Data Vector Databases
Use when the user asks to pick an index type for vector similarity search, pgvector, Qdrant, Milvus, Pinecone, Weaviate, HNSW vs IVF vs PQ, metadata filtering or storing embeddings. Produces vector store choice, collection schema and ANN index settings for recall, latency and memory. Not for full RAG pipeline design (use llm-rag-retrieval-internals).
Install
npx skills add j4flmao/agent-skills --skill data-vector-databasesgit clone --depth 1 https://github.com/j4flmao/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/data/vector-databases ~/.claude/skills/data-vector-databasesPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Vector Databases
## Purpose
Store embedding vectors with metadata and return the nearest neighbors of a query vector fast enough for interactive use. Exact search compares the query with every vector (O(N·d)); approximate nearest neighbor (ANN) indexes trade a measurable amount of recall for large speedups. The work is choosing the store, the index and its parameters, and proving recall on your own data.
## Agent Protocol
### Trigger
"vector database", "vector db", "pgvector", "qdrant", "milvus", "pinecone", "weaviate", "hnsw", "ivfflat", "ivf-pq", "ann", "similarity search", "store embeddings", "hybrid search", "recall@k".
### Input Context
- Number of vectors now and in 12 months, dimensions, embedding model, update rate.
- Query latency SLO and QPS, filter requirements (tenant, ACL, dates), existing database.
- Accuracy target (recall@k vs exact search).
### Output Artifact
Store choice + schema + index parameters + evaluation plan. No file unless requested.
### Response Format
```
Scale: {N vectors} x {d dims} {dtype} ≈ {GB raw}
Store: {pgvector|Qdrant|Milvus|managed...} because {reason}
Index: {HNSW m/ef_construction/ef_search | IVF nlist/nprobe | +PQ/quantization}
Filtering: {pre/in-index/post}
Eval: recall@{k} vs exact on {n} queries, p95 latency
```
### Completion Criteria
- [ ] Distance metric matches how the embedding model was trained (cosine / dot / L2).
- [ ] Recall@k measured against exact (brute-force) results on a sample of real queries.Details
- Skill name
data-vector-databases- Repository
- j4flmao/agent-skills
- Path
skills/data/vector-databases/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Data Vector Databases skill do?
Use when the user asks to pick an index type for vector similarity search, pgvector, Qdrant, Milvus, Pinecone, Weaviate, HNSW vs IVF vs PQ, metadata filtering or storing embeddings. Produces vector store choice, collection schema and ANN index settings for recall, latency and memory. Not for full RAG pipeline design (use llm-rag-retrieval-internals).
How do I install the Data Vector Databases skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add j4flmao/agent-skills --skill data-vector-databases. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Data Vector Databases popular?
It lives in j4flmao/agent-skills, which has 45 GitHub stars and 6 forks.
Related skills
Agent Observability
45j4flmao/agent-skills
Use when the user asks about agent observability, tracing agent reasoning, debugging an agent loop, OpenTelemetry GenAI spans for LLM calls, LLM cost tracking per agent, agent audit logs or hallucination/eval monitoring in production. Produces instrumentation config, trace schema, dashboards, alerts and cost attribution. Not for generic service tracing without LLMs (use devops-opentelemetry).
AI Agent Architectures
45j4flmao/agent-skills
Use when the user asks to build an AI agent, design an agent that calls tools and keeps memory, write an agent system prompt or pick an agent framework (Claude Agent SDK, OpenAI Agents SDK, LangGraph). Produces an architecture brief covering loop, tools, memory, guardrails and evals, routing depth to child skills. Not for workflow patterns (use ai-agentic-workflows).
AI Agent Core Loop
45j4flmao/agent-skills
Use when the user asks about the agent loop, ReAct vs plan-and-solve, re-planning, Reflexion, an agent stuck in a loop, max iterations or termination conditions. Produces a loop spec or patch with state, success predicate, caps and no-progress detection. Not for overall agent design (use ai-agent-architectures) or tool schemas (use tool-calling-principles).
Edge AI
45j4flmao/agent-skills
Use when the user asks about edge AI, on-device inference, TensorRT on Jetson, ONNX Runtime, LiteRT (TFLite), TinyML, int8 quantization, Coral, NPUs or ExecuTorch. Produces export, quantization and on-device benchmarking plans. Not for model training (use ml-deep-learning) or cloud LLM serving (use ml-inference-optimization).
Data Modeling
45j4flmao/agent-skills
Use when the user asks about relational or graph data modeling: 3NF normalization, surrogate keys, temporal tables, table inheritance, property graph vs RDF or knowledge graph schemas. Produces a schema-first model with keys, constraints and denormalization rules. Not for Kimball star schemas (use data-dimensional-modeling) or graph DB operations (use data-graph-database).
Extreme Quantization Mastery
45j4flmao/agent-skills
Use when the user asks about FP8, INT4, NVFP4, MXFP4, GPTQ, AWQ, SmoothQuant, W4A16, W8A8, NF4 or bitsandbytes for LLMs on NVIDIA GPUs. Produces a quantization recipe, code and accuracy-eval plan matched to the GPU and serving engine. Not for format/GGUF basics (use llm-model-quantization) or TensorRT engines (use tensorrt-optimization).
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.