vector-databases — Claude Code skill: what it does, how to install
Compares vector databases and index algorithms for RAG and semantic retrieval. Helps pick an engine based on dataset scale and metadata filtering needs.
no license 128 installs ★ 7 updated 2026-01-15
npx skills add eyadsibai/ltk --skill vector-databases -a claude-codeWhat vector-databases does
The assistant gets a decision guide for selecting vector storage across semantic search and RAG workflows. It breaks down differences between Chroma, FAISS, Qdrant, Pinecone, and Weaviate, focusing on cloud availability, scale, and metadata filtering. It also outlines index structures like Flat, IVF, HNSW, and PQ for datasets ranging from 10K items to billions of vectors.
Chroma will not handle distributed production workloads because it runs strictly as a single node. Yet it needs zero configuration for local prototypes and automatically creates embeddings from raw text. When raw throughput on GPU matters without metadata, the guide points to FAISS, whereas Qdrant handles production setups with payload filters during query execution.
What it helps with
- choose a vector database suited for target dataset scale
- select the right index algorithm among Flat, IVF, HNSW, and PQ
- apply metadata filtering during semantic retrieval
- pick an embedded storage engine for RAG prototyping
Example prompts for the agent
- Help me pick a vector database for a local RAG prototype
- Which index algorithm is better for fast retrieval, HNSW or IVF?
- Compare Chroma and Qdrant for production workloads with metadata filters
How to install vector-databases
1Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill vector-databases -a claude-code2Manually: put the files in place
~/.claude/skills/vector-databases/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/vector-databases/
1Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill vector-databases -a codex2Manually: put the files in place
.agents/skills/vector-databases/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill vector-databases -a cursor2Manually: put the files in place
.cursor/skills/vector-databases/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eyadsibai/ltk plugins/ltk-data/skills/vector-databases2Manually: put the files in place
.github/skills/vector-databases/SKILL.md1Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill vector-databases -a gemini-cli2Platform CLI
gemini skills install https://github.com/eyadsibai/ltk --path plugins/ltk-data/skills/vector-databasesManually: put the files in place
.devin/skills/vector-databases/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eyadsibai/ltk --skill vector-databases -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about vector-databases
How do I install vector-databases in Claude Code?
Run npx skills add eyadsibai/ltk --skill vector-databases -a claude-code. The instruction file will be placed at ~/.claude/skills/vector-databases/SKILL.md.
What does vector-databases do?
It gives the coding assistant a structured reference for choosing vector engines and indexing methods. This helps design semantic retrieval and RAG setups accurately.
How does FAISS differ from Qdrant according to the guide?
FAISS focuses on raw retrieval speed and GPU execution without metadata filtering. Qdrant supports in-search payload filtering and horizontal scaling in production.