 清晰化不明确的部分（建议在 `\u002Fspeckit.plan` 之前使用；原名为 `\u002Fquizme`） |\n| `\u002Fspeckit.analyze` | `speckit-analyze` | 跨工件一致性与覆盖率分析（在 `\u002Fspeckit.tasks` 之后、`\u002Fspeckit.implement` 之前运行） |\n| `\u002Fspeckit.checklist` | `speckit-checklist` | 生成自定义的质量检查清单，用于验证需求的完整性、清晰性和一致性（类似于“英语的单元测试”） |\n\n## 🔧 Specify CLI 参考\n\n有关完整命令详情、选项和示例，请参阅 [CLI 参考](https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002Freference\u002Foverview.html)。\n\n## 🧩 自定义 Spec Kit：扩展与预设\n\nSpec Kit 可通过两种互补的系统——**扩展**和**预设**——进行个性化定制，此外还支持项目本地覆盖以进行一次性调整：\n\n| 优先级 | 组件类型 | 位置 |\n| -------: | ------------------------------------------------- | -------------------------------- |\n| ⬆ 1 | 项目本地覆盖 | `.specify\u002Ftemplates\u002Foverrides\u002F` |\n| 2 | 预设 — 自定义核心与扩展 | `.specify\u002Fpresets\u002Ftemplates\u002F` |\n| 3 | 扩展 — 添加新功能 | `.specify\u002Fextensions\u002Ftemplates\u002F` |\n| ⬇ 4 | Spec Kit 核心 — 内置 SDD 命令与模板 | `.specify\u002Ftemplates\u002F` |\n\n- **模板**会在**运行时**被解析——Spec Kit 会自上而下查找，并使用第一个匹配项。\n- 项目本地覆盖（`.specify\u002Ftemplates\u002Foverrides\u002F`）允许您针对单个项目进行一次性调整，而无需创建完整的预设。\n- **扩展\u002F预设命令**会在**安装时**应用——当您运行 `specify extension add` 或 `specify preset add` 时，命令文件会被写入代理目录（例如 `.claude\u002Fcommands\u002F`）。\n- 如果多个预设或扩展提供了相同的命令，则优先级最高的版本生效。移除后，次高优先级的版本会自动恢复。\n- 如果没有覆盖或自定义设置，Spec Kit 将使用其核心默认值。\n\n### 扩展 — 添加新功能\n\n当您需要超出 Spec Kit 核心功能范围的能力时，可以使用**扩展**。扩展会引入新的命令和模板——例如，添加内置 SDD 命令未涵盖的领域特定工作流、与外部工具集成，或增加全新的开发阶段。它们扩展了 *Spec Kit 的能力*。\n\n```bash\n# 搜索可用的扩展\nspecify extension search\n\n# 安装一个扩展\nspecify extension add \u003C扩展名>\n```\n\n例如，扩展可以添加 Jira 集成、实施后的代码评审、V 模型测试可追溯性，或项目健康诊断等功能。\n\n有关完整命令指南，请参阅 [扩展参考](https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002Freference\u002Fextensions.html)。您还可以浏览上方的 [社区扩展](#-community-extensions) 以了解现有选项。\n\n### 预设 — 自定义现有工作流\n\n当您希望改变 Spec Kit 的运行方式，而无需添加新功能时，可以使用 **预设**。预设会覆盖核心以及已安装扩展中自带的模板和命令——例如，强制采用以合规为导向的规格格式、使用领域特定术语，或将组织标准应用于计划和任务。它们能够自定义 Spec Kit 及其扩展生成的工件和说明文档。\n\n```bash\n# 搜索可用的预设\nspecify preset search\n\n# 安装一个预设\nspecify preset add \u003C预设名称>\n```\n\n例如，预设可以重新组织规格模板，以要求法规可追溯性；调整工作流程以适应您所使用的开发方法（如敏捷、看板、瀑布模型、用例驱动设计或领域驱动设计）；在计划中加入强制性的安全评审节点；强制执行测试先行的任务顺序；或将整个工作流程本地化为另一种语言。[海盗语演示](https:\u002F\u002Fgithub.com\u002Fmnriem\u002Fspec-kit-pirate-speak-preset-demo) 展示了自定义的深度。多个预设可以按优先级叠加使用。\n\n完整的命令指南，包括解析顺序和优先级叠加，请参阅 [预设参考文档](https:\u002F\u002Fgithub.github.io\u002Fspec-kit\u002Freference\u002Fpresets.html)。\n\n### 何时使用哪种方式\n\n| 目标 | 使用 |\n| --- | --- |\n| 添加全新的命令或工作流 | 扩展 |\n| 自定义规格、计划或任务的格式 | 预设 |\n| 集成外部工具或服务 | 扩展 |\n| 强制执行组织或法规标准 | 预设 |\n| 发布可重用的领域特定模板 | 两者皆可——预设用于覆盖模板，扩展则用于将模板与新命令打包在一起 |\n\n## 📚 核心理念\n\n规范驱动开发是一种结构化的流程，强调：\n\n- **意图驱动开发**：先明确“做什么”，再考虑“怎么做”\n- **丰富的规范创建**：通过约束条件和组织原则来构建规范\n- **多步骤迭代优化**：而非仅凭提示一次性生成代码\n- **高度依赖**先进 AI 模型的能力来进行规范解读\n\n## 🌟 开发阶段\n\n| 阶段 | 重点 | 关键活动 |\n| ---------------------------------------- | ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ |\n| **从零到一开发**（“绿地开发”） | 从头开始构建 | \u003Cul>\u003Cli>从高层次需求入手\u003C\u002Fli>\u003Cli>生成规范\u003C\u002Fli>\u003Cli>规划实施步骤\u003C\u002Fli>\u003Cli>构建生产就绪的应用程序\u003C\u002Fli>\u003C\u002Ful> |\n| **创意探索** | 并行实现 | \u003Cul>\u003Cli>探索多种解决方案\u003C\u002Fli>\u003Cli>支持多种技术栈和架构\u003C\u002Fli>\u003Cli>尝试不同的用户体验模式\u003C\u002Fli>\u003C\u002Ful> |\n| **迭代增强**（“棕地开发”） | 棕地现代化 | \u003Cul>\u003Cli>逐步添加新功能\u003C\u002Fli>\u003Cli>改造遗留系统\u003C\u002Fli>\u003Cli>调整流程\u003C\u002Fli>\u003C\u002Ful> |\n\n## 🎯 实验目标\n\n我们的研究和实验重点关注以下方面：\n\n### 技术无关性\n\n- 使用多样化的技术栈构建应用\n- 验证规范驱动开发并非局限于特定技术、编程语言或框架的假设\n\n### 企业约束\n\n- 展示关键任务型应用的开发\n- 融入组织约束条件（云服务商、技术栈、工程实践）\n- 支持企业级设计系统和合规要求\n\n### 以用户为中心的开发\n\n- 为不同用户群体和偏好构建应用\n- 支持多种开发方式（从直觉编码到原生 AI 开发）\n\n### 创意与迭代流程\n\n- 验证并行实现探索的概念\n- 提供稳健的迭代式功能开发流程\n- 将流程扩展至升级和现代化任务\n\n## 🔧 前置条件\n\n- **Linux\u002FmacOS\u002FWindows**\n- [受支持的](#-supported-ai-coding-agent-integrations) AI 编码助手\n- [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F) 用于包管理\n- [Python 3.11+](https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)\n- [Git](https:\u002F\u002Fgit-scm.com\u002Fdownloads)\n\n如果您在使用某个助手时遇到问题，请提交 issue，以便我们优化集成。\n\n## 📖 了解更多\n\n- **[完整的规范驱动开发方法论](.\u002Fspec-driven.md)** - 深入探讨完整流程\n- **[详细流程](#-detailed-process)** - 分步实施指南\n\n---\n\n## 📋 详细流程\n\n\u003Cdetails>\n\u003Csummary>点击展开详细的分步指南\u003C\u002Fsummary>\n\n您可以使用 Specify CLI 来初始化项目，它会将所需的工件引入您的环境。运行以下命令：\n\n```bash\nspecify init \u003C项目名称>\n```\n\n或者在当前目录下初始化：\n\n```bash\nspecify init .\n# 或者使用 --here 标志\nspecify init --here\n# 如果目录中已有文件，跳过确认\nspecify init . --force\n# 或\nspecify init --here --force\n```\n\n![Specify CLI 在终端中引导新项目](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgithub_spec-kit_readme_6f451003b826.gif)\n\n系统会提示您选择正在使用的 AI 助手。您也可以直接在终端中指定助手：\n\n```bash\nspecify init \u003C项目名称> --ai copilot\nspecify init \u003C项目名称> --ai gemini\nspecify init \u003C项目名称> --ai codex\n\n# 或在当前目录下：\nspecify init . --ai copilot\nspecify init . --ai codex --ai-skills\n\n# 或使用 --here 标志\nspecify init --here --ai copilot\nspecify init --here --ai codex --ai-skills\n\n# 强制合并到非空当前目录\nspecify init . --force --ai copilot\n\n# 或\nspecify init --here --force --ai copilot\n```\n\nCLI 会检查您是否已安装 Claude Code、Gemini CLI、Cursor CLI、Qwen CLI、opencode、Codex CLI、Qoder CLI、Tabnine CLI、Kiro CLI、Pi、Forge、Goose 或 Mistral Vibe。如果您尚未安装，或者希望在不检查工具的情况下获取模板，可以在命令中使用 `--ignore-agent-tools`：\n\n```bash\nspecify init \u003C项目名称> --ai copilot --ignore-agent-tools\n```\n\n### **步骤 1：** 确立项目原则\n\n进入项目文件夹并运行您的 AI 助手。在我们的示例中，我们使用的是 `claude`。\n\n![引导 Claude Code 环境](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgithub_spec-kit_readme_be9bceb0148f.gif)\n\n如果您看到 `\u002Fspeckit.constitution`、`\u002Fspeckit.specify`、`\u002Fspeckit.plan`、`\u002Fspeckit.tasks` 和 `\u002Fspeckit.implement` 命令可用，则说明配置正确。\n\n第一步应使用 `\u002Fspeckit.constitution` 命令确立项目的指导原则。这有助于确保在整个后续开发阶段中做出一致的决策：\n\n```text\n\u002Fspeckit.constitution 制定以代码质量、测试标准、用户体验一致性及性能要求为核心的项目原则。同时明确这些原则如何指导技术决策和实现选择。\n```\n\n此步骤会创建或更新 `.specify\u002Fmemory\u002Fconstitution.md` 文件，其中包含 AI 助手在规格定义、计划制定和实施阶段将参考的项目基础准则。\n\n### **步骤 2：** 创建项目规格\n\n在确立项目原则后，您可以开始编写功能规格说明书。使用 `\u002Fspeckit.specify` 命令，并提供您希望开发的项目的具体需求。\n\n> [!重要提示]\n> 尽可能明确地说明您要构建什么以及为什么构建。**此时不要关注技术栈**。\n\n示例提示：\n\n```text\n开发 Taskify 团队生产力平台。该平台应允许用户创建项目、添加团队成员、分配任务、评论任务，并以看板风格在不同看板之间移动任务。在本阶段的功能开发中，我们称之为“创建 Taskify”，系统将支持多个用户，但用户将在前期预先定义好。我希望有五位用户，分为两类：一位产品经理和四位工程师。请创建三个不同的示例项目。每个任务的状态应设有标准的看板列，例如“待办”、“进行中”、“评审中”和“已完成”。由于这只是最初的测试版本，用于确保基本功能已就绪，因此本应用暂不设置登录功能。在任务卡片的 UI 中，您应能够在看板工作区的不同列之间切换任务的当前状态。您还可以为特定卡片留下无限数量的评论。此外，您应能从该任务卡片中将任务分配给有效的用户之一。首次启动 Taskify 时，系统会列出五位可供选择的用户。无需输入密码。点击某位用户后，您将进入主视图，显示项目列表。点击某个项目后，您将打开该项目的看板。您可以看到各个列，并能够拖放卡片在不同列之间移动。分配给您——当前登录用户——的任务将以不同于其他任务的颜色显示，以便您快速识别自己的任务。您可以编辑自己留下的评论，但无法编辑他人留下的评论。您可以删除自己留下的评论，但不能删除他人留下的评论。\n```\n\n输入此提示后，您应该会看到 Claude Code 开始规划和规格编写流程。Claude Code 还会触发一些内置脚本来初始化代码库。\n\n完成此步骤后，您应会生成一个新的分支（例如 `001-create-taskify`），并在 `specs\u002F001-create-taskify` 目录下生成新的规格文档。\n\n生成的规格文档应包含一组用户故事和功能需求，按照模板进行定义。\n\n此时，您的项目文件夹内容应类似于以下结构：\n\n```text\n└── .specify\n ├── memory\n │ └── constitution.md\n ├── scripts\n │ ├── check-prerequisites.sh\n │ ├── common.sh\n │ ├── create-new-feature.sh\n │ ├── setup-plan.sh\n │ └── update-claude-md.sh\n ├── specs\n │ └── 001-create-taskify\n │ └── spec.md\n └── templates\n ├── plan-template.md\n ├── spec-template.md\n └── tasks-template.md\n```\n\n### **步骤 3：** 功能规格澄清（规划前必做）\n\n在生成基础规格说明书后，您可以进一步澄清首次尝试中未完全捕捉到的需求。\n\n在制定技术方案之前，应先执行结构化的澄清流程，以减少后续的返工。\n\n推荐顺序：\n\n1. 使用 `\u002Fspeckit.clarify`（结构化）——按顺序、基于覆盖范围的提问方式，并将答案记录在“澄清”部分。\n2. 如仍有模糊之处，可选择性地进行即兴式的自由格式细化。\n\n如果您有意跳过澄清步骤（例如进行探索性原型开发），请明确说明，以免助手因缺少澄清而阻塞。\n\n示例自由格式细化提示（在 `\u002Fspeckit.clarify` 之后，若仍需补充）：\n\n```text\n对于每个示例项目或您创建的项目，其任务数量应在 5 到 15 个之间随机分布于不同的完成状态。请确保每个完成阶段至少有一项任务。\n```\n\n此外，您还应要求 Claude Code 验证“评审与验收检查清单”，对符合要求的条目打勾，未满足要求的则保持空白。可以使用如下提示：\n\n```text\n阅读评审与验收检查清单，如果功能规格符合标准，请逐一勾选清单中的各项；若不符合，则保持空白。\n```\n\n与 Claude Code 的交互是澄清和讨论规格的好机会——**请勿将其首次尝试视为最终结果**。\n\n### **步骤 4：** 生成计划\n\n现在你可以明确技术栈和其他技术需求。你可以使用项目模板中内置的 `\u002Fspeckit.plan` 命令，并提供如下提示：\n\n```text\n我们将使用 .NET Aspire 来构建此项目，数据库采用 Postgres。前端应使用 Blazor Server，具备拖放式任务看板和实时更新功能。同时需要创建一个 REST API，包含项目 API、任务 API 和通知 API。\n```\n\n此步骤的输出将包括若干实现细节文档，你的目录结构大致如下：\n\n```text\n.\n├── CLAUDE.md\n├── memory\n│ └── constitution.md\n├── scripts\n│ ├── check-prerequisites.sh\n│ ├── common.sh\n│ ├── create-new-feature.sh\n│ ├── setup-plan.sh\n│ └── update-claude-md.sh\n├── specs\n│ └── 001-create-taskify\n│ ├── contracts\n│ │ ├── api-spec.json\n│ │ └── signalr-spec.md\n│ ├── data-model.md\n│ ├── plan.md\n│ ├── quickstart.md\n│ ├── research.md\n│ └── spec.md\n└── templates\n ├── CLAUDE-template.md\n ├── plan-template.md\n ├── spec-template.md\n └── tasks-template.md\n```\n\n请检查 `research.md` 文档，确保根据你的指示选择了合适的技术栈。如果某些组件显得不合适，可以请 Claude Code 进行优化，甚至让它验证你本地安装的目标平台或框架版本（例如 .NET）。\n\n此外，如果你选择的技术栈变化较快（如 .NET Aspire 或 JavaScript 框架），还可以让 Claude Code 针对选定的技术栈进行更深入的研究，提示如下：\n\n```text\n我希望你仔细审查实施计划和详细文档，找出那些可能因 .NET Aspire 是快速变化的库而需要进一步研究的地方。对于这些需要额外研究的点，请在 `research.md` 中补充我们将在 Taskify 应用中使用的具体版本信息，并启动并行研究任务，通过网络资源进一步澄清相关细节。\n```\n\n在此过程中，你可能会发现 Claude Code 研究的方向有偏差——这时你可以通过以下提示引导它回到正轨：\n\n```text\n我认为我们需要将这个问题分解成一系列步骤。首先，列出你在实施过程中不确定或需要进一步研究的任务清单。然后针对每一项任务，单独启动一个研究任务，这样我们就能并行地研究所有具体的子问题。我注意到你目前是在泛泛地研究 .NET Aspire，但这对我们当前的需求帮助不大。这种研究过于宽泛，应该聚焦于解决特定的问题。\n```\n\n> [!注意]\n> Claude Code 可能会过于积极，添加一些你并未要求的内容。此时应请它说明更改的理由及来源。\n\n### **步骤 5：** 让 Claude Code 验证计划\n\n计划制定完成后，你应该让 Claude Code 对其进行全面检查，以确保没有遗漏任何环节。可以使用如下提示：\n\n```text\n现在请你审核一下实施计划和详细文档，仔细查看其中是否遗漏了显而易见的执行步骤。因为我不确定现有内容是否足够全面。例如，在核心实现部分，当逐步推进时，最好能够引用详细文档中的相应章节，以便获取所需信息。\n```\n\n这有助于完善实施计划，避免 Claude Code 在规划过程中遗漏潜在盲点。完成初步优化后，再让 Claude Code 再次对照检查清单，确认无误后再进入实施阶段。\n\n如果你已安装 [GitHub CLI](https:\u002F\u002Fdocs.github.com\u002Fen\u002Fgithub-cli\u002Fgithub-cli)，还可以让 Claude Code 直接从当前分支创建一个到 `main` 分支的拉取请求，并附上详细描述，以确保整个过程被妥善记录。\n\n> [!注意]\n> 在让代理开始实施之前，还应提醒 Claude Code 对细节进行交叉核对，看看是否存在过度设计的部分（记住，它有时会过于激进）。如果有此类情况，可要求 Claude Code 进行调整。务必确保 Claude Code 在制定计划时遵循基础文件 [constitution](base\u002Fmemory\u002Fconstitution.md) 的规定。\n\n### **步骤 6：** 使用 \u002Fspeckit.tasks 生成任务分解\n\n在实施计划得到验证后，你可以将其拆解为一系列按正确顺序执行的具体可操作任务。使用 `\u002Fspeckit.tasks` 命令，从你的实施计划中自动生成详细的任务分解：\n\n```text\n\u002Fspeckit.tasks\n```\n\n此步骤会在你的特性规范目录下生成一个 `tasks.md` 文件，其中包含：\n\n- **按用户故事组织的任务分解**——每个用户故事对应一个独立的实现阶段，包含一组具体任务。\n- **依赖关系管理**——任务按照组件间的依赖顺序排列（例如，先模型层，再服务层，最后是端点）。\n- **并行执行标记**——可并行执行的任务会标注 `[P]`，以优化开发流程。\n- **文件路径说明**——每项任务都明确指定了代码应编写的具体文件路径。\n- **测试驱动开发结构**——如果要求编写测试，则会包含测试任务，并安排在实现之前完成。\n- **检查点验证**——每个用户故事阶段都设有检查点，用于验证独立功能的正确性。\n\n生成的 `tasks.md` 提供了清晰的路线图，便于后续使用 `\u002Fspeckit.implement` 命令系统化地推进实施，从而保证代码质量，并支持用户故事的增量交付。\n\n### **步骤 7：** 实施\n\n准备就绪后，使用 `\u002Fspeckit.implement` 命令来执行你的实施计划：\n\n```text\n\u002Fspeckit.implement\n```\n\n`\u002Fspeckit.implement` 命令将：\n\n- 验证所有先决条件是否已就位（章程、规格说明、计划和任务）\n- 解析 `tasks.md` 中的任务分解\n- 按照正确的顺序执行任务，同时尊重依赖关系和并行执行标记\n- 遵循你在任务计划中定义的测试驱动开发方法\n- 提供进度更新并妥善处理错误\n\n> [!重要]\n> AI 代理将执行本地 CLI 命令（例如 `dotnet`、`npm` 等）——请确保你的机器上已安装所需的工具。\n\n实施完成后，请测试应用程序，并解决那些在 CLI 日志中可能看不到的运行时错误（例如浏览器控制台错误）。你可以将此类错误复制并粘贴回你的 AI 代理以获得解决。\n\n\u003C\u002Fdetails>\n\n---\n\n## 🔍 故障排除\n\n### Linux 上的 Git 凭证管理器\n\n如果你在 Linux 上遇到 Git 身份验证问题，可以安装 Git 凭证管理器：\n\n```bash\n#!\u002Fusr\u002Fbin\u002Fenv bash\nset -e\necho \"正在下载 Git 凭证管理器 v2.6.1...\"\nwget https:\u002F\u002Fgithub.com\u002Fgit-ecosystem\u002Fgit-credential-manager\u002Freleases\u002Fdownload\u002Fv2.6.1\u002Fgcm-linux_amd64.2.6.1.deb\necho \"正在安装 Git 凭证管理器...\"\nsudo dpkg -i gcm-linux_amd64.2.6.1.deb\necho \"配置 Git 使用 GCM...\"\ngit config --global credential.helper manager\necho \"清理中...\"\nrm gcm-linux_amd64.2.6.1.deb\n```\n\n## 💬 支持\n\n如需支持，请提交一个 [GitHub 问题](https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fissues\u002Fnew)。我们欢迎关于 Spec-Driven Development 的错误报告、功能请求以及相关问题。\n\n## 🙏 致谢\n\n该项目深受 [John Lam](https:\u002F\u002Fgithub.com\u002Fjflam) 的工作和研究的启发，并以此为基础。\n\n## 📄 许可证\n\n本项目根据 MIT 开源许可证条款进行许可。完整的条款请参阅 [LICENSE](.\u002FLICENSE) 文件。","# Spec Kit 快速上手指南\n\nSpec Kit 是一个开源工具包，旨在通过“规范驱动开发”（Spec-Driven Development）模式，帮助开发者专注于产品场景和预期结果，而非从零开始编写每一行代码。它将规范转化为可执行的指令，直接生成工作代码。\n\n## 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n* **操作系统**：Windows, macOS, 或 Linux\n* **核心依赖**：必须安装 [`uv`](https:\u002F\u002Fgithub.com\u002Fastral-sh\u002Fuv) 包管理器。Spec Kit 官方推荐使用 `uv` 进行安装和管理，以确保版本稳定性和隔离性。\n * 安装 uv (官方脚本):\n ```bash\n curl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\n # Windows PowerShell:\n powershell -c \"irm https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.ps1 | iex\"\n ```\n* **AI 编程助手**：需要在项目中配置并运行支持的 AI Agent（如 GitHub Copilot Workspace, Cursor, Codex CLI 等），因为 Spec Kit 主要通过 AI 助手的斜杠命令（Slash Commands）进行交互。\n\n> **注意**：PyPI 上同名包并非官方维护，请务必通过 GitHub 源安装。目前暂无官方提供的中国镜像源，若下载缓慢请自行配置网络加速。\n\n## 安装步骤\n\n推荐使用 **持久化安装** 方式，以便在任何项目中直接使用 `specify` 命令。\n\n### 1. 安装 Specify CLI\n\n使用 `uv` 从 GitHub 安装最新稳定版（请将 `vX.Y.Z` 替换为 [Releases](https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Freleases) 中的最新版本号，或直接使用下方命令安装主干版本）：\n\n```bash\n# 推荐：安装特定稳定版本 (替换 vX.Y.Z)\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z\n\n# 或者：安装最新主干版本 (可能包含未发布变更)\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git\n```\n\n### 2. 验证安装\n\n安装完成后，验证版本以确保成功：\n\n```bash\nspecify version\n```\n\n### 3. 升级工具\n\n如需升级到新版本，使用以下命令强制重新安装：\n\n```bash\nuv tool install specify-cli --force --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z\n```\n\n*(可选) 单次试用无需安装，可使用 `uvx` 运行：*\n```bash\nuvx --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@vX.Y.Z specify init \u003CPROJECT_NAME>\n```\n\n## 基本使用\n\nSpec Kit 的工作流主要在您的 AI 编程助手（如 Copilot, Cursor 等）中通过斜杠命令完成。\n\n### 第一步：初始化项目\n\n在终端中创建新项目或在现有项目中初始化：\n\n```bash\n# 创建新项目\nspecify init \u003CPROJECT_NAME>\n\n# 或在当前目录初始化 (指定 AI 助手，例如 copilot)\nspecify init . --ai copilot\n# 或者\nspecify init --here --ai copilot\n```\n\n### 第二步：在 AI 助手中建立规范\n\n打开项目目录，启动您的 AI 助手。根据您使用的工具，命令前缀可能是 `\u002Fspeckit.*` 或 `$speckit-*`。以下以 `\u002Fspeckit` 为例：\n\n1. **制定项目原则 (`\u002Fspeckit.constitution`)**\n 定义代码质量、测试标准和架构原则。\n ```text\n \u002Fspeckit.constitution Create principles focused on code quality, testing standards, user experience consistency, and performance requirements\n ```\n\n2. **创建业务规范 (`\u002Fspeckit.specify`)**\n 描述你要构建什么（关注 **做什么** 和 **为什么**，暂不涉及技术栈）。\n ```text\n \u002Fspeckit.specify Build an application that can help me organize my photos in separate photo albums. Albums are grouped by date and can be re-organized by dragging and dropping on the main page. Albums are never in other nested albums. Within each album, photos are previewed in a tile-like interface.\n ```\n\n3. **制定技术计划 (`\u002Fspeckit.plan`)**\n 指定技术栈和架构选择。\n ```text\n \u002Fspeckit.plan The application uses Vite with minimal number of libraries. Use vanilla HTML, CSS, and JavaScript as much as possible. Images are not uploaded anywhere and metadata is stored in a local SQLite database.\n ```\n\n4. **分解任务 (`\u002Fspeckit.tasks`)**\n 将计划转化为可执行的任务列表。\n ```text\n \u002Fspeckit.tasks\n ```\n\n5. **执行实现 (`\u002Fspeckit.implement`)**\n 让 AI 代理按照计划自动执行所有任务并生成代码。\n ```text\n \u002Fspeckit.implement\n ```\n\n完成上述步骤后，AI 将依据规范自动生成高质量代码。更多高级用法（如社区扩展、自定义预设）请参考官方文档。","某初创团队需要在两周内快速交付一个具备复杂业务逻辑的电商订单系统，且必须确保代码质量以应对高并发场景。\n\n### 没有 spec-kit 时\n- 开发人员陷入“凭感觉编码”（vibe coding）的陷阱，直接动手写代码而缺乏明确的可执行规范，导致后期返工频繁。\n- 需求文档与最终代码严重脱节，产品经理描述的场景无法直接转化为技术实现，沟通成本极高。\n- 每次修改需求都需人工梳理受影响模块，极易遗漏边界条件，引发难以追踪的生产环境 Bug。\n- 新成员加入项目时，面对零散的代码库难以快速理解核心业务逻辑，上手周期长达数周。\n- 测试阶段才发现大量逻辑漏洞，修复成本随开发进度呈指数级上升，交付风险不可控。\n\n### 使用 spec-kit 后\n- 团队优先定义可执行的规格说明书（Spec），spec-kit 直接基于规格生成高质量的基础代码骨架，杜绝盲目编码。\n- 产品场景被转化为预测性结果，规格即实现，确保了业务逻辑从设计到落地的精准一致性。\n- 需求变更只需更新规格文件，spec-kit 自动重新生成对应实现并标记差异，大幅降低人为疏漏风险。\n- 新成员通过阅读可执行的规格文档即可掌握系统全貌，结合生成的代码能快速定位逻辑，当天即可贡献代码。\n- 开发过程变为“规格驱动”，大部分逻辑错误在生成阶段即被规避，测试重点转向极端场景，交付信心显著提升。\n\nspec-kit 通过将规格说明书变为可执行的代码源头，让团队从繁琐的重复编码中解放出来，专注于构建高价值的产品场景。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fgithub_spec-kit_8e05e17e.jpg","github","GitHub","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fgithub_c56d6aba.png","How people build software.",null,"https:\u002F\u002Fgithub.com\u002Fabout","https:\u002F\u002Fgithub.com\u002Fgithub",[81,85,89],{"name":82,"color":83,"percentage":84},"Python","#3572A5",85.2,{"name":86,"color":87,"percentage":88},"Shell","#89e051",7.8,{"name":90,"color":91,"percentage":92},"PowerShell","#012456",7,88749,7634,"2026-04-17T09:48:14","MIT","Linux, macOS, Windows","未说明",{"notes":100,"python":101,"dependencies":102},"该工具是一个命令行套件 (CLI)，需配合 AI 编码助手（如 GitHub Copilot、Claude Code 等）使用。官方推荐使用 'uv' 工具进行安装和管理，不支持从 PyPI 安装。企业或无网环境需手动下载 wheel 包。无需本地 GPU 或大模型运行环境，计算依赖由集成的 AI 代理提供。","未说明 (通过 uv 工具链管理)",[103,104],"uv","specify-cli",[35,15,13,14],[107,108,109,110,111,112,113],"ai","copilot","development","engineering","prd","spec","spec-driven",23,"2026-03-27T02:49:30.150509","2026-04-18T00:45:43.425854",[118,123,128,133,138,143],{"id":119,"question_zh":120,"answer_zh":121,"source_url":122},38318,"遇到 'Unable to resolve chat model' 错误或 VS Code 中 Copilot 频繁报错怎么办？","尝试删除 GitHub Copilot 的配置文件（dotfiles）并重新登录。具体操作是找到并删除相关的 .github-copilot 或类似隐藏配置文件，然后重新进行身份验证登录，通常可以解决模型解析失败的问题。","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fissues\u002F1414",{"id":124,"question_zh":125,"answer_zh":126,"source_url":127},38319,"SpecKit 初始化后命令（Commands）不显示或无法使用如何解决？","这通常是因为安装配置错误，导致 AI 模型调用不匹配（例如使用了 Qwen 但系统试图调用 Claude）。解决方法是：删除所有相关的配置文件（如 .claude, .qwen, .specify 等），然后使用正确的 AI 模型名称重新运行初始化命令（init）。","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fissues\u002F202",{"id":129,"question_zh":130,"answer_zh":131,"source_url":132},38320,"为什么 SpecKit 生成的代码过多、忽略项目结构或产生过度设计？","这是因为 LLM 具有不确定性且缺乏完整的项目上下文。建议不要将规划完全交给 AI，而是由开发者将任务拆分为原子级的步骤，手动制定计划，然后让 LLM 逐个实现这些具体步骤。对于复杂任务，可以使用其他工具的“计划模式”（Plan Mode）辅助，但核心逻辑和上下文需由人工把控。","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fissues\u002F75",{"id":134,"question_zh":135,"answer_zh":136,"source_url":137},38321,"运行 SpecKit 初始化命令时出现错误或命令过时怎么办？","请确保使用 README 中最新的命令格式。旧的命令可能已失效，推荐使用以下最新命令进行初始化：`uvx --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit specify init --here`。如果仍然报错，请检查网络连接及 uvx 工具版本。","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fissues\u002F9",{"id":139,"question_zh":140,"answer_zh":141,"source_url":142},38322,"如何在多终端并行运行 SpecKit Agent 而不发生 Git 冲突或文件损坏？","目前社区已通过扩展支持基于 Git Worktree 的隔离模式。你可以寻找相关的社区扩展（如 PR #2207 提到的功能），它能为每个任务创建临时的 Git Worktree，在隔离目录中执行计划，完成后自动清理，从而避免多个 Agent 同时操作同一仓库导致的竞争条件。","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fissues\u002F1476",{"id":144,"question_zh":145,"answer_zh":146,"source_url":147},38323,"在 Codex CLI 中运行 `specify init` 后生成的 markdown 文件为何不可见？","SpecKit 生成的规范文件可能被放置在了特定目录（如 .codex）中，而 Codex CLI 默认未配置读取该路径。请检查生成文件的实际路径，并确保你的 Codex CLI 配置指向了包含这些 .md 文件的目录，或者将文件移动到 Codex CLI 默认识别的项目根目录或指定配置文件夹中。","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit\u002Fissues\u002F1866",[149,154,159,164,169,174,179,184,189,194,199,204,209,214,219,224,229,234,239,244],{"id":150,"version":151,"summary_zh":152,"released_at":153},306467,"v0.7.2","## 安装\n\n```bash\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@v0.7.2\nspecify init my-project\n```\n\n## 变更内容\n\n- chore: 版本升级至 0.7.2\n- docs: 添加核心命令参考，并简化 README 中的 CLI 部分 (#2245)\n- docs: 添加工作流参考，重新组织为 `docs\u002Freference\u002F` 目录结构，并添加 `--version` 标志 (#2244)\n- docs: 添加预设参考页面，并将 `pack_id` 重命名为 `preset_id` (#2243)\n- docs: 添加扩展参考页面和集成常见问题解答 (#2242)\n- docs: 将集成文档整合到 `docs\u002Fintegrations.md` 文件中 (#2241)\n- feat: 将 memorylint 和 superpowers-bridge 的版本更新至 1.3.0，并提供新的下载地址 (#2240)\n- feat: 集成目录 — 发现、版本管理和社区分发 (#2130)\n- 将 Catalog CI 扩展添加到社区目录 (#2239)\n- 添加了 issues 扩展 (#2194)\n- chore: 发布 0.7.1，开始 0.7.2.dev0 开发 (#2235)\n","2026-04-16T18:56:34",{"id":155,"version":156,"summary_zh":157,"released_at":158},306468,"v0.7.1","## 安装\n\n```bash\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@v0.7.1\nspecify init my-project\n```\n\n## 变更内容\n\n- chore: 版本升级至 0.7.1\n- ci: 在测试矩阵中添加 windows-latest (#2233)\n- docs: 从本地开发指南中移除已弃用的 --skip-tls 引用 (#2231)\n- fix: 允许 Claude 将技能串联起来以执行钩子 (#2227)\n- docs: 将 TESTING.md 合并到 CONTRIBUTING.md 中，并移除 TESTING.md (#2228)\n- 将 agent-assign 扩展添加到社区目录 (#2030)\n- fix: 修复非官方 PyPI 警告 (#1982) 和旧版扩展命令名称的自动修正 (#2017) (#2027)\n- feat: 在社区目录中注册 architect-preview (#2214)\n- chore: 在 specify init 命令中弃用 --ai 标志，改用 --integration (#2218)\n- chore: 发布 0.7.0 版本，开始 0.7.1.dev0 的开发 (#2217)\n","2026-04-15T20:38:56",{"id":160,"version":161,"summary_zh":162,"released_at":163},306469,"v0.7.0","## 安装\n\n```bash\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@v0.7.0\nspecify init my-project\n```\n\n## 变更内容\n\n- chore: 版本升级至 0.7.0\n- 添加带有目录系统的工作流引擎 (#2158)\n- docs(catalog): 将 claude-ask-questions 添加到社区预设目录 (#2191)\n- 添加 SFSpeckit — Salesforce SDD 扩展 (#2208)\n- feat(scripts): 为 gitflow 提供可选的单段分支前缀 (#2202)\n- chore: 发布 0.6.2，开始 0.6.3.dev0 的开发 (#2205)\n- 将 Worktrees 扩展添加到社区目录 (#2207)\n- feat: 更新 catalog.community.json，用于预设小说写作 (#2199)\n","2026-04-14T18:04:39",{"id":165,"version":166,"summary_zh":167,"released_at":168},306470,"v0.6.2","## 安装\n\n```bash\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@v0.6.2\nspecify init my-project\n```\n\n## 变更内容\n\n- chore: 版本升级至 0.6.2\n- feat: 注册“假设分析”社区扩展 (#2182)\n- feat: 将 GitHub Issues 集成添加到社区目录 (#2188)\n- feat(agents): 添加对 Goose AI 代理的支持 (#2015)\n- 更新社区目录中的 ralph 扩展至 v1.0.1 (#2192)\n- fix: 在分支上跳过文档部署工作流 (#2171)\n- chore: 发布 0.6.1，开始 0.6.2.dev0 开发 (#2162)\n","2026-04-13T17:51:11",{"id":170,"version":171,"summary_zh":172,"released_at":173},306471,"v0.6.1","## 安装\n\n```bash\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@v0.6.1\nspecify init my-project\n```\n\n## 变更内容\n\n- chore: 版本升级至 0.6.1\n- feat: 添加包含最少工作流命令的精简预设 (#2161)\n- 将 Brownfield Bootstrap 扩展加入社区目录 (#2145)\n- 将 CI Guard 扩展加入社区目录 (#2157)\n- 将 SpecTest 扩展加入社区目录 (#2159)\n- fix: 打包的扩展不应包含下载 URL (#2155)\n- 将 PR Bridge 扩展加入社区目录 (#2148)\n- feat(cursor-agent): 从 .cursor\u002Fcommands 迁移到 .cursor\u002Fskills (#2156)\n- 将 TinySpec 扩展加入社区目录 (#2147)\n- chore: 将 spec-kit-verify 升级至 1.0.3，将 spec-kit-review 升级至 1.0.1 (#2146)\n- 将 Status Report 扩展加入社区目录 (#2123)\n- chore: 发布 0.6.0，开始 0.6.1.dev0 的开发 (#2144)\n","2026-04-10T21:19:38",{"id":175,"version":176,"summary_zh":177,"released_at":178},306472,"v0.6.0","## 安装\n\n```bash\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@v0.6.0\nspecify init my-project\n```\n\n## 变更内容\n\n- chore: 版本升级至 0.6.0\n- 将 Bugfix Workflow 社区扩展添加到目录和 README 中 (#2135)\n- 将 Worktree Isolation 扩展添加到社区目录中 (#2143)\n- 将多仓库分支预设添加到社区目录中 (#2139)\n- 改善 README 的清晰度 (#2013)\n- 重写 AGENTS.md 文件，以适应集成架构 (#2119)\n- docs: 将 SpecKit Companion 添加到社区伙伴部分 (#2140)\n- feat: 将 memorylint 扩展添加到社区目录中 (#2138)\n- chore: 发布 0.5.1 版本，并开始 0.5.2.dev0 开发 (#2137)\n","2026-04-09T19:15:10",{"id":180,"version":181,"summary_zh":182,"released_at":183},306473,"v0.5.1","## 安装\n\n```bash\nuv 工具安装 specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@v0.5.1\nspecify init my-project\n```\n\n## 变更内容\n\n- chore: 版本升级至 0.5.1\n- fix: 锁定 typer≥0.24.0 和 click≥8.2.1，以修复导入崩溃问题 (#2136)\n- feat: 将 fleet 扩展更新至 v1.1.0 (#2029)\n- fix(forge): 在 frontmatter 的 name 字段中使用连字符表示法 (#2075)\n- fix(bash): 修复 update-agent-context.sh 中的 sed 替换转义、BSD 兼容性及冗余代码清理问题 (#2090)\n- 将 Spec Diagram 社区扩展添加到目录和 README 中 (#2129)\n- feat: Git 扩展第二阶段 — 增加 GIT_BRANCH_NAME 覆盖、对现有目录使用 --force 选项，以及自动安装测试 (#1940) (#2117)\n- fix(git): 展示现有分支的检出错误 (#2122)\n- 将 Branch Convention 社区扩展添加到目录和 README 中 (#2128)\n- docs: 简化 2026 年 3 月的通讯，提升可读性 (#2127)\n- fix: 恢复社区扩展的别名兼容性 (#2110) (#2125)\n- 新增 2026 年 3 月的通讯 (#2124)\n- 将 Spec Refine 社区扩展添加到目录和 README 中 (#2118)\n- 将 explicit-task-dependencies 社区预设添加到目录和 README 中 (#2091)\n- 将 toc-navigation 社区预设添加到目录和 README 中 (#2080)\n- fix: 防止正文以 `\"` 结尾时 TOML 关闭引号出现歧义 (#2113) (#2115)\n- 修复 trae 的 speckit 问题 (#2112)\n- feat: Git 扩展第一阶段 — 将 `extensions\u002Fgit` 打包，并在所有核心命令上添加钩子 (#1941)\n- 将 confluence 扩展升级至 v1.1.1 (#2109)\n- 将 V-Model Extension Pack 更新至 v0.5.0 (#2108)\n- 添加 canon 扩展及 canon-core 预设。(#2022)\n- [stage2] fix: 在旧版 TOML 渲染器中序列化多行描述 (#2097)\n- [stage1] fix: 从 TOML 集成提示中移除 YAML frontmatter (#2096)\n- 添加 Confluence 扩展 (#2028)\n- fix: 在测试和文档中接受 4 位及以上规格编号 (#2094)\n- fix(scripts): 改进 Git 分支创建的错误处理 (#2089)\n- 将 optimize 扩展添加到社区目录中 (#2088)\n- feat: 添加“VS Code 提问”预设 (#2086)\n- 将 security-review v1.1.1 添加到社区扩展目录中 (#2073)\n- 添加 `specify integration` 子命令，用于初始化后的集成管理 (#2083)\n- 从 CLI 中移除模板版本信息，修复 Claude 用户可调用功能，并清理无用代码 (#2081)\n- fix: 在技能的 frontmatter 中添加 user-invocable: true (#2077)\n- fix: 为 stale 工作流添加 actions:write 权限 (#2079)\n- feat: 为 Claude Code 命令添加 argument-hint frontmatter (#1951) (#2059)\n- 将 conduct 扩展更新至 v1.0.1 (#2078)\n- chore(deps): 将 astral-sh\u002Fsetup-uv 从 7.6.0 升级至 8.0.0 (#2072)\n- chore(deps): 将 actions\u002Fconfigure-pages 从 5 升级至 6 (#2071)\n- feat: 将 spec-kit-fixit 扩展添加到社区目录中 (#2024)\n- chore: 发布 0.5.0，开始 0.5.1.dev0 的开发 (#2070)\n- feat: 添加 Forgecode 代理支持 (#2034)\n","2026-04-08T22:50:24",{"id":185,"version":186,"summary_zh":187,"released_at":188},306474,"v0.5.0","## 安装\n\n```bash\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@v0.5.0\nspecify init my-project\n```\n\n## 变更内容\n\n- chore: 版本升级至 0.5.0\n- 引入 DEVELOPMENT.md (#2069)\n- 将社区伙伴中的 cc-sdd 引用更新为 cc-spex (#2007)\n- chore: 发布 0.4.5，开始 0.4.6.dev0 开发 (#2064)\n","2026-04-02T20:55:37",{"id":190,"version":191,"summary_zh":192,"released_at":193},306475,"v0.4.5","## 安装\n\n```bash\nuv tool install specify-cli --from git+https:\u002F\u002Fgithub.com\u002Fgithub\u002Fspec-kit.git@v0.4.5\nspecify init my-project\n```\n\n## 变更内容\n\n- chore: 版本升级至 0.4.5\n- 第6阶段：完成迁移——移除旧版脚手架路径 (#1924) (#2063)\n- 将 Claude Code 作为原生技能安装，并对预设\u002F集成流程进行调整 (#2051)\n- 添加 repoindex 0402 (#2062)\n- 第5阶段：技能、通用及选项驱动的集成 (#1924) (#2052)\n- feat(scripts): 为 create-new-feature 添加 --dry-run 标志 (#1998)\n- fix: 支持特征分支号为 4 位及以上数字 (#2040)\n- 添加社区内容免责声明 (#2058)\n- docs: 在 README 和扩展文档中添加社区扩展网站链接 (#2014)\n- docs: 移除已失效的 Cognitive Squad 和 Understanding 扩展链接，并从 extensions\u002Fcatalog.community.json 中删除这些链接 (#2057)\n- 将 fix-findings 扩展加入社区目录 (#2039)\n- 第4阶段：TOML 集成——Gemini 和 Tabnine 已迁移到插件架构 (#2050)\n- feat: 向社区目录添加 5 个生命周期扩展 (#2049)\n- 第3阶段：标准 Markdown 集成——19 个代理已迁移到插件架构 (#2038)\n- chore: 发布 0.4.4，开始 0.4.5.dev0 开发 (#2048)\n","2026-04-02T17:35:44",{"id":195,"version":196,"summary_zh":197,"released_at":198},306476,"v0.4.4","这是您可以与您选择的代理一起使用的最新版本集。我们建议使用 Specify CLI 来搭建您的项目脚手架，不过您也可以单独下载这些组件并自行管理。\n\n## 更改日志\n\n- chore: 将版本号升级至 0.4.4\n- 阶段 2：Copilot 集成 — 共享模板基元的概念验证 (#2035)\n- docs: 将 AGENTS.md 与 AGENT_CONFIG 同步，以补全缺失的代理信息 (#2025)\n- docs: 确保手动测试使用本地 Specify (#2020)\n- 阶段 1：集成基础 — 基类、清单系统和注册表 (#1925)\n- fix: 加强 GitHub Actions 工作流的安全性 (#2021)\n- chore: 在发布后于 main 分支上使用 PEP 440 .dev0 版本 (#2032)\n- feat: 将 Superpowers 桥接扩展添加到社区目录 (#2023)\n- feat: 将 product-forge 扩展添加到社区目录 (#2012)\n- feat(scripts): 为 create-new-feature 添加 --allow-existing-branch 标志 (#1999)\n- fix(scripts): 为 copilot-instructions.md 添加正确的路径 (#1997)\n- 更新 README.md (#1995)\n- fix: 防止扩展命令被覆盖 (#1994)\n- 修复 Claude Code CLI 在 npm 本地安装中的检测问题 (#1978)\n- fix(scripts): 尊重 PowerShell 代理和脚本过滤器 (#1969)\n- feat: 将 MAQA 扩展套件（共 7 个扩展）添加到社区目录 (#1981)\n- feat: 将 spec-kit-onboard 扩展添加到社区目录 (#1991)\n- 将 plan-review-gate 添加到社区目录 (#1993)\n- chore(deps): 将 actions\u002Fdeploy-pages 从 4 升级至 5 (#1990)\n- chore(deps): 将 DavidAnson\u002Fmarkdownlint-cli2-action 从 19 升级至 23 (#1989)","2026-04-01T13:57:37",{"id":200,"version":201,"summary_zh":202,"released_at":203},306477,"v0.4.3","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\r\n\r\n## Changelog\r\n\r\n- chore: bump version to 0.4.3\r\n- Unify Kimi\u002FCodex skill naming and migrate legacy dotted Kimi dirs (#1971)\r\n- fix(ps1): replace null-conditional operator for PowerShell 5.1 compatibility (#1975)\r\n","2026-03-26T21:00:15",{"id":205,"version":206,"summary_zh":207,"released_at":208},306478,"v0.4.2","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\n\n## Changelog\n\n- chore: bump version to 0.4.2\n- feat: Auto-register ai-skills for extensions whenever applicable (#1840)\n- docs: add manual testing guide for slash command validation (#1955)\n- Add AIDE, Extensify, and Presetify to community extensions (#1961)\n- docs: add community presets section to main README (#1960)\n- docs: move community extensions table to main README for discoverability (#1959)\n- docs(readme): consolidate Community Friends sections and fix ToC anchors (#1958)\n- fix(commands): rename NFR references to success criteria in analyze and clarify (#1935)\n- Add Community Friends section to README (#1956)\n- docs: add Community Friends section with Spec Kit Assistant VS Code extension (#1944)\n- chore: bump version to 0.4.1 (#1953)\n- Add checkpoint extension (#1947)\n- fix(scripts): prioritize .specify over git for repo root detection (#1933)\n- docs: add AIDE extension demo to community projects (#1943)\n- fix(templates): add missing Assumptions section to spec template (#1939)\n- chore: bump version to 0.4.0 (#1937)\n- fix(cli): add allow_unicode=True and encoding=\"utf-8\" to YAML I\u002FO (#1936)\n- fix(codex): native skills fallback refresh + legacy prompt suppression (#1930)\n- feat(cli): embed core pack in wheel for offline\u002Fair-gapped deployment (#1803)\n- ci: increase stale workflow operations-per-run to 250 (#1922)\n- docs: update publishing guide with Category and Effect columns (#1913)\n- fix: Align native skills frontmatter with install_ai_skills (#1920)\n- feat: add timestamp-based branch naming option for `specify init` (#1911)\n- docs: add Extension Comparison Guide for community extensions (#1897)\n- docs: update SUPPORT.md, fix issue templates, add preset submission template (#1910)\n- Add support for Junie (#1831)\n- feat: migrate Codex\u002Fagy init to native skills workflow (#1906)\n- chore: bump version to 0.3.2 (#1909)\n- Add conduct extension to community catalog (#1908)\n- feat(extensions): add verify-tasks extension to community catalog (#1871)\n- feat(presets): add enable\u002Fdisable toggle and update semantics (#1891)\n- feat: add iFlow CLI support (#1875)\n- feat(commands): wire before\u002Fafter hook events into specify and plan templates (#1886)\n- docs(catalog): add speckit-utils to community catalog (#1896)\n- docs: Add Extensions & Presets section to README (#1898)\n- chore: update DocGuard extension to v0.9.11 (#1899)\n- Update cognitive-squad catalog entry — Triadic Model, full lifecycle (#1884)\n- feat: register spec-kit-iterate extension (#1887)\n- fix(scripts): add explicit positional binding to PowerShell create-new-feature params (#1885)\n- fix(scripts): encode residual JSON control chars as \\uXXXX instead of stripping (#1872)\n- chore: update DocGuard extension to v0.9.10 (#1890)\n- Feature\u002Fspec kit add pi coding agent pullrequest (#1853)\n- feat: register spec-kit-learn extension (#1883)\n- chore: bump version to 0.3.1 (#1880)\n- docs: add greenfield Spring Boot pirate-speak preset demo to README (#1878)\n- fix(ai-skills): exclude non-speckit copilot agent markdown from skill… (#1867)\n- feat: add Trae IDE support as a new agent (#1817)\n- feat(cli): polite deep merge for settings.json and support JSONC (#1874)\n- feat(extensions,presets): add priority-based resolution ordering (#1855)\n- fix(scripts): suppress stdout from git fetch in create-new-feature.sh (#1876)\n- fix(scripts): harden bash scripts — escape, compat, and error handling (#1869)\n- Add cognitive-squad to community extension catalog (#1870)\n- docs: add Go \u002F React brownfield walkthrough to community walkthroughs (#1868)\n- chore: update DocGuard extension to v0.9.8 (#1859)\n- Feature: add specify status command (#1837)\n- fix(extensions): show extension ID in list output (#1843)\n- feat(extensions): add Archive and Reconcile extensions to community catalog (#1844)\n- feat: Add DocGuard CDD enforcement extension to community catalog (#1838)\n- chore: bump version to 0.3.0 (#1839)\n- feat(presets): Pluggable preset system with catalog, resolver, and skills propagation (#1787)\n- fix: match 'Last updated' timestamp with or without bold markers (#1836)\n- Add specify doctor command for project health diagnostics (#1828)\n- fix: harden bash scripts against shell injection and improve robustness (#1809)\n- fix: clean up command templates (specify, analyze) (#1810)\n- fix: migrate Qwen Code CLI from TOML to Markdown format (#1589) (#1730)\n- fix(cli): deprecate explicit command support for agy (#1798) (#1808)\n- Add \u002Fselftest.extension core extension to test other extensions (#1758)\n- feat(extensions): Quality of life improvements for RFC-aligned catalog integration (#1776)\n- Add Java brownfield walkthrough to community walkthroughs (#1820)\n- chore: bump version to 0.2.1 (#1813)\n- Added February 2026 newsletter (#1812)\n- feat: add Kimi Code CLI agent support (#1","2026-03-25T15:50:10",{"id":210,"version":211,"summary_zh":212,"released_at":213},306479,"v0.4.1","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\r\n\r\n## Changelog\r\n\r\n- chore: bump version to 0.4.1\r\n- Add checkpoint extension (#1947)\r\n- fix(scripts): prioritize .specify over git for repo root detection (#1933)\r\n- docs: add AIDE extension demo to community projects (#1943)\r\n- fix(templates): add missing Assumptions section to spec template (#1939)\r\n","2026-03-24T14:24:39",{"id":215,"version":216,"summary_zh":217,"released_at":218},306480,"v0.4.0","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\r\n\r\n## Changelog\r\n\r\n- chore: bump version to 0.4.0\r\n- fix(cli): add allow_unicode=True and encoding=\"utf-8\" to YAML I\u002FO (#1936)\r\n- fix(codex): native skills fallback refresh + legacy prompt suppression (#1930)\r\n- feat(cli): embed core pack in wheel for offline\u002Fair-gapped deployment (#1803)\r\n- ci: increase stale workflow operations-per-run to 250 (#1922)\r\n- docs: update publishing guide with Category and Effect columns (#1913)\r\n- fix: Align native skills frontmatter with install_ai_skills (#1920)\r\n- feat: add timestamp-based branch naming option for `specify init` (#1911)\r\n- docs: add Extension Comparison Guide for community extensions (#1897)\r\n- docs: update SUPPORT.md, fix issue templates, add preset submission template (#1910)\r\n- Add support for Junie (#1831)\r\n- feat: migrate Codex\u002Fagy init to native skills workflow (#1906)\r\n","2026-03-23T14:26:14",{"id":220,"version":221,"summary_zh":222,"released_at":223},306481,"v0.3.2","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\r\n\r\n## Changelog\r\n\r\n- chore: bump version to 0.3.2\r\n- Add conduct extension to community catalog (#1908)\r\n- feat(extensions): add verify-tasks extension to community catalog (#1871)\r\n- feat(presets): add enable\u002Fdisable toggle and update semantics (#1891)\r\n- feat: add iFlow CLI support (#1875)\r\n- feat(commands): wire before\u002Fafter hook events into specify and plan templates (#1886)\r\n- docs(catalog): add speckit-utils to community catalog (#1896)\r\n- docs: Add Extensions & Presets section to README (#1898)\r\n- chore: update DocGuard extension to v0.9.11 (#1899)\r\n- Update cognitive-squad catalog entry — Triadic Model, full lifecycle (#1884)\r\n- feat: register spec-kit-iterate extension (#1887)\r\n- fix(scripts): add explicit positional binding to PowerShell create-new-feature params (#1885)\r\n- fix(scripts): encode residual JSON control chars as \\uXXXX instead of stripping (#1872)\r\n- chore: update DocGuard extension to v0.9.10 (#1890)\r\n- Feature\u002Fspec kit add pi coding agent pullrequest (#1853)\r\n- feat: register spec-kit-learn extension (#1883)\r\n\r\n\r\n","2026-03-19T13:24:38",{"id":225,"version":226,"summary_zh":227,"released_at":228},306482,"v0.3.1","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\r\n\r\n## Changelog\r\n\r\n- chore: bump version to 0.3.1\r\n- docs: add greenfield Spring Boot pirate-speak preset demo to README (#1878)\r\n- fix(ai-skills): exclude non-speckit copilot agent markdown from skill… (#1867)\r\n- feat: add Trae IDE support as a new agent (#1817)\r\n- feat(cli): polite deep merge for settings.json and support JSONC (#1874)\r\n- feat(extensions,presets): add priority-based resolution ordering (#1855)\r\n- fix(scripts): suppress stdout from git fetch in create-new-feature.sh (#1876)\r\n- fix(scripts): harden bash scripts — escape, compat, and error handling (#1869)\r\n- Add cognitive-squad to community extension catalog (#1870)\r\n- docs: add Go \u002F React brownfield walkthrough to community walkthroughs (#1868)\r\n- chore: update DocGuard extension to v0.9.8 (#1859)\r\n- Feature: add specify status command (#1837)\r\n- fix(extensions): show extension ID in list output (#1843)\r\n- feat(extensions): add Archive and Reconcile extensions to community catalog (#1844)\r\n- feat: Add DocGuard CDD enforcement extension to community catalog (#1838)\r\n","2026-03-17T16:30:38",{"id":230,"version":231,"summary_zh":232,"released_at":233},306483,"v0.3.0","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\r\n\r\n## Changelog\r\n\r\n- chore: bump version to 0.3.0\r\n- feat(presets): Pluggable preset system with catalog, resolver, and skills propagation (#1787)\r\n- fix: match 'Last updated' timestamp with or without bold markers (#1836)\r\n- Add specify doctor command for project health diagnostics (#1828)\r\n- fix: harden bash scripts against shell injection and improve robustness (#1809)\r\n- fix: clean up command templates (specify, analyze) (#1810)\r\n- fix: migrate Qwen Code CLI from TOML to Markdown format (#1589) (#1730)\r\n- fix(cli): deprecate explicit command support for agy (#1798) (#1808)\r\n- Add \u002Fselftest.extension core extension to test other extensions (#1758)\r\n- feat(extensions): Quality of life improvements for RFC-aligned catalog integration (#1776)\r\n- Add Java brownfield walkthrough to community walkthroughs (#1820)\r\n\r\n","2026-03-13T20:12:26",{"id":235,"version":236,"summary_zh":237,"released_at":238},306484,"v0.2.1","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\r\n\r\n## Changelog\r\n\r\n- chore: bump version to 0.2.1\r\n- Added February 2026 newsletter (#1812)\r\n- feat: add Kimi Code CLI agent support (#1790)\r\n- docs: fix broken links in quickstart guide (#1759) (#1797)\r\n- docs: add catalog cli help documentation (#1793) (#1794)\r\n- fix: use quiet checkout to avoid exception on git checkout (#1792)\r\n- feat(extensions): support .extensionignore to exclude files during install (#1781)\r\n- feat: add Codex support for extension command registration (#1767)\r\n","2026-03-11T22:14:40",{"id":240,"version":241,"summary_zh":242,"released_at":243},306485,"v0.2.0","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\r\n\r\n## Changelog\r\n\r\n- chore: bump version to 0.2.0\r\n- fix: sync agent list comments with actual supported agents (#1785)\r\n- feat(extensions): support multiple active catalogs simultaneously (#1720)\r\n- Pavel\u002Fadd tabnine cli support (#1503)\r\n- Add Understanding extension to community catalog (#1778)\r\n- Add ralph extension to community catalog (#1780)\r\n- Update README with project initialization instructions (#1772)\r\n- feat: add review extension to community catalog (#1775)\r\n- Add fleet extension to community catalog (#1771)\r\n- Integration of Mistral vibe support into speckit (#1725)\r\n- fix: Remove duplicate options in specify.md (#1765)\r\n- fix: use global branch numbering instead of per-short-name detection (#1757)\r\n- Add Community Walkthroughs section to README (#1766)\r\n- feat(extensions): add Jira Integration to community catalog (#1764)\r\n- Add Azure DevOps Integration extension to community catalog (#1734)\r\n- Fix docs: update Antigravity link and add initialization example (#1748)\r\n- fix: wire after_tasks and after_implement hook events into command templates (#1702)\r\n- make c ignores consistent with c++ (#1747)\r\n","2026-03-09T19:43:30",{"id":245,"version":246,"summary_zh":247,"released_at":248},306486,"v0.1.13","This is the latest set of releases that you can use with your agent of choice. We recommend using the Specify CLI to scaffold your projects, however you can download these independently and manage them yourself.\r\n\r\n## Changelog\r\n\r\n- chore: bump version to 0.1.13\r\n- feat: add kiro-cli and AGENT_CONFIG consistency coverage (#1690)\r\n- feat: add verify extension to community catalog (#1726)\r\n- Add Retrospective Extension to community catalog README table (#1741)\r\n- fix(scripts): add empty description validation and branch checkout error handling (#1559)\r\n- fix: correct Copilot extension command registration (#1724)\r\n- fix(implement): remove Makefile from C ignore patterns (#1558)\r\n- Add sync extension to community catalog (#1728)\r\n- fix(checklist): clarify file handling behavior for append vs create (#1556)\r\n- fix(clarify): correct conflicting question limit from 10 to 5 (#1557)\r\n","2026-03-03T22:07:08"]