toolfs-rag
Semantic search over vector databases for document retrieval. Use this skill when the user requests searching documents, finding relevant content, or performing semantic queries such as "Search for information about X", "Find documents related to Y", or "Query the knowledge base".
npx skills add majiayu000/claude-skill-registry --skill rag-icewhaletech-toolfs --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# ToolFS RAG Semantic search over vector databases for document retrieval. RAG (Retrieval-Augmented Generation) enables finding relevant documents and content based on semantic similarity rather than exact keyword matches. ## How It Works 1. **Vector Search**: Queries are converted to embeddings and compared against document vectors 2. **Similarity Scoring**: Results are ranked by semantic similarity scores 3. **Top-K Results**: Returns the most relevant documents up to the specified limit 4. **Metadata Filtering**: Results include metadata for context and filtering ## Usage ### Semantic Search **ToolFS Path:** ``` /toolfs/rag/query?text=<query_text>&top_k=<number> ``` **Parameters:** - `text` or `q`: The search query (URL-encoded) - `top_k`: Number of results to return (default: 5) **Example:** ```json GET /toolfs/rag/query?text=ToolFS%20skill%20architecture&top_k=3 // Response { "query": "ToolFS skill architecture", "top_k": 3, "results": [ { "id": "doc-001", "content": "ToolFS provides a skill system that supports WASM modules for sandboxed execution. Skills can be mounted to virtual paths and executed through the Skill API.", "score": 0.95, "metadata": { "source": "documentatio
- How It Works
- Usage
- Semantic Search
- When to Use This Skill
- Query Parameters
- Result Structure
- Output Format
- Present Results to User
- Troubleshooting
- No Results Found
- Low Quality Results
- Best Practices
What does the toolfs-rag skill do?
Semantic search over vector databases for document retrieval. Use this skill when the user requests searching documents, finding relevant content, or performing semantic queries such as "Search for information about X", "Find documents related to Y", or "Query the knowledge base".
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill rag-icewhaletech-toolfs --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.