faion-rag-engineer
RAG engineering: embeddings, chunking, vector databases, hybrid search, reranking.
npx skills add majiayu000/claude-skill-registry --skill faion-rag-engineer --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.
> **Entry point:** `/faion-net` — invoke this skill for automatic routing to the appropriate domain. # RAG Engineer Skill **Communication: User's language. Code: English.** ## Purpose Specializes in RAG (Retrieval Augmented Generation) systems. Covers document processing, embeddings, vector search, and retrieval optimization. ## Context Discovery ### Auto-Investigation Check these project signals before asking questions: | Signal | Where to Check | What to Look For | |--------|----------------|------------------| | **Dependencies** | package.json, requirements.txt | langchain, llamaindex, qdrant-client, chromadb, weaviate-client | | **Vector DB** | docker-compose.yml, .env | Qdrant, Weaviate, Chroma config/containers | | **Document dirs** | /docs, /data, /content | Documents to index (PDF, MD, TXT) | | **Existing embeddings** | Grep for "embed", "vector", "retriever" | Current RAG implementation | ### Discovery Questions ```yaml question: "What's your RAG use case?" header: "RAG Goal" multiSelect: false options: - label: "Documentation Q&A" description: "Answer questions from internal docs" - label: "Knowledge base search" description: "Semantic search over articles/guides" - label
- Purpose
- Context Discovery
- Auto-Investigation
- Discovery Questions
- Scope
- Quick Start
- Methodologies (22)
- Architecture
- Code Examples
- Basic RAG Pipeline
- Hybrid Search with Qdrant
- Reranking
- Evaluation Metrics
- Related Skills
What does the faion-rag-engineer skill do?
RAG engineering: embeddings, chunking, vector databases, hybrid search, reranking.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill faion-rag-engineer --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.