SkillAtlasSkill 详情

ai-maestro-documentation-search

This is the open-source content repository behind

审核状态:已审核Quality 80Security 80

复制安装命令

用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。

复制前请先查看来源、License 和安全提示。

项目 README

来源文件:README.md

抓取于 2026年9月3日

Skill Store — Marketplace Repository

This is the open-source content repository behind Skill Store. It stores every approved Agent Skill, the records that go with it, and the automated security audits published with each skill.

This repo is a companion to the Skill Store platform, not the place to submit skills. Skills are added through skillstore.io — its review pipeline writes to this repo automatically. Please do not open a pull request here to add a skill; PRs adding skills will be closed. See Contributing a skill below.

Installing a skill

The recommended way to install any skill is the skillstore CLI — one command works for both Claude Code and Codex:

npx skillstore add author/skill-name

For example:

npx skillstore add aiskillstore/code-review

It downloads the skill and drops it into the right skills/ directory for your tool. Claude Code auto-discovers it; for Codex, restart the session.

Prefer to do it by hand, or installing via Claude Web? See the full Installation Guides for every method (CLI, manual, and ZIP upload) and the scope directories (~/.agents/skills/, .claude/skills/, ~/.claude/skills/, .codex/skills/, …).

Contributing a skill

Submit through the platform — not through a pull request:

  1. Go to skillstore.io/submit.
  2. Enter the GitHub repository URL that contains your SKILL.md.
  3. Your submission runs through automated security analysis.
  4. A maintainer reviews and approves it.
  5. On approval, the skill is published here and appears on skillstore.io.

What makes a valid skill

  • SKILL.md — the skill definition (required, per the Agent Skills spec)
  • Supporting files the skill references (optional)
  • LICENSE (recommended)

Security audit

Every submission is scanned automatically before it can be published. The audit flags things like:

  • Dangerous code patterns (eval, exec, raw system commands)
  • File access outside the project scope
  • Network calls to external hosts
  • Obfuscated or minified code
  • Credential / secret handling

Security analysis is report-only: findings inform maintainers and users, but a risk result does not automatically block an otherwise approved skill from being published. See our Security Trust Center for the methodology, limitations, and risk-level definitions.

Live Security Passport example:

Skillstore security

Repository layout

.
├── skills/        # Approved, published skills (one folder each, with SKILL.md)
├── pending/       # Submissions awaiting review
├── packages/
│   ├── cli/       # The `skillstore` CLI (npx skillstore add …)
│   └── skillstore/
├── schemas/       # JSON schemas for skill records
├── scripts/       # Maintenance & scoring scripts
└── .github/workflows/   # Submission, audit, and sync automation

The contents of this repo are maintained by Skill Store's automated pipeline. Manual changes are limited to maintainers.

Links

License

The marketplace catalog is MIT-licensed. Individual skills carry their own licenses — check each skill's LICENSE file.

研究与检索开发与工程

中风险

  • 来源需自行核对维护者身份。
  • 包含脚本或命令调用,安装前请复核。
  • 未检测到明显外部权限要求。
  • 未检测到高风险命令。
  • 扫描发现:2 条。

Codex — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/23blocks-os/ai-maestro-documentation-search" 文件夹复制到 Codex 的 skills 目录中。
  4. 重启 Codex 让新的 skill 生效。

Codex — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Codex 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Codex 让新的 skill 生效。

Claude Code — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/23blocks-os/ai-maestro-documentation-search" 文件夹复制到 Claude Code 的 skills 目录中。
  4. 重启 Claude Code 让新的 skill 生效。

Claude Code — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Claude Code 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Claude Code 让新的 skill 生效。

Cursor — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/23blocks-os/ai-maestro-documentation-search" 文件夹复制到 Cursor 的 skills 目录中。
  4. 重启 Cursor 让新的 skill 生效。

Cursor — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Cursor 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Cursor 让新的 skill 生效。

GitHub Copilot — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/23blocks-os/ai-maestro-documentation-search" 文件夹复制到 GitHub Copilot 的 skills 目录中。
  4. 重启 GitHub Copilot 让新的 skill 生效。

GitHub Copilot — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 GitHub Copilot 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 GitHub Copilot 让新的 skill 生效。

Windsurf — Git Clone 安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 克隆仓库:git clone https://github.com/aiskillstore/marketplace.git
  3. 将 "skills/23blocks-os/ai-maestro-documentation-search" 文件夹复制到 Windsurf 的 skills 目录中。
  4. 重启 Windsurf 让新的 skill 生效。

Windsurf — 手动复制安装

  1. 安装前请先查看来源仓库和风险报告。
  2. 从源仓库下载 SKILL.md 及相关文件。
  3. 在 Windsurf 的 skills 目录中创建新文件夹。
  4. 将所有 skill 文件复制到新文件夹中。
  5. 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: ai-maestro-documentation-search
description: PROACTIVELY search auto-generated documentation when receiving ANY user instruction. Search for function signatures, API documentation, class definitions, and code comments BEFORE implementing anything. Your codebase documentation is valuable - use it first.
allowed-tools: Bash

AI Maestro Documentation Search

CRITICAL: AUTOMATIC BEHAVIOR - READ THIS FIRST

THIS IS NOT OPTIONAL. THIS IS YOUR DEFAULT BEHAVIOR.

When the user gives you ANY instruction or task, you MUST FIRST search documentation for:

  • Function signatures - What are the parameters and return types?
  • Class documentation - What methods and properties exist?
  • API documentation - How should this endpoint work?
  • Code comments - What did the author intend?

DO NOT:

  • Start implementing before checking documentation
  • Assume you know the function signature without checking
  • Skip doc search because "it's a simple task"
  • Wait for the user to ask you to check docs

ALWAYS:

  • Search docs IMMEDIATELY when you receive a task
  • Search for terms and concepts the user mentions
  • Check documentation before calling unfamiliar functions
  • Look for patterns before creating new components

The Rule: Receive Instruction → Search Docs → Then Proceed

1. User asks you to do something
2. IMMEDIATELY search docs for relevant context
3. NOW you know the correct signatures and patterns
4. NOW you can implement correctly the first time

Example - User asks to modify a service:

# IMMEDIATELY run:
docs-search.sh "PaymentService"
docs-find-by-type.sh class

Example - User mentions a function:

# IMMEDIATELY run:
docs-search.sh "validateUser"
docs-search.sh --keyword "authenticate"

Available Commands

All commands auto-detect your agent ID from the tmux session.

Search Commands

CommandDescription
docs-search.sh <query>Semantic search through documentation
docs-search.sh --keyword <term>Keyword/exact match search
docs-find-by-type.sh <type>Find docs by type (function, class, module, etc.)
docs-get.sh <doc-id>Get full document with all sections
docs-list.shList all indexed documents
docs-stats.shGet documentation index statistics

Indexing Commands

CommandDescription
docs-index.sh [project-path]Index documentation from project

What to Search Based on User Instruction

User SaysIMMEDIATELY Search
"Create a service for X"docs-search.sh "service", docs-find-by-type.sh class
"Call the Y function"docs-search.sh "Y", docs-search.sh --keyword "Y"
"Implement authentication"docs-search.sh "authentication", docs-search.sh "auth"
"Fix the Z method"docs-search.sh "Z" --keyword, docs-find-by-type.sh function
Any API/function namedocs-search.sh "<name>" --keyword

Usage Examples

Search for Documentation

# Semantic search - finds conceptually related docs
docs-search.sh "authentication flow"
docs-search.sh "how to validate user input"
docs-search.sh "database connection pooling"

# Keyword search - exact term matching
docs-search.sh --keyword "authenticate"
docs-search.sh --keyword "UserController"

Find by Document Type

# Find all function documentation
docs-find-by-type.sh function

# Find all class documentation
docs-find-by-type.sh class

# Find all module/concern documentation
docs-find-by-type.sh module

# Find all interface documentation
docs-find-by-type.sh interface

Get Full Document

# After finding a doc ID from search results
docs-get.sh doc-abc123

# Shows full content including all sections

List and Stats

# List all indexed documents
docs-list.sh

# Get index statistics
docs-stats.sh

Index Documentation

# Index current project (auto-detected from agent config)
docs-index.sh

# Index specific project
docs-index.sh /path/to/project

Document Types

The following document types are recognized:

TypeDescriptionSources
functionFunction/method documentationJSDoc, RDoc, docstrings
classClass documentationClass-level comments
moduleModule/namespace documentationModule comments
interfaceInterface/type documentationTypeScript interfaces
componentReact/Vue component documentationComponent comments
constantDocumented constantsConstant comments
readmeREADME filesREADME.md, README.txt
guideGuide/tutorial documentationdocs/ folder

Integration with Other Skills

Docs-search works best when combined with other skills:

Combined Search Pattern (RECOMMENDED)

When you receive ANY user instruction:

# 1. Search your memory first
memory-search.sh "topic"

# 2. Search documentation
docs-search.sh "topic"

# 3. Check code structure
graph-describe.sh ComponentName

This gives you complete context:

  • Memory: What was discussed before?
  • Docs: What does the documentation say?
  • Graph: What is the code structure?

Why This Matters

Without searching docs first, you will:

  • Use wrong function signatures (then get runtime errors)
  • Miss existing implementations (then duplicate code)
  • Violate documented patterns (then create inconsistency)
  • Misunderstand APIs (then build the wrong thing)

Doc search takes 1 second. Redoing work takes hours.

Error Handling

Script not found:

  • Check PATH: which docs-search.sh
  • Verify scripts installed: ls -la ~/.local/bin/docs-*.sh
  • Scripts are installed to ~/.local/bin/ which should be in your PATH
  • If not found, run: ./install-docs-tools.sh

API connection fails:

  • Ensure AI Maestro is running: curl http://localhost:23000/api/agents
  • Ensure documentation has been indexed: docs-stats.sh
  • If no docs indexed, run: docs-index.sh

Documentation is empty:

  • Check project has documented code (JSDoc, docstrings, comments)
  • Verify project path is correct
  • Re-index with: docs-index.sh /path/to/project

No results found:

  • Inform the user: "No documentation found for X - proceeding with code analysis, but documentation may need to be generated."

Installation

If commands are not found:

./install-docs-tools.sh

This installs scripts to ~/.local/bin/.

发现问题?提交给管理员复核

评分:

评论 (0)

暂无评论,成为第一个评论者吧!