nkapila6

Local Rag Search

知識管理v0.1.0
作者:nkapila6更新於 2026-05-11local-rag-search@clawhub_nkapila6/local-rag-search
知識庫問答資訊檢索#Rag#Current Information#Search The Web#Web Search

據 AlphaMoat 統計,截至 2026-10,Local Rag Search 累計下載 7,031 次、獲 4 個星標,按累計下載量在本次參與排名的 10,914 個 AI 技能中排名第 4,019 位,在「知識管理」分類(745 個)中排名第 284 位。

列表預設按累計下載量排序,也可按星標排序;詳情頁排名按累計下載量計算。

累計下載
7031
星標
4
全站下載量排名
#4,019
全站前 37% · 「知識管理」前 39%
平台累計下載星標評論
ClawHub ↗50613-
SkillHub ↗70314—

各平台的計數口徑不同,統計時間不一致。

這個技能是做什麼的

提供 DuckDuckGo、Google 與多引擎搜尋,按相似度排序並返回來源 URL。需伺服器及相應工具可用;無需單獨 API 整合不等於離線,查詢仍訪問搜尋服務。應核查時效與多方來源,相關性得分不是事實核驗。

資料釋出於 2026-10-27

可以用來做什麼

  • 收集並比較網頁研究來源

什麼時候用

  • MCP 搜尋伺服器可用時

示例提示詞

以下是根據技能文件生成的示例,不代表實際執行結果。

規劃相關檢索詞與引擎,再引用來源、檢查日期並指出衝突發現。

月度資料趨勢

累計下載7031
3415535772992026-03 · 累計下載 36832026-05 · 累計下載 43162026-06 · 累計下載 44792026-07 · 累計下載 47222026-08 · 累計下載 48262026-09 · 累計下載 52022026-10 · 累計下載 703126-0326-0926-10
星標4
3442026-03 · 星標 32026-05 · 星標 42026-06 · 星標 32026-07 · 星標 42026-08 · 星標 42026-09 · 星標 42026-10 · 星標 426-0326-0926-10

2026-09 起統計方法調整:同名技能按作者分別統計,並覆蓋全部技能。圖中虛線為調整前的月份,與之後的資料不直接比較,也不計算跨越調整的增長。

月份累計下載環比星標
2026-107031—4
2026-095202—4
2026-084826+2.2%4
2026-074722+5.4%4
2026-064479+3.8%3
2026-054316—4
2026-033683—3

SKILL.md 原文

以下是作者釋出的原始檔案,按純文字顯示,本站未做修改或稽核;其中的連結不可點選,命令請核實後再執行。抓取於 2026-10-23。

6.2 KB · ClawHub v0.1.0
---
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.
---

# Local RAG Search Skill

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.

## Available Tools
展開全部(共 189 行)

### 1. `rag_search_ddgs` - DuckDuckGo Search
Use this for privacy-focused, general web searches.

**When to use:**
- User prefers privacy-focused searches
- General information lookup
- Default choice for most queries

**Parameters:**
- `query`: Natural language search query
- `num_results`: Initial results to fetch (default: 10)
- `top_k`: Most relevant results to return (default: 5)
- `include_urls`: Include source URLs (default: true)

### 2. `rag_search_google` - Google Search
Use this for comprehensive, technical, or detailed searches.

**When to use:**
- Technical or scientific queries
- Need comprehensive coverage
- Searching for specific documentation

### 3. `deep_research` - Multi-Engine Deep Research
Use this for comprehensive research across multiple search engines.

**When to use:**
- Researching complex topics requiring broad coverage
- Need diverse perspectives from multiple sources
- Gathering comprehensive information on a subject

**Available backends:**
- `duckduckgo`: Privacy-focused general search
- `google`: Comprehensive technical results
- `bing`: Microsoft's search engine
- `brave`: Privacy-first search
- `wikipedia`: Encyclopedia/factual content
- `yahoo`, `yandex`, `mojeek`, `grokipedia`: Alternative engines

**Default:** `["duckduckgo", "google"]`

### 4. `deep_research_google` - Google-Only Deep Research
Shortcut for deep research using only Google.

### 5. `deep_research_ddgs` - DuckDuckGo-Only Deep Research
Shortcut for deep research using only DuckDuckGo.

## Best Practices

### Query Formulation
1. **Use natural language**: Write queries as questions or descriptive phrases
   - Good: "latest developments in quantum computing"
   - Good: "how to implement binary search in Python"
   - Avoid: Single keywords like "quantum" or "Python"

2. **Be specific**: Include context and details
   - Good: "React hooks best practices for 2024"
   - Better: "React useEffect cleanup function best practices"

### Tool Selection Strategy

1. **Single Topic, Quick Answer** → Use `rag_search_ddgs` or `rag_search_google`
   ```
   rag_search_ddgs(
       query="What is the capital of France?",
       top_k=3
   )
   ```

2. **Technical/Scientific Query** → Use `rag_search_google`
   ```
   rag_search_google(
       query="Docker multi-stage build optimization techniques",
       num_results=15,
       top_k=7
   )
   ```

3. **Comprehensive Research** → Use `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
   )
   ```

4. **Factual/Encyclopedia Content** → Use `deep_research` with Wikipedia
   ```
   deep_research(
       search_terms=["World War II timeline", "WWII key battles"],
       backends=["wikipedia"],
       num_results_per_term=5
   )
   ```

### Parameter Tuning

**For quick answers:**
- `num_results=5-10`, `top_k=3-5`

**For comprehensive research:**
- `num_results=15-20`, `top_k=7-10`

**For deep research:**
- `num_results_per_term=10-15`, `top_k_per_term=3-5`
- Use 2-5 related search terms
- Use 1-3 backends (more = more comprehensive but slower)

## Workflow Examples

### Example 1: Current Events
```
Task: "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 URLs
```

### Example 2: Technical Deep Dive
```
Task: "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 guide
```

### Example 3: Multi-Perspective Research
```
Task: "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 studies
```

## Guidelines

1. **Always cite sources**: When `include_urls=True`, reference the source URLs in your response
2. **Verify recency**: Check if the content appears current and relevant
3. **Cross-reference**: For important facts, use multiple search terms or engines
4. **Respect privacy**: Use DuckDuckGo for general queries unless specific needs require Google
5. **Batch related queries**: When researching a topic, create multiple related search terms for deep_research
6. **Semantic relevance**: Trust the RAG scoring - top results are semantically closest to the query
7. **Explain your choice**: Briefly mention which tool you're using and why

## Error Handling

If a search returns insufficient results:
1. Try rephrasing the query with different keywords
2. Switch to a different backend
3. Increase `num_results` parameter
4. Use `deep_research` with multiple related search terms

## Privacy Considerations

- DuckDuckGo: Privacy-focused, doesn't track users
- Google: Most comprehensive but tracks searches
- Recommend DuckDuckGo as default unless user specifically needs Google's coverage

## Performance Notes

- First search may be slower (model loading)
- Subsequent searches are faster (cached models)
- More backends = more comprehensive but slower
- Adjust `num_results` and `top_k` based on use case

「知識管理」分類下的熱門技能

搜尋引擎知識管理

透過公開搜尋URL在16個搜尋引擎(7個國內直連+9個國際)中做跨引擎檢索、結果去重與多源交叉驗證,無需API Key,內建零依賴Python指令碼。Use when 使用者要求“搜一下/查資料/多找幾個來源/核實訊息/找公眾號文章/排查報錯/找論文或開源專案”時。輸入自然語言查詢詞,輸出帶來源連結與可信度標註的結構化結果。不適用於私有資料檢索、批次抓取、需要登入後可見的內容。

↓ 1075.9萬★ 147u_8ee34d77
ima-skills知識管理

透過 IMA OpenAPI 管理筆記與知識庫內容。

↓ 108.4萬★ 566u_1742680f
Summarize知識管理

把長文字、文件與網頁內容壓縮成要點和關鍵詞的摘要工具。

↓ 87.6萬★ 1048paudyyin
全網搜尋知識管理

透過“查一下、搜一下、搜尋、找一下”等自然語言檢索公開網頁,整理來源並交付橫版 PDF、Markdown 與標題連結表。支援使用者主動開啟、檢視和取消技能收藏,保留原報告取回。

↓ 50.9萬★ 2u_32d99f8a
web-tools-guide知識管理

規定如何為網頁請求選擇合適工具的必讀指引。

↓ 40萬★ 220user_ec205dbb
Aihot Skill Lite知識管理

AI HOT(aihot.virxact.com)中文 AI 資訊查詢 Skill,幫助使用者獲取今日 AI 圈動態、AI 日報、AI 熱點、最新 AI 資訊以及 OpenAI、Anthropic、Google 等公司的最新發布資訊。

↓ 32.1萬★ 92Khazix
全球12億文獻知識庫(8千萬中文期刊可下載)知識管理

全球12億文獻知識庫(8千萬中文期刊可下載)——透過 SmartLib 開放平台 API 提供中外文學術文獻檢索與下載能力,覆蓋 8000 萬篇授權中文期刊全文 + 12.28 億條全球文獻後設資料(期刊 7.19 億 / 專利 2.15 億 / 會議 7155 萬 / 學位論文 2473 萬 / 標準 268 萬)。 能力:中英文關鍵詞檢索、文獻詳情、中文期刊 PDF 全文下載、外文 OA 文獻十級渠道免費下載(不消耗配額)、智慧關鍵詞擴充套件、核心期刊優先排序、相關性重排、引文追溯、分類號檢索。 配額:首次使用自動註冊,免費 100 次檢索 + 10 次下載 / 月;耗盡自動彈出方案(體驗卡 / 個人版月 / 專業版月 / 單篇下載 / 下載包),可說「升級 / 充值」喚起;企業 / 機構定製聯絡 [email protected]。 觸發:使用者表達"查論文""找文獻""檢索學術""搜期刊""查專利""找標準""下論文""寫文獻綜述""找參考文獻""查 SCI/EI"等意圖時啟用;也適用"幫我找關於 XX 的論文""寫文獻綜述""找幾篇引用支撐論點"。英文:"find papers" "search literature" "write literature review" "find supporting citations"。 呼叫前必須先用 /consume 獲取 consume_token,再憑 token 調 /search(每次計費介面呼叫都需一次 /consume)。

↓ 30.3萬★ 189user_164f4c1f
Markdown Converter知識管理

用 uvx 直接呼叫 markitdown,把各類檔案轉成 Markdown。

↓ 20.4萬★ 256Peter Steinberger

資料月份:2026-10 · 下載/星標數聚合自公開技能註冊庫(ClawHub、SkillHub),按月更新。口徑說明見資料方法。