Topic · Code and Developer
Vector Databases and Embeddings skills for Claude Code and Codex
Skills for vector search and embeddings: Qdrant, Pinecone, Chroma, FAISS, Redis search, OpenSearch and pgvector, covering hybrid search, sizing, scaling, multitenancy, search quality and embedding generation. They help an agent build retrieval that is fast and returns the right results.
Highest-scoring vector database skills in the October 22, 2026 snapshot: google-cloud-solution-hybrid-search-alloydb from google/skills (85/100), qdrant-edge from qdrant/skills (84/100) and faiss from Orchestra-Research/AI-Research-SKILLs (77/100). Scores come from the Suede Skill Check.
- 57 listed skills
- 9 repositories
- 17 with full pages
50 from official publishers. 3 bundle scripts. 2 connect to an outside service. Listed in Data, Analytics and Databases (38), AI Agents and LLM Engineering (11), DevOps and Cloud (6), Developer Tools and Frameworks (2).
All 57 vector database skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| faiss 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Guides fast k-NN search and clustering of dense vectors with Facebook's FAISS, including GPU acceleration and Flat, IVF, and HNSW index types. |
| google-cloud-solution-hybrid-search-alloydb 85/100 · B | google/skills | Generates architecture, design, and deployment guidance for hybrid search systems combining semantic and keyword search, optimized for AlloyDB use cases. |
| langchain 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Guides building LLM-powered applications with LangChain, including agents, chains, RAG, tool calling, memory management, and vector store retrieval across multiple providers. |
| qdrant-advisor 77/100 · C | qdrant/skills | Diagnoses, troubleshoots, and advises on Qdrant deployments by loading the latest official Qdrant skills live from skills.qdrant.tech, covering performance, scaling, search quality, and monitoring. |
| qdrant-deployment-options 81/100 · B | qdrant/skills | Guides choosing a Qdrant deployment type, such as Docker, Cloud, local mode, embedded, Qdrant EDGE, or self-hosted, including when lowest latency is needed. |
| qdrant-edge 84/100 · B | qdrant/skills | Guides building on Qdrant Edge, the embedded in-process shard, including syncing with the server, BM25 and hybrid search, and snapshots. |
| qdrant-hybrid-cloud-setup 79/100 · C | qdrant/skills | Guides installing and running Qdrant Hybrid Cloud on your own Kubernetes cluster, covering storage, backups, the agent and operator, cluster exposure, and secret rotation. |
| qdrant-migration-tool 84/100 · B | qdrant/skills | Guides using the Qdrant Migration Tool CLI to move vectors, metadata, and sparse embeddings from other vector databases into Qdrant, including resuming interrupted runs. |
| qdrant-model-migration 84/100 · B | qdrant/skills | Guides migrating to a new embedding model in Qdrant without downtime, including re-embedding data, changing model dimensions, switching providers, and A/B testing models. |
| qdrant-monitoring 80/100 · B | qdrant/skills | Guides Qdrant monitoring and observability setup, including which metrics to track, Prometheus, Grafana, health checks, alerts, and log centralization. |
| qdrant-multitenancy 84/100 · B | qdrant/skills | Guides tenant isolation architecture in Qdrant for multi-tenant applications, including partitioning tenants by payload, how many collections to create, and data residency. |
| qdrant-scaling 83/100 · B | qdrant/skills | Guides Qdrant scaling decisions such as node count, sharding, vertical versus horizontal scaling, throughput, tail latency, and retention windows for expiring old vectors. |
| qdrant-search-quality 78/100 · C | qdrant/skills | Diagnoses and improves Qdrant search relevance, covering embedding model choice, hybrid search, fusion, reranking, relevance feedback, and measuring retrieval quality. |
| qdrant-sizing 84/100 · B | qdrant/skills | Sizes a Qdrant deployment before provisioning, estimating RAM, node count, and instance type from vector count and dimensions, or checking an existing estimate. |
| qdrant-version-upgrade 84/100 · B | qdrant/skills | Covers upgrading Qdrant server and SDKs without interrupting availability or losing data integrity, including rolling upgrades, version compatibility, and pre-upgrade checks. |
| redis-search 76/100 · C | redis/agent-skills | Guides Redis Search work, including FT.CREATE schema design, field types, query syntax, command selection, vector similarity, hybrid retrieval, and RAG pipelines. |
| sentence-transformers 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Generates sentence, text, and image embeddings with 5000+ pre-trained models for semantic similarity, clustering, retrieval, RAG, and semantic search. |
| amazon-aurora-postgresql 78/100 · C | aws/agent-toolkit-for-aws | Amazon Aurora PostgreSQL — creates, modifies, and advises on Aurora PostgreSQL clusters specifically (PostgreSQL-compatible engine, Aurora… |
| amazon-opensearch-service 78/100 · C | aws/agent-toolkit-for-aws | Guides migration, provisioning, search, log-analytics, trace-analytics, and Agentic AI Assistant workflows for Amazon OpenSearch Service and… |
| chroma 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple… |
| nemo-retriever 79/100 · C | NVIDIA/skills | Use when searching, extracting, ingesting, or querying a document collection with the NeMo Retriever 26.8.1 CLI, including local LanceDB indexes and… |
| paidf-curation-and-retrieval 85/100 · B | NVIDIA/skills | Use when operating PAIDF Curation and Retrieval or NVIDIA Cosmos Curator pipelines (split, filter, caption, embed, dedup, shard, image annotate) or… |
| pinecone 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and… |
| pinecone-rag 84/100 · B | github/awesome-copilot | Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. ALWAYS USE THIS SKILL when the user… |
| qdrant-clients-sdk 70/100 · C | qdrant/skills | Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments. |
| qdrant-horizontal-scaling 73/100 · C | qdrant/skills | Diagnoses and guides Qdrant horizontal scaling decisions. Use when someone asks 'vertical or horizontal?', 'how many nodes?', 'how many shards?'… |
| qdrant-hybrid-search 75/100 · C | qdrant/skills | Explains hybrid search in Qdrant. Use when someone asks 'how do I setup hybrid search?', 'how to combine keyword and semantic search?', 'sparse plus… |
| qdrant-hybrid-search-combining 76/100 · C | qdrant/skills | Fusing scores from multiple searches into a single ranked result (RRF, DBSF, custom fusion). Use when someone asks 'RRF or DBSF?', 'how to combine… |
| qdrant-hybrid-search-prefetches 76/100 · C | qdrant/skills | Constructing prefetch queries for hybrid retrieval, including sparse/dense and multi-field setups, and choosing a sparse embedding model. Use when… |
| qdrant-indexing-performance-optimization 73/100 · C | qdrant/skills | Diagnoses and fixes slow Qdrant indexing and data ingestion. Use when someone reports 'uploads are slow', 'indexing takes forever', 'optimizer is… |
| qdrant-memory-usage-optimization 76/100 · C | qdrant/skills | Diagnoses and reduces Qdrant memory usage. Use when someone reports 'memory too high', 'RAM keeps growing', 'node crashed', 'out of memory', 'memory… |
| qdrant-minimize-latency 73/100 · C | qdrant/skills | Guides Qdrant query latency optimization. Use when someone asks 'search is slow', 'how to reduce latency', 'p99 is too high', 'tail latency'… |
| qdrant-monitoring-debugging 73/100 · C | qdrant/skills | Diagnoses Qdrant production issues using metrics and observability tools. Use when someone reports 'optimizer stuck', 'indexing too slow', 'memory… |
| qdrant-monitoring-setup 73/100 · C | qdrant/skills | Guides Qdrant monitoring setup including Prometheus scraping, health probes, Hybrid Cloud metrics, alerting, and log centralization. Use when… |
| qdrant-performance-optimization 73/100 · C | github/awesome-copilot | Different techniques to optimize the performance of Qdrant, including indexing strategies, query optimization, and hardware considerations. Use when… |
| qdrant-performance-optimization 81/100 · B | qdrant/skills | Navigation hub linking sub-skills for proactive Qdrant tuning: search speed, indexing performance, and memory usage optimization. Use when planning… |
| qdrant-relevance-feedback 74/100 · C | qdrant/skills | Expanding the candidate pool via relevance feedback, as an alternative to reranking when a dense retriever is too weak. Use when someone asks about… |
| qdrant-scaling 76/100 · C | github/awesome-copilot | Guides Qdrant scaling decisions. Use when someone asks 'how many nodes do I need', 'data doesn't fit on one node', 'need more throughput', 'cluster… |
| qdrant-scaling-data-volume 72/100 · C | qdrant/skills | Guides Qdrant data volume scaling decisions. Use when someone asks 'data doesn't fit on one node', 'too much data', 'need more storage', 'vertical… |
| qdrant-scaling-qps 73/100 · C | qdrant/skills | Guides Qdrant query throughput (QPS) scaling. Use when someone asks 'how to increase QPS', 'need more throughput', 'queries per second too low'… |
| qdrant-scaling-query-volume 70/100 · C | qdrant/skills | Guides Qdrant query volume scaling. Use when someone asks 'query returns too many results', 'scroll performance', 'large limit values', 'paginating… |
| qdrant-search-quality 76/100 · C | github/awesome-copilot | Diagnoses and improves Qdrant search relevance. Use when someone reports 'search results are bad', 'wrong results', 'low precision', 'low recall'… |
| qdrant-search-quality-diagnosis 69/100 · D | github/awesome-copilot | Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches'… |
| qdrant-search-quality-diagnosis 76/100 · C | qdrant/skills | Diagnoses Qdrant search quality issues. Use when someone reports 'results are bad', 'wrong results', 'not relevant results', 'missing matches'… |
| qdrant-search-speed-optimization 76/100 · C | qdrant/skills | Diagnoses and fixes slow Qdrant search. Use when someone reports 'search is slow', 'high latency', 'queries take too long', 'low QPS', 'throughput… |
| qdrant-search-strategies 78/100 · C | qdrant/skills | Guides Qdrant search strategy selection. Use when someone asks 'should I use hybrid search?', 'how to rerank?', 'results are not relevant', 'I don't… |
| qdrant-sliding-time-window 76/100 · C | qdrant/skills | Guides sliding time window scaling in Qdrant. Use when someone asks 'only recent data matters', 'how to expire old vectors', 'time-based data… |
| qdrant-tenant-scaling 73/100 · C | qdrant/skills | Guides Qdrant multi-tenant scaling. Use when someone asks 'how to scale tenants', 'one collection per tenant?', 'tenant isolation', 'dedicated… |
| qdrant-vector-search 69/100 · D | Orchestra-Research/AI-Research-SKILLs | High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest… |
| qdrant-version-upgrade 64/100 · D | github/awesome-copilot | Guidance on how to upgrade your Qdrant version without interrupting the availability of your application and ensuring data integrity. |
| qdrant-vertical-scaling 76/100 · C | qdrant/skills | Guides Qdrant vertical scaling decisions. Use when someone asks 'how to scale up a node', 'need more RAM', 'upgrade node size', 'vertical scaling'… |
| rag-architect 84/100 · B | jeffallan/claude-skills | Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search… |
| storing-and-querying-vectors 84/100 · B | aws/agent-toolkit-for-aws | Store and query vector embeddings using Amazon S3 Vectors, a cost-effective long-term vector storage service with its own API namespace (s3vectors)… |
| tao-generate-image-embeddings 90/100 · A | NVIDIA/skills | Run TAO Data Services image embedding to turn a parquet of image filepaths into an embedding parquet using CLIP, SigLIP, or a TAO checkpoint. Use… |
| tao-mine-nearest-neighbors 87/100 · B | NVIDIA/skills | Run TAO Data Services TMM nearest-neighbor mining from embedding parquet files. Use when a workflow needs to mine source samples closest to target… |
| venice-embeddings 70/100 · C | veniceai/skills | Call POST /embeddings on Venice. Covers request shape (input, model, encoding_format, dimensions, user), text-only input (token arrays rejected)… |
| vss-deploy-video-embedding 81/100 · B | NVIDIA/skills | Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU… |
How to choose vector database skills
Qdrant publishes the largest set, one skill per task (hybrid search, sizing, scaling, latency, quality diagnosis); other stores have one skill each. Choose by the database you run.
Hosted vector stores need an API key and endpoint, listed under Before you install. Local options such as FAISS and Chroma run without an account and suit prototypes.
Search quality depends on the embedding model as much as the store. Keep a small labeled query set so the agent can measure recall before and after a change.
Ranked vector database shortlists
Related topics
SQL and Databases 116RAG and Retrieval 32Performance and Load Testing 14AWS 151Observability and Monitoring 54Deployment and Hosting 40Google Cloud 146Kubernetes 72
Find your next useful skill
Explore Rising Skills with quality scores and source reports, or search from inside your agent.
Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills