Search, install, update, and rate AI agent skills from agentskill.sh (100,000+ skills). Use when the user asks to find skills, install extensions or plugins, discover new capabilities, check what skills are available, or says "how do I do X" when a skill might help. Also handles listing installed skills, checking for updates, rating skills, removing skills, and scanning skills for security issues.
Download and install agent skills from URLs into the ~/.chatshell/skills/ directory. This skill contains the exact workflow for parsing GitHub, GitLab, Bitbucket, and direct URLs, handling all URL variants (repo root, /tree/ directory, /blob/ file, raw content links), detecting single vs. multi-skill repos, managing conflicts with backups, and verifying installations. ALWAYS use this skill when the user shares any URL that might contain a SKILL.md or asks to install/add/download/grab/set up a skill from a link -- the skill knows the correct install path and directory structure that the agent cannot infer on its own. Also triggers when a user pastes a GitHub/GitLab/Bitbucket URL mentioning "skill" in the path.
Verify and install project tooling before feature development. Detects language (Node/TS, Python, Rust, Go), installs linter, formatter, type checker, dead code detection, pre-commit hooks, test framework, and standardized scripts. Idempotent — tracks state in .tooling-state.json. Use when starting a new project, when /develop Phase 4c runs, or when the user says "bootstrap", "setup tooling", "install dev tools", "quality gates".
Interactive setup wizard for PM Pilot. Detects MCP tools, sets company name, creates memory template, validates installation.
- 📄 agentar_cli.mjs
- 📄 SKILL.md
Search, install, and export agentars and teams from the CatchClaw marketplace. Use when the user wants to find, install, or package agent templates or teams.
为任何项目创建完整的文档网站。当被要求时使用此技能： "创建文档", "添加文档", "建立文档网站", "生成文档", "文档化项目", "编写文档", "初始化文档", "添加文档文件夹", "创建文档网站"。生成基于 Movk Nuxt Docs 的网站 包含搜索、深色模式、MCP 服务器和 llms.txt 集成。 --- # 创建文档 为任何项目生成完整的、生产就绪的文档网站。 ## 工作流程 1. **分析** - 检测包管理器、monorepo 结构、读取上下文 2. **初始化** - 使用正确的设置创建文档目录 3. **生成** - 使用模板编写文档页面 4. **配置** - 设置 AI 集成（MCP、llms.txt） 5. **最终化** - 提供后续步骤和正确的命令 --- ## 包管理器参考 从 lock 文件检测，如果未找到则默认使用 npm： | Lock 文件 | PM | 安装 | 运行 | 添加 | |-----------|------|---------|-----|-----| | `pnpm-lock.yaml` | pnpm | `pnpm install` | `pnpm run` | `pnpm add` | | `package-lock.json` | npm | `npm install` | `npm run` | `npm install` | | `yarn.lock` | yarn | `yarn install` | `yarn` | `yarn add` | | `bun.lockb` | bun | `bun install` | `bun run` | `bun add` | 在下面的命令中使用 `[pm]` 作为占位符。 --- ## 步骤 1：分析项目 ### 检测项目结构 ``` 检查： ├── pnpm-workspace.yaml → pnpm monorepo ├── turbo.json → Turborepo monorepo ├── lerna.json → Lerna monorepo ├── nx.json → Nx monorepo ├── apps/ → Apps 目录（monorepo） ├── packages/ → Packages 目录（monorepo） ├── docs/ → 现有文档（避免覆盖） ├── README.md → 主文档源 └── src/ 或 lib/ → 源代码位置 ``` ### 确定文档位置 | 项目类型 | 目标目录 | Workspace 项目 | |--------------|------------------|-----------------| | 标准项目 | `./docs` | N/A | | Monorepo with `apps/` | `./apps/docs` | `apps/docs` | | Monorepo with `packages/` | `./docs` | `docs` | | 现有 `docs/` 文件夹 | 询问用户或 `./documentation` | — | ### 读取上下文文件 | 文件 | 提取 | |------|---------| | `README.md` | 项目名称、描述、功能、使用示例 | | `package.json` | 名称、描述、依赖、仓库 URL | | `src/` 或 `lib/` | 导出的函数、可组合项用于 API 文档 | --- ## 步骤 2：初始化文档 ### 创建目录结构 ```bash # 完整模板
