vector-databases
Model data as vectors with payload metadata, then run similarity search with optional filters or multi-stage retrieval. Keep index maintenance in the loop so performance does not degrade as the collection changes.
npx skills add majiayu000/claude-skill-registry --skill vector-databases-cuba6112-skillfactory --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.
--- name: vector-databases description: Design vector database ingestion and retrieval pipelines (points + payloads, filtered similarity search, multi-stage hybrid retrieval, index maintenance). Use when building RAG/vector search flows or debugging retrieval quality; triggers: vector database, RAG, embeddings, hybrid search, filtered search, Qdrant, Weaviate, Chroma. --- # Vector Databases ## Overview Model data as vectors with payload metadata, then run similarity search with optional filters or multi-stage retrieval. Keep index maintenance in the loop so performance does not degrade as the collection changes. ## When to Use - Use this skill when the frontmatter triggers apply; otherwise start with a simple keyword search or database query. ## Decision Tree 1. Do you need metadata filters for access control or faceting? - Yes: store payloads and use filtered search. 2. Do you need to blend multiple signals (dense + sparse or multi-step)? - Yes: use a multi-stage hybrid query plan. 3. Is search latency degrading after heavy updates or deletes? - Yes: run optimizer/maintenance operations. ## Workflows ### 1. Point Ingestion With Payloads 1. Generate embeddings for each document or
- Overview
- When to Use
- Decision Tree
- Workflows
- 1. Point Ingestion With Payloads
- 2. Filtered Similarity Search
- 3. Multi-Stage Hybrid Retrieval
- 4. Index Maintenance Pass
- Non-Obvious Insights
- Evidence
- Scripts
- Dependencies
- References
What does the vector-databases skill do?
Model data as vectors with payload metadata, then run similarity search with optional filters or multi-stage retrieval. Keep index maintenance in the loop so performance does not degrade as the collection changes.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill vector-databases-cuba6112-skillfactory --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.