经 AI Skill Hub 精选评估,spec-kit AI技能包 获评「强烈推荐」。在 GitHub 上收获超过 97.4k 颗 Star,这款AI工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.2 分,适合有一定技术背景的用户使用。
spec-kit AI技能包 是一款基于 Python 开发的开源工具,专注于 规格驱动开发、AI助手、代码生成 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
spec-kit AI技能包 是一款基于 Python 开发的开源工具,专注于 规格驱动开发、AI助手、代码生成 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:pip 安装(推荐)
pip install spec-kit
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install spec-kit
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/github/spec-kit
cd spec-kit
pip install -e .
# 验证安装
python -c "import spec_kit; print('安装成功')"
# 命令行使用
spec-kit --help
# 基本用法
spec-kit input_file -o output_file
# Python 代码中调用
import spec_kit
# 示例
result = spec_kit.process("input")
print(result)
# spec-kit 配置文件示例(config.yml) app: name: "spec-kit" debug: false log_level: "INFO" # 运行时指定配置文件 spec-kit --config config.yml # 或通过环境变量配置 export SPEC_KIT_API_KEY="your-key" export SPEC_KIT_OUTPUT_DIR="./output"
<p align="center"> <strong>An open source toolkit for building high-quality software with any AI coding agent — a ready-to-use spec-driven process (or bring your own), endlessly extensible, community-driven, and built for your whole organization.</strong> </p>
<p align="center"> <a href="https://github.com/github/spec-kit/releases/latest"><img src="https://img.shields.io/github/v/release/github/spec-kit" alt="Latest Release"/></a> <a href="https://github.com/github/spec-kit/stargazers"><img src="https://img.shields.io/github/stars/github/spec-kit?style=social" alt="GitHub stars"/></a> <a href="https://github.com/github/spec-kit/blob/main/LICENSE"><img src="https://img.shields.io/github/license/github/spec-kit" alt="License"/></a> <a href="https://github.github.io/spec-kit/"><img src="https://img.shields.io/badge/docs-GitHub_Pages-blue" alt="Documentation"/></a> </p>
<p align="center"> <strong>English</strong> · <a href="./README.zh-CN.md">简体中文</a> </p>
[!NOTE] One year of Spec Kit — and 1.0.0 One year after the first commit, Spec Kit has reached 1.0.0 — not because the work is finished or its shape is frozen, but because the project has grown into something coherent, useful, and shaped by far more people than those who started it. The lead maintainer's personal anniversary post, Spec Kit Turns One — and Ships 1.0.0, defines what 1.0.0 actually means for the project: it is now just a number. As agents make adapting to change dramatically cheaper, the value moves from stability to adaptability. To everyone who has used Spec Kit, challenged its assumptions, reported a problem, contributed code or documentation, created an extension or preset, shared an idea, or helped someone else get started: thank you. This milestone belongs to the community that carried the project through its first year and continues to shape where it goes next.
---
Want to see Spec Kit in action? Watch our video overview!
Use 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.
```bash
If you encounter issues with an agent, please open an issue so we can refine the integration.
Requires uv (install uv). Replace vX.Y.Z with the latest release tag from Releases — keep the leading v (for example, v0.12.11, not 0.12.11):
uv tool install specify-cli --from git+https://github.com/github/spec-kit.git@vX.Y.Z
Prefer installing from PyPI? The specify-cli package is also published there:
uv tool install specify-cli
See the Installation Guide for alternative methods, verification, upgrade, and troubleshooting.
specify extension add <extension-name> ```
For example, extensions could add Jira integration, post-implementation code review, V-Model test traceability, or project health diagnostics.
See the Extensions reference for the full command guide. Browse the community extensions for what's available.
specify preset add <preset-name> ```
For 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 shows just how deep the customization can go. Multiple presets can be stacked with priority ordering.
See the Presets reference for the full command guide, including resolution order and priority stacking.
Extensions and presets are individual building blocks. A bundle packages a curated set of them — extensions, presets, steps, and workflows — into a single, versioned, role-oriented setup so a whole team persona (product manager, business analyst, security researcher, developer, …) can be provisioned with one command.
A bundle is described by a hand-written bundle.yml manifest. It pins each component to a version and, optionally, targets a specific integration; a bundle with no integration is agnostic and inherits whatever integration the project already uses.
```bash
specify bundle info <bundle-id>
specify bundle install <bundle-id>
specify bundle list specify bundle update <bundle-id> # or --all specify bundle remove <bundle-id> # removes only this bundle's components
Bundles resolve from a **priority-ordered catalog stack** (project > user >
built-in). Each source carries an install policy: `install-allowed` sources can
be installed from, while `discovery-only` sources are visible in `search`/`info`
but refuse installation. Manage the stack with `specify bundle catalog list|add|remove`.
Authors validate and package bundles locally. Distribution is hosting the built
artifact and adding a catalog source; community bundle submissions use the
[Bundle Submission](https://github.com/github/spec-kit/issues/new?template=bundle_submission.yml)
issue template so required component catalogs and install evidence can be reviewed:
bash specify bundle validate --path ./my-bundle # structural + reference checks specify bundle build --path ./my-bundle # produce a versioned .zip artifact ```
Four ready-to-read example bundle manifests live under examples/bundles/ (product manager, business analyst, security researcher, developer). These are bundle packaging examples, not filled generated feature specs; for end-to-end community examples, see the community walkthroughs.
Key guarantees: info shows exactly what install adds (transparency); installs are idempotent and confined to the project root; remove never touches components another installed bundle still needs; and all consume/author commands work offline against local or pinned sources.
Replace vX.Y.Z with the latest release tag, keeping the leading v.
uv tool install specify-cli --from git+https://github.com/github/spec-kit.git@vX.Y.Z
specify init my-project --integration copilot
cd my-project
Launch your coding agent in the project directory, then:
/speckit-constitution). This is a one-time step per project./speckit-specify)./speckit-plan)./speckit-tasks)./speckit-implement)./speckit-converge).[!NOTE] Repeat steps 4 and 5 until /speckit-converge reports Converged.
Replace vX.Y.Z with the latest release tag, keeping the leading v.
uv tool install specify-cli --from git+https://github.com/github/spec-kit.git@vX.Y.Z
specify init my-project --integration copilot
cd my-project
specify extension add bug
Launch your coding agent in the project directory, then:
/speckit-bug-assess "<bug report>" slug=login-crash)./speckit-bug-fix slug=login-crash)./speckit-bug-test slug=login-crash).Replace vX.Y.Z with the latest release tag, keeping the leading v.
uv tool install specify-cli --from git+https://github.com/github/spec-kit.git@vX.Y.Z
specify init my-project --integration copilot
cd my-project
specify extension add assess
Launch your coding agent in the project directory, then:
/speckit-assess-intake "<idea>" slug=offline-mode)./speckit-assess-research slug=offline-mode)./speckit-assess-define slug=offline-mode)./speckit-assess-shape slug=offline-mode)./speckit-assess-decide slug=offline-mode).[!NOTE] Idea assessment is standalone. If you choose to build an idea with a go decision, you can hand it off to /speckit-specify.
Additional commands for enhanced quality and validation:
| Command | Agent Skill | Description |
|---|---|---|
/speckit.clarify | speckit-clarify | Clarify underspecified areas (recommended before /speckit.plan; formerly /quizme) |
/speckit.analyze | speckit-analyze | Cross-artifact consistency & coverage analysis (run after /speckit.tasks, before /speckit.implement) |
/speckit.checklist | speckit-checklist | Generate custom quality checklists that validate requirements completeness, clarity, and consistency (like "unit tests for English") |
For full command details, options, and examples, see the CLI Reference.
Spec 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 guide.
Run specify integration list to see all available integrations in your installed version.
Spec Kit can be tailored to your needs through two complementary systems — extensions and presets — plus project-local overrides for one-off adjustments:
| Priority | Component Type | Location |
|---|---|---|
| ⬆ 1 | Project-Local Overrides | .specify/templates/overrides/ |
| 2 | Presets — Customize core & extensions | .specify/presets/templates/ |
| 3 | Extensions — Add new capabilities | .specify/extensions/templates/ |
| ⬇ 4 | Spec Kit Core — Built-in SDD commands & templates | .specify/templates/ |
.specify/templates/overrides/) let you make one-off adjustments for a single project without creating a full preset.specify extension add or specify preset add, command files are written into agent directories (e.g., .claude/commands/).specify extension search
Use 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.
```bash
specify self upgrade
Spec Kit 是一个开源工具包,旨在帮助开发者更高效地构建高质量软件。它让你可以将精力集中在产品场景和可预测的结果上,而不是陷入“凭感觉编程”(vibe coding)的重复劳动中。通过规范化的流程,Spec Kit 能够显著提升开发效率,确保软件构建过程更加严谨且符合预期。
Spec Kit 支持通过 Extensions(扩展)来增强其核心能力。当内置的 SDD 命令无法满足特定需求时,你可以通过扩展引入新的命令、模板或领域特定的工作流。无论是集成外部工具,还是增加全新的开发阶段,Extensions 都能极大地扩展 Spec Kit 的功能边界,使其适应更复杂的开发场景。
在使用 Spec Kit 之前,请确保你的系统环境满足以下要求:支持 Linux、macOS 或 Windows 系统;需要安装支持的 AI coding agent;推荐使用 uv 进行包管理(也可使用 pipx 进行持久化安装);此外,系统必须安装 Python 3.11 或更高版本以确保兼容性。
首先,你需要安装 Specify CLI。请确保已安装 uv,并使用命令 `uv tool install specify-cli --from git+https://github.com/github/spec-kit.git@vX.Y.Z` 进行安装(请将 vX.Y.Z 替换为最新的 Release 版本号)。如果需要安装扩展功能,可以使用 `specify extension add <extension-name>` 命令。你可以通过查看官方的 Installation Guide 来获取关于验证、升级及故障排除的详细说明。
在实际使用中,Spec Kit 强调规范化的工作流。例如,在创建完基准规范(baseline specification)后,如果发现某些需求未被准确捕获,必须执行功能规范澄清(Functional specification clarification)流程。务必在创建技术方案(technical plan)之前运行结构化的澄清工作流,以确保后续开发基于准确的需求定义。
Spec Kit 提供了一系列可选命令,用于增强代码质量和验证能力。通过特定的 Agent Skill(如 `speckit-clarify`),你可以使用 `/speckit.clarify` 等命令来澄清描述不足的需求。此外,你可以通过 Extensions 和 Presets 系统进行个性化定制,甚至通过项目本地的覆盖配置(project-local overrides)来实现针对特定任务的灵活调整。
关于 Specify CLI 的完整命令详情、参数选项及使用示例,请参阅官方提供的 CLI Reference 文档。该文档为开发者提供了详尽的接口说明,帮助你更精准地调用各项功能。
Spec Kit 具有极强的兼容性,支持超过 30 种 AI coding agent,涵盖了 CLI 工具和基于 IDE 的助手。你可以通过运行 `specify integration list` 命令来查看当前支持的所有集成列表。此外,Spec Kit 允许用户通过 Extensions 和 Presets 系统进行深度定制,使其完美适配个人的开发习惯与项目需求。
高热度开源项目,融合规格化开发与AI生成能力,降低重复编码工作。架构完整、易扩展,是现代工程化的优秀实践工具。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:spec-kit AI技能包 的核心功能完整,质量优秀。对于AI 技术爱好者来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | spec-kit |
| 原始描述 | 开源AI工具:💫 Toolkit to help you get started with Spec-Driven Development。⭐97.4k · Python |
| Topics | 规格驱动开发AI助手代码生成PRD转化工程工具 |
| GitHub | https://github.com/github/spec-kit |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-13 · 更新时间:2026-05-16 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。