Create complete documentation sites for projects. Use when asked to: "create docs", "add documentation", "setup docs site", "generate docs", "document my project", "write docs", "initialize documentation", "add a docs folder", "create a docs website". Generates Docus-based sites with search, dark mode, MCP server, and llms.txt integration. --- # Create Docs Generate a complete, production-ready documentation site for any project. ## Workflow 1. **Analyze** - Detect package manager, monorepo structure, read context 2. **Initialize** - Create docs directory with correct setup 3. **Generate** - Write documentation pages using templates 4. **Configure** - Set up AI integration (MCP, llms.txt) 5. **Finalize** - Provide next steps with correct commands --- ## Package Manager Reference Detect from lock files, default to npm if none found: | Lock File | PM | Install | Run | Add | |-----------|------|---------|-----|-----| | `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` | Use `[pm]` as placeholder in commands below. --- ## Step 1: Analyze Project ### Detect Project Structure ```
Install and configure TMA1 local observability. Use when the user says: install tma1, setup observability, monitor my agent, track token usage, set up telemetry.
One-stop search and install for coding resources. Aggregates MCP Servers, Skills, Rules, and Prompts. Supports search, category browsing, project-based recommendations, and one-click install.
Use when tasks involve browser automation with bridgic-browser via terminal CLI (`bridgic-browser ...`) or Python SDK (`from bridgic.browser.session import Browser`, `from bridgic.browser.tools import BrowserToolSetBuilder`). Trigger for navigation, scraping, form filling, accessibility snapshot refs, e2e checks, stealth browsing, CLI-SDK mapping/migration, and generating SDK code from CLI action steps. --- ## Prerequisite (Important!!) Before performing any operations, **MAKE SURE to use `uv`** to initialize the execution environment and install dependencies first. Note: DO NOT rely on any execution environment other than `uv`, to ensure the execution environment is isolated from the host machine. - **Initialize project**: `[ -f pyproject.toml ] || uv init --bare --python 3.10` - **Install dependencies**: `uv add --upgrade bridgic-browser`. - **Ensure that `uv` is available**: If `uv` is not found or not installed, run `pip install uv` to install it. Then rerun the previous "Install dependencies" step. - **Install browser binaries** (one-time): `uv run playwright install chromium` The CLI tools (`references/cli-guide.md`) and the Python SDK (`references/sdk-guide.md`) come from the **same package** — installing one installs both. ## Strategies & Guidelines (Important!!) When writing browser automation or web scraping code, **ALWAYS follow this "explore first, then coding" strategy**: - First, use the `bridgic-browser` CLI tools to explore the page structure. It is recommended to use headed mode with the command `bridgic-browser open --headed <url>` during exploration. - Then, use the `bridgic-browser` Python SDK to write the code.
Install the OpenClaw Mem0 v2 enhanced memory plugin
ferris-search install, mcp add ferris-search, setup ferris-search,
Knowledge management for AI agents. Use the `brv` CLI to store and retrieve project patterns, decisions, and architectural rules in .brv/context-tree. Use before work (brv query) and after implementing (brv curate). Install: npm install -g byterover-cli.
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".
- 📄 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
