Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of RAG-based web search with DuckDuckGo, Google, and multi-engine deep research capabilities.
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install local-rag-search或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install local-rag-search⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/local-rag-search/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
--- name: local-rag-search description: Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of RAG-based web search with DuckDuckGo, Google, and multi-engine deep research capabilities. ---
This skill enables you to effectively use the mcp-local-rag MCP server for intelligent web searches with semantic ranking. The server performs RAG-like similarity scoring to prioritize the most relevant results without requiring any external APIs.
rag_search_ddgs - DuckDuckGo SearchUse this for privacy-focused, general web searches.
When to use:
Parameters:
query: Natural language search querynum_results: Initial results to fetch (default: 10)top_k: Most relevant results to return (default: 5)include_urls: Include source URLs (default: true)rag_search_google - Google SearchUse this for comprehensive, technical, or detailed searches.
When to use:
deep_research - Multi-Engine Deep ResearchUse this for comprehensive research across multiple search engines.
When to use:
Available backends:
duckduckgo: Privacy-focused general searchgoogle: Comprehensive technical resultsbing: Microsoft's search enginebrave: Privacy-first searchwikipedia: Encyclopedia/factual contentyahoo, yandex, mojeek, grokipedia: Alternative enginesDefault: ["duckduckgo", "google"]
deep_research_google - Google-Only Deep ResearchShortcut for deep research using only Google.
deep_research_ddgs - DuckDuckGo-Only Deep ResearchShortcut for deep research using only DuckDuckGo.
- Good: "latest developments in quantum computing" - Good: "how to implement binary search in Python" - Avoid: Single keywords like "quantum" or "Python"
- Good: "React hooks best practices for 2024" - Better: "React useEffect cleanup function best practices"
rag_search_ddgs or rag_search_google``` rag_search_ddgs( query="What is the capital of France?", top_k=3 ) ```
rag_search_google``` rag_search_google( query="Docker multi-stage build optimization techniques", num_results=15, top_k=7 ) ```
deep_research with multiple search terms``` deep_research( search_terms=[ "machine learning fundamentals", "neural networks architecture", "deep learning best practices 2024" ], backends=["google", "duckduckgo"], top_k_per_term=5 ) ```
deep_research with Wikipedia``` deep_research( search_terms=["World War II timeline", "WWII key battles"], backends=["wikipedia"], num_results_per_term=5 ) ```
For quick answers:
num_results=5-10, top_k=3-5For comprehensive research:
num_results=15-20, top_k=7-10For deep research:
num_results_per_term=10-15, top_k_per_term=3-5Task: "What happened at the UN climate summit last week?"
1. Use rag_search_google for recent news coverage
2. Set top_k=7 for comprehensive view
3. Present findings with source URLsTask: "How do I optimize PostgreSQL queries?"
1. Use deep_research with multiple specific terms:
- "PostgreSQL query optimization techniques"
- "PostgreSQL index best practices"
- "PostgreSQL EXPLAIN ANALYZE tutorial"
2. Use backends=["google", "stackoverflow"] if available
3. Synthesize findings into actionable guideTask: "Research the impact of remote work on productivity"
1. Use deep_research with diverse search terms:
- "remote work productivity statistics 2024"
- "hybrid work model effectiveness studies"
- "work from home challenges research"
2. Use backends=["google", "duckduckgo"] for broad coverage
3. Synthesize different perspectives and studiesinclude_urls=True, reference the source URLs in your responseIf a search returns insufficient results:
num_results parameterdeep_research with multiple related search termsnum_results and top_k based on use case安装 Local Rag Search 后，可以对 AI 说这些话来触发它
Help me get started with Local Rag Search
Explains what Local Rag Search does, walks through the setup, and runs a quick demo based on your current project
Use Local Rag Search to efficiently perform web searches using the mcp-local-rag server wit...
Invokes Local Rag Search with the right parameters and returns the result directly in the conversation
What can I do with Local Rag Search in my data & analytics workflow?
Lists the top use cases for Local Rag Search, with example commands for each scenario
将技能文件夹放到 ~/.claude/skills/local-rag-search/ 目录（个人级，所有项目可用），或 .claude/skills/local-rag-search/（项目级）。重启 AI 客户端后，用 /local-rag-search 主动调用，或让 AI 根据上下文自动发现并使用。
Local Rag Search 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
Local Rag Search 可免费安装使用。请查阅仓库了解许可证信息。
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research topics across multiple sources, or gather context from the internet without using external APIs. This skill teaches effective use of RAG-based web search with DuckDuckGo, Google, and multi-engine deep research capabilities.
Automate my data & analytics tasks using Local Rag Search
Identifies repetitive steps in your workflow and sets up Local Rag Search to handle them automatically
Local Rag Search 属于「Data & Analytics」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。