本文へ移動
cccskills
無料GitHub で公開

ai-maestro-documentation-search

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.

インストール方法を見る

含まれるファイル(2)

  • SKILL.md6.4 KB
  • skill-report.json57.6 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

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/.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Trigger for: explaining current FAR, DFARS, or agency-supplement text; determining documented acquisition-policy status for an agency and FAR part; comparing codified text, RFO model text, and agency deviations; tracing acquisition rulemaking; finding procurement comment periods; analyzing public comments; refreshing prior policy analysis; or producing an Acquisition Policy Impact Brief. Use published federal sources and supplied policy documents without making legal or procurement-specific applicability determinations. Do not use for clause selection, market research execution, opportunities, pricing, grants, or cooperative agreements.

日本語の概要は準備中です。原文の説明を表示しています。

aiskillstore/marketplace4322026年10月13日 更新

Systematic framework for extracting actionable items from documents and organizing them into prioritized, trackable checklists. Use when converting reports, meeting notes, audits, or any document with embedded action items into structured TODO lists.

日本語の概要は準備中です。原文の説明を表示しています。

aiskillstore/marketplace4322026年10月13日 更新

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web automation, data extraction, testing, agent browsing, research. Triggers: browser, web automation, scrape, navigate, click, fill form, screenshot, browse web, playwright, headless browser, web agent, surf internet, record video

日本語の概要は準備中です。原文の説明を表示しています。

aiskillstore/marketplace4322026年10月13日 更新

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

日本語の概要は準備中です。原文の説明を表示しています。

aiskillstore/marketplace4322026年10月13日 更新

Run AI apps via inference.sh CLI - image generation, video creation, LLMs, search, 3D, Twitter automation. Models: FLUX, Veo, Gemini, Grok, Claude, Seedance, OmniHuman, Tavily, Exa, OpenRouter, and many more. Use when running AI apps, generating images/videos, calling LLMs, web search, or automating Twitter. Triggers: inference.sh, infsh, ai model, run ai, serverless ai, ai api, flux, veo, claude api, image generation, video generation, openrouter, tavily, exa search, twitter api, grok

日本語の概要は準備中です。原文の説明を表示しています。

aiskillstore/marketplace4322026年10月13日 更新

Agile ceremonies and sprint management specialist. Use when running standups, retrospectives, sprint planning, or tracking sprint progress.

日本語の概要は準備中です。原文の説明を表示しています。

aiskillstore/marketplace4322026年10月13日 更新

aiskillstore のスキルをすべて見る

このスキルの問題を報告する