awesome-claude-code — AI Agent 工作流中文教程
awesome-claude-code — AI Agent 工作流中文教程 是 AI Skill Hub 本期精选Agent工作流之一。在 GitHub 上收获超过 44.5k 颗 Star，综合评分 7.5 分，整体质量较高。我们推荐使用将其纳入你的 AI 工具库，帮助提升工作效率。
📚 深度解析
awesome-claude-code — AI Agent 工作流中文教程 工作流的设计遵循"最小配置，最大复用"原则：核心逻辑已经封装好，用户只需配置自己的 API Key 和业务参数即可快速上手。工作流内置错误处理和重试机制，在网络波动或 API 限速等情况下仍能稳定运行，适合作为生产环境的自动化基础设施。
在实际部署时，建议先在测试环境中运行 3-5 次，验证各个环节的输出结果符合预期，再部署到生产环境。AI Skill Hub 评分 7.5 分，是同类 Agent 工作流中的精选推荐。
📋 工具概览
一份精心收集的Claude Code技能、钩子、命令、代理管理器、应用程序和插件的列表，帮助开发者优化AI工作流
awesome-claude-code — AI Agent 工作流中文教程 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。
📖 中文文档
一份精心收集的Claude Code技能、钩子、命令、代理管理器、应用程序和插件的列表，帮助开发者优化AI工作流
awesome-claude-code — AI Agent 工作流中文教程 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。
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
# 方式一：pip 安装（推荐）
pip install awesome-claude-code
# 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 awesome-claude-code
# 方式三：从源码安装（获取最新功能）
git clone https://github.com/hesreallyhim/awesome-claude-code
cd awesome-claude-code
pip install -e .
# 验证安装
python -c "import awesome_claude_code; print('安装成功')"
- 访问 GitHub 仓库获取工作流文件
- 在对应平台（Dify / Flowise / Make 等）中找到「导入工作流」功能
- 上传工作流文件
- 按照提示配置必要的环境变量和 API Key
- 运行测试确认流程正常后投入使用
# 命令行使用
awesome-claude-code --help
# 基本用法
awesome-claude-code input_file -o output_file
# Python 代码中调用
import awesome_claude_code
# 示例
result = awesome_claude_code.process("input")
print(result)
# awesome-claude-code 配置文件示例（config.yml） app: name: "awesome-claude-code" debug: false log_level: "INFO" # 运行时指定配置文件 awesome-claude-code --config config.yml # 或通过环境变量配置 export AWESOME_CLAUDE_CODE_API_KEY="your-key" export AWESOME_CLAUDE_CODE_OUTPUT_DIR="./output"
简介
_A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at Anthropic PBC. A delectable showcase of top tier skills, ambidextrous agents, scintillating status lines, top notch developer tooling, and also we have plugins. Suitable for beginners and veterans, with an emphasis on code quality, security, and originality.
<br>
The current iteration of the list, such as you see it today, was launched with the express intent to highlight resources that were not on the last iteration, and in particular to make selections from the list of recommendations. However, this is only temporary - resources will continue to be added over the coming weeks, and "legacy" resources will be migrated to the new format. So, if you had been featured on the list before, and you don't see your project now, that's the reason why - "legacy" resources that are still maintained and awesome will be added back in soon - and, in the meantime, they are also preserved (but will not be updated) in the README_ALTERNATIVES directory.
<br>
The Claude Code Ticker - A Sample of Claude Code Projects Around GitHub
<picture> <img src="assets/repo-ticker.svg" alt="Featured Claude Code Projects" width="100%"> </picture>
</div>
Providers, Runtime & Integration Infrastructure
- chrome-cdp-ex by Endeavor Yen - A zero-dependency Claude Code skill (68 commands) that connects to your real Chrome — logged-in tabs, cookies, live page state — to give the agent a perception layer: layout, visible styles, per-action "what changed" evidence, CSS-cascade-to-source tracing, and session replay/Playwright export. Notably rigorous about its own claims, with a dogfood benchmark gate that blocks performance/adoption assertions unless it passes. <img src="https://img.shields.io/github/created-at/EndeavorYen/chrome-cdp-ex?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="created"> <img src="https://img.shields.io/github/last-commit/EndeavorYen/chrome-cdp-ex?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="last-commit"> <img src="https://img.shields.io/github/license/EndeavorYen/chrome-cdp-ex?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="license"> <img src="https://img.shields.io/github/stars/EndeavorYen/chrome-cdp-ex?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="stars">
- Claude Codex Settings by fatih akyon - A well-organized, well-written set of plugins covering core developer activities, such as working with common cloud platforms like GitHub, Azure, MongoDB, and popular services such as Tavily, Playwright, and more. Clear, not overly-opinionated, and compatible with a few other providers. <img src="https://img.shields.io/github/created-at/fcakyon/claude-codex-settings?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="created"> <img src="https://img.shields.io/github/last-commit/fcakyon/claude-codex-settings?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="last-commit"> <img src="https://img.shields.io/github/license/fcakyon/claude-codex-settings?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="license"> <img src="https://img.shields.io/github/stars/fcakyon/claude-codex-settings?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="stars">
- claude-code-wsl2-setup by congmnguyen - A focused collection of documented scripts that fix the most painful Claude Code papercuts on WSL2 + Windows Terminal — clipboard screenshot paste via a Go daemon, Windows notifications on Stop/PermissionRequest hooks, LSP wiring, a usage-aware status line, and voice-mode audio routing. Each fix is written up with root cause and exact config (including non-obvious traps like SessionEnd firing per subagent), and the work was upstreamed into Awesome-WSL. <img src="https://img.shields.io/github/created-at/congmnguyen/claude-code-wsl2-setup?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="created"> <img src="https://img.shields.io/github/last-commit/congmnguyen/claude-code-wsl2-setup?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="last-commit"> <img src="https://img.shields.io/github/license/congmnguyen/claude-code-wsl2-setup?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="license"> <img src="https://img.shields.io/github/stars/congmnguyen/claude-code-wsl2-setup?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="stars">
- Codex Skill by klaudworks - Enables users to prompt codex from claude code. Unlike the raw codex mcp server, this skill infers parameters such as model, reasoning effort, sandboxing from your prompt or asks you to specify them. It also simplifies continuing prior codex sessions so that codex can continue with the prior context. <img src="https://img.shields.io/github/created-at/skills-directory/skill-codex?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="created"> <img src="https://img.shields.io/github/last-commit/skills-directory/skill-codex?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="last-commit"> <img src="https://img.shields.io/github/license/skills-directory/skill-codex?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="license"> <img src="https://img.shields.io/github/stars/skills-directory/skill-codex?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="stars">
- Flue by S.F. Kislev - A tiny bridge that lets Claude Code drive desktop software — Photoshop, Premiere, Blender, Unity, InDesign, Office, 13 apps total — by writing one-time scripts against each app's own automation runtime (COM / AppleScript / CEP), instead of MCP servers or fragile screenshot-based computer use. A genuinely novel approach that unlocks the apps' full scripting surfaces (InDesign alone exposes ~28k objects) with low maintenance. <img src="https://img.shields.io/github/created-at/SFKislev/Flue?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="created"> <img src="https://img.shields.io/github/last-commit/SFKislev/Flue?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="last-commit"> <img src="https://img.shields.io/github/license/SFKislev/Flue?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="license"> <img src="https://img.shields.io/github/stars/SFKislev/Flue?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="stars">
- Fusion Harness by disler - Fuses 2–5 frontier models instead of racing them — one architect, one primary builder, and up to three secondary builders — giving N-way opinions, debate, fusion, coordinated implementation, direct one-agent routing, and gate-first validation. Ships as a composable Pi extension with pre-built model stacks and install/prime commands, and a video walkthrough of the whole approach. <img src="https://img.shields.io/github/created-at/disler/fusion-harness?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="created"> <img src="https://img.shields.io/github/last-commit/disler/fusion-harness?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="last-commit"> <img src="https://img.shields.io/github/license/disler/fusion-harness?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="license"> <img src="https://img.shields.io/github/stars/disler/fusion-harness?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="stars">
- llm-router by Yali Pollak - A local-first router that sits under Claude Code (and Codex/Gemini CLI) and sends each prompt to the cheapest capable model, with three-layer token compression and automatic provider fallback — protecting your premium quota and cutting cost with zero config on a Claude subscription. Credibly engineered: 1,900+ tests, an independent RouterArena benchmark placement, and an honest local-only design with no hosted proxy. <img src="https://img.shields.io/github/created-at/ypollak2/llm-router?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="created"> <img src="https://img.shields.io/github/last-commit/ypollak2/llm-router?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="last-commit"> <img src="https://img.shields.io/github/license/ypollak2/llm-router?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="license"> <img src="https://img.shields.io/github/stars/ypollak2/llm-router?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="stars">
- OpenWeb by openweb-org - An agent-native skill that accesses 90+ websites by calling their underlying APIs directly (typed JSON in, JSON out) instead of screenshotting and parsing the DOM, with auth auto-resolved locally from your existing browser session. Security is first-class — every operation is tagged read/write/delete/transact behind permission tiers, SSRF protection runs on each request, and there is no vendor backend or proxy in the request path. <img src="https://img.shields.io/github/created-at/openweb-org/openweb?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="created"> <img src="https://img.shields.io/github/last-commit/openweb-org/openweb?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="last-commit"> <img src="https://img.shields.io/github/license/openweb-org/openweb?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="license"> <img src="https://img.shields.io/github/stars/openweb-org/openweb?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="stars">
- SPARDA by Zakaria Gharzouli (Residual Labs) - Converts a running Express or FastAPI app into an MCP server by AST-parsing its routes and injecting a marked, byte-for-byte-removable /mcp router, so the agent can operate your live application (real auth, real data) rather than just read files. Exceptionally safety-minded: writes are disabled by default behind two-phase confirmation, docstrings are sanitized against prompt injection, a circuit-breaker quarantines failing routes, nothing leaves the machine, and persistence stores structure never payloads. <img src="https://img.shields.io/github/created-at/zyx77550/sparda?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="created"> <img src="https://img.shields.io/github/last-commit/zyx77550/sparda?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="last-commit"> <img src="https://img.shields.io/github/license/zyx77550/sparda?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="license"> <img src="https://img.shields.io/github/stars/zyx77550/sparda?style=flat-square&labelColor=2b2b2b&color=6b6b6b" alt="stars">
该项目提供了一个广泛的Claude Code技能列表，包括钩子、命令、代理管理器、应用程序和插件，帮助开发者优化AI工作流。然而，项目维护者应该注意保持技能列表的更新和准确性。
- 构建多智能体协作系统的 Agent 开发者
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- Python 依赖冲突：建议用 venv / uv 隔离环境
- 云端托管：可放在 Vercel / Railway / Fly.io 等 PaaS 平台
⚡ 核心功能
- 可视化 Agent 工作流编排，无需编写复杂代码
- 支持多步骤自动化任务链，实现全流程无人值守
- 与外部 API、数据库和第三方服务无缝集成
- 内置错误处理与自动重试机制，保障稳定运行
- 提供可复用的自动化模板，快速在同类场景部署
- 构建多智能体协作系统的 Agent 开发者
- Agent 任务先做 dry-run 验证工具调用链，再开启自主执行
- API key 直接提交到 git 仓库（请用 .env 并加入 .gitignore）
- Python 依赖冲突：建议用 venv / uv 隔离环境
👥 适合人群
🎯 使用场景
- 自动化日常重复性工作，将精力集中于创造性任务
- 构建数据采集 → 处理 → 输出的完整自动化管线
- 实现跨平台、跨系统的数据流转和业务协同
⚖️ 优点与不足
- +GitHub 44.5k Star，社区高度认可
- +AI Skill Hub 精选推荐
- +大幅减少重复性人工操作
- +可视化流程，清晰直观
- +可扩展性强，支持复杂场景
- −初始配置和调试需投入一定时间
- −强依赖外部服务的稳定性
- −复杂场景需具备一定技术基础
该工具使用 NOASSERTION 协议，商用场景请仔细阅读协议条款，必要时咨询法律意见。
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。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
🔗 相关工具推荐
❓ 常见问题 FAQ
经综合评估，awesome-claude-code — AI Agent 工作流中文教程 在Agent工作流赛道中表现稳健，质量良好。如果你已有明确的使用需求，可以直接上手体验；如果还在评估阶段，建议对比同类工具后再做决策。
| 原始名称 | awesome-claude-code |
| 原始描述 | A curated list of awesome skills, hooks, slash-commands, agent orchestrators, applications, and plugins for Claude Code by Anthropic |
| Topics | agent-skillsagentic-codeagentic-codingai-workflow-optimizationai-workflowsanthropicclaude-skill |
| GitHub | https://github.com/hesreallyhim/awesome-claude-code |
| License | NOASSERTION |
| 语言 | Python |
收录时间：2026-05-22 · 更新时间：2026-05-30 · License：NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
🤖 交给 Agent 安装 · awesome-claude-code — AI Agent 工作流中文教程
选择 Agent 类型，复制安装指令后粘贴到对应客户端