AI Skill Hub 强烈推荐:克劳德开发工具包 是一款优质的Agent工作流。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案,这是一个值得深入了解的选择。
克劳德开发工具包 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
克劳德开发工具包 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install claude-dev-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 claude-dev-kit
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/pillip/claude-dev-kit
cd claude-dev-kit
pip install -e .
# 验证安装
python -c "import claude_dev_kit; print('安装成功')"
# 命令行使用
claude-dev-kit --help
# 基本用法
claude-dev-kit input_file -o output_file
# Python 代码中调用
import claude_dev_kit
# 示例
result = claude_dev_kit.process("input")
print(result)
# claude-dev-kit 配置文件示例(config.yml) app: name: "claude-dev-kit" debug: false log_level: "INFO" # 运行时指定配置文件 claude-dev-kit --config config.yml # 或通过环境变量配置 export CLAUDE_DEV_KIT_API_KEY="your-key" export CLAUDE_DEV_KIT_OUTPUT_DIR="./output"
Turn a PRD into shipped code. Specialized engineering agents and skills handle the entire development lifecycle — from PRD to code review to deployment — so you can focus on what to build, not how.
claude-kit takes a PRD (Product Requirements Document) as input and orchestrates AI agents to support the entire development lifecycle — from requirements analysis to code review and deployment.
Core Principles: - GitHub-first: Issues and PRs are the single source of truth - 1 Issue = 1 PR: Each issue maps to exactly one pull request - issues.md as SSOT: Progress and completion are tracked by Status in this file - Skill orchestration: Skills feed back into each other — review findings auto-create issues, shipped code triggers test gap detection, standalone skills register in the sprint ecosystem
/implement ISSUE-001 → /review ISSUE-001 → /ship Pick an issue from issues.md, implement it with TDD, review with security audit, and merge.
/issue "Add Stripe payment processing with subscription tiers, billing page, and invoice history" Auto-detects that this spans multiple screens/modules, estimates issue count, updates planning and design docs incrementally (append-only), and creates a batch of implementation issues with dependencies.
gh) — authenticated/migrate [target, e.g. "Django 5.0" or "Python 3.12"]
Scans the codebase for impact, generates a step-by-step migration plan with rollback instructions, and applies changes incrementally with test verification.
``` /prd → /kickoff → /uiux → /sprint
claude-dev-kit ships as a Claude Code plugin marketplace (.claude-plugin/marketplace.json).
Inside a Claude Code session:
```bash
/plugin marketplace add pillip/claude-dev-kit /plugin install claude-dev-kit@claude-dev-kit
Or from a shell (same effect, scriptable):
bash claude plugin marketplace add pillip/claude-dev-kit claude plugin install claude-dev-kit@claude-dev-kit # --scope user|project|local ```
Namespacing: plugin skills are namespaced by plugin name — e.g. /claude-dev-kit:implement, /claude-dev-kit:review. This is mandatory for plugins (it prevents cross-plugin collisions).
Script resolution: kit helper scripts (checkpoints, worktree wrappers) resolve through ${CLAUDE_PLUGIN_ROOT}, which Claude Code substitutes into skill text at load time — no files are copied into your project, and the absolute prefix keeps working from inside worktrees.
Installs the status line script to ~/.claude/kit/bin/. Run once per machine (needs a clone of this repo):
bash scripts/install_user.sh
Migrating from the retired submodule installer? The symlink-based project installer was removed after the plugin path reached parity (ISSUE-027). Remove the old symlinks from your project's.claude/agents/,.claude/skills/, and.claude/hooks/, drop the.claude-kitsubmodule if you no longer need it, and install the plugin as above. Skill names gain the/claude-dev-kit:prefix.
/implement ISSUE-001
issues.mdCloses #<issue_number> in bodyissues.md metadata/ship
Verifies tests pass, updates documentation, merges the PR, and reports test coverage gaps in shipped code with suggestions to run /testgen.
claude plugin uninstall claude-dev-kit
claude plugin marketplace remove claude-dev-kit
Or in-session via /plugin. Plugin files live in Claude Code's cache (~/.claude/plugins/), so uninstalling leaves nothing behind in your project — any .claude-kit/ runtime state in a project can be deleted freely.
The kit assumes the repo IS the team boundary. Two adoption patterns cover the common shapes — and there is deliberately no separate "team layer."
``` Start with an idea, validate it, write a PRD, generate planning docs, design the UI, and let the team-lead auto-implement everything.
**Existing codebase (no PRD):** /scan → /sprint
**Single issue:** /implement ISSUE-001 → /review ISSUE-001 → /ship
**Add a feature to existing product:** /issue "feature description" → /sprint (or /implement per issue) ```
Optional pre-PRD:/brainstorm(Socratic exploration) and/bizanalysis(market + SWOT) are stand-alone primitives, not part of the default flow. If your idea is clear, start from/prd. These exist for the case where you genuinely don't know what to build yet./uiux,/mobile-uiux, and/desktop-uiuxare optional for UI projects. Backend/CLI projects go directly from/kickoffto/sprint./sprintauto-orchestrates multiple issues. For a single issue, use/implementdirectly./scanis for existing codebases without a PRD. It reverse-engineers planning docs from code.
A few environment variables tune gate behaviour without editing code. All are optional — the defaults are safe for local and CI runs:
- KIT_CHECKPOINT_TEST_TIMEOUT — seconds allowed for test-phase checkpoints (/implement RED/test, /ship smoke) and the verify_gates.py unit gate. Default 600; invalid or non-positive values fall back to the default. - KIT_SPRINT_QUEUE_GH_TIMEOUT — default 10; seconds for the sprint queue's gh pr view merge-state probe (scripts/sprint_queue.py). On timeout the probe degrades to a phase-only decision so an offline or hung gh never blocks the frequently-run queue. - KIT_ALLOW_BROWSER_INSTALL — set to 1 to let the visual-diff and computed-styles gates auto-install Playwright + Chromium (heavy network + subprocess provisioning) when the browser is missing. Unset (the default) or any other value keeps the gate side-effect-free: it skips with a "browser unavailable" note instead of mutating the environment.
qa-designer generates a ## Verify Gates Configuration section in docs/test_plan.md. Users can edit it to override defaults without touching Python:
```markdown
Server start command: npm run dev Server health URL: http://localhost:3000 Server startup timeout: 30 Mobile test framework: maestro Mobile build command: npm run build:ios Mobile Detox config: ios.sim.debug
New project: ``` /prd → /kickoff → /uiux → /sprint
claude-kit (v0.1) 是一个强大的 AI 开发辅助工具,旨在将 PRD(产品需求文档)直接转化为可交付的代码。它通过编排 33 个 AI agents 和 22 项技能,覆盖了从头脑风暴、需求分析到代码评审及最终部署的完整开发生命周期。项目遵循 GitHub-first 原则,将 Issues 和 PRs 作为唯一事实来源(SSOT),确保开发过程透明且可追溯,实现 1 Issue 对应 1 PR 的规范化管理。
claude-kit 提供全场景的 AI 开发能力:支持从零开始构建产品,通过指令链完成从构思到 UI/UX 设计再到自动实现的闭环;支持在现有代码库中通过 /issue 指令添加复杂功能,系统会自动拆解任务并更新设计文档;同时具备强大的迁移能力,可通过 /migrate 指令安全地升级依赖或运行时环境,并配合测试验证确保平滑过渡。
在使用 claude-kit 之前,请确保您的开发环境满足以下要求:操作系统需为 macOS 或 Linux;必须安装 Python 3.11 或更高版本;需要配置好 Git 环境;此外,必须安装并完成身份验证的 GitHub CLI (gh);最后,您需要能够访问 Claude Code(支持 CLI、桌面应用或 IDE 扩展形式)。
安装过程分为两个核心步骤:首先,将 claude-kit 作为 git submodule 添加到您的服务仓库中,执行 `git submodule add git@github.com:pillip/claude-dev-kit.git .claude-kit`;其次,在每台机器上运行一次用户工具安装脚本 `bash .claude-kit/scripts/install_user.sh`,将状态栏脚本安装至 `~/.claude/kit/bin/`,以完成环境初始化。
claude-kit 支持多种工作模式以适应不同开发阶段。对于新项目,您可以使用指令链从 /brainstorm 开始构建完整流程;对于缺乏 PRD 的现有代码库,可通过 /scan 进入 Sprint 模式;若需处理单个任务,可使用 /implement 结合 TDD 进行开发并由 /review 进行安全审计;对于功能扩展,只需描述需求,系统将自动进行任务拆解与规划。
项目的质量把控通过 `docs/test_plan.md` 进行配置。qa-designer 会在该文件中自动生成 `## Verify Gates Configuration` 章节。用户无需修改 Python 代码,只需直接编辑该 Markdown 文件中的配置项(如 Server start command、health URL 或 Mobile test framework 等),即可灵活覆盖默认的验证门禁逻辑,实现低成本的自动化测试定制。
claude-kit 提供了高度结构化的工作流:新项目遵循从构思到实现的完整链路(/brainstorm → /prd → /uiux → /sprint);针对现有项目,可通过 /scan 快速接入;针对特定 Issue,采用 /implement → /review → /ship 的标准交付流程;而对于复杂的功能需求,系统会通过 /issue 触发自动化的任务拆解与迭代开发模式。
高质量的AI工作流工具,自动化代码生成
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。
总体来看,克劳德开发工具包 是一款质量优秀的Agent工作流,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | claude-dev-kit |
| 原始描述 | 开源AI工作流:A Claude Code kit that turns a PRD into shipped code — 32 AI agents, 21 skills, 。⭐11 · Python |
| Topics | ai-agentsautonomous-codingclaudecode-generation |
| GitHub | https://github.com/pillip/claude-dev-kit |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-05 · 更新时间:2026-06-05 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端