What are the best Claude Code skills for RAG and vector search?
google-cloud-solution-rag-enterprise-search-gke-sqldb from google/skills is the highest-scoring Claude Code skill for RAG and vector search, at 87/100 (grade B) on the Suede Skill Check. The table below compares the top 15 of 55 listed RAG skills from 7 repositories by score, publisher and license, using the October 22, 2026 snapshot of SuedeAI.directory.
- 55 listed RAG skills
- 10 full pages scoring 80+
- 9 repositories
Compare 15 Claude Code skills for RAG and vector search
Ranked by Suede Skill Check score. Linked names open the directory listing; scores come from the published rubric.
| Skill | Publisher | Suede Skill Check | License | What it does |
|---|---|---|---|---|
| google-cloud-solution-rag-enterprise-search-gke-sqldb | Google Official google/skills | 87/100 · B | Apache-2.0 | Generates architecture, design, and deployment guidance for a RAG-capable enterprise search system on Google Cloud, using a vector-enabled SQL database and Kubernetes containers. |
| paidf-curation-and-retrieval | NVIDIA Official NVIDIA/skills | 85/100 · B | CC-BY-4.0 AND Apache-2.0 | Use when operating PAIDF Curation and Retrieval or NVIDIA Cosmos Curator pipelines (split, filter, caption, embed, dedup, shard, image annotate) or… |
| qdrant-edge | Qdrant Official qdrant/skills | 84/100 · B | Apache-2.0 | Guides building on Qdrant Edge, the embedded in-process shard, including syncing with the server, BM25 and hybrid search, and snapshots. |
| qdrant-migration-tool | Qdrant Official qdrant/skills | 84/100 · B | Apache-2.0 | 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 | Qdrant Official qdrant/skills | 84/100 · B | Apache-2.0 | 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. |
| rag-architect | jeffallan jeffallan/claude-skills | 84/100 · B | MIT | Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search… |
| agent-platform-rag-engine-management | Google Official google/skills | 84/100 · B | Apache-2.0 | Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files… |
| pinecone-rag | GitHub Official github/awesome-copilot | 84/100 · B | Apache-2.0 | Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. ALWAYS USE THIS SKILL when the user… |
| rag-eval | NVIDIA Official NVIDIA/skills | 81/100 · B | Apache-2.0 | Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use… |
| rag-perf | NVIDIA Official NVIDIA/skills | 81/100 · B | Apache-2.0 | Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for… |
| amazon-opensearch-service | aws Official aws/agent-toolkit-for-aws | 78/100 · C | Apache-2.0 | Guides migration, provisioning, search, log-analytics, trace-analytics, and Agentic AI Assistant workflows for Amazon OpenSearch Service and… |
| pinecone | Orchestra-Research Orchestra-Research/AI-Research-SKILLs | 77/100 · C | MIT | Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and… |
| langchain | Orchestra-Research Orchestra-Research/AI-Research-SKILLs | 77/100 · C | MIT | Guides building LLM-powered applications with LangChain, including agents, chains, RAG, tool calling, memory management, and vector store retrieval across multiple providers. |
| sentence-transformers | Orchestra-Research Orchestra-Research/AI-Research-SKILLs | 77/100 · C | MIT | Generates sentence, text, and image embeddings with 5000+ pre-trained models for semantic similarity, clustering, retrieval, RAG, and semantic search. |
| qdrant-scaling | GitHub Official github/awesome-copilot | 76/100 · C | MIT | 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… |
Questions and answers
Which RAG skill has the highest Suede Skill Check score?
google-cloud-solution-rag-enterprise-search-gke-sqldb from google/skills scores 87/100, grade B, the highest of the 55 listed RAG skills in the October 22, 2026 snapshot. It earns full points for structural checks, recent maintenance and instruction depth. paidf-curation-and-retrieval from NVIDIA/skills follows at 85/100.
How do I install a RAG skill in Claude Code?
Run npx skills add with the skill folder's GitHub URL from your project, or copy the folder into .claude/skills/ and Claude Code loads it when a request matches its description. For google-cloud-solution-rag-enterprise-search-gke-sqldb, run: npx skills add https://github.com/google/skills/tree/main/skills/cloud/google-cloud-solution-rag-enterprise-search-gke-sqldb. Each full skill page on SuedeAI.directory lists the same steps for Claude Code and Codex.
Are these RAG skills free?
All 15 RAG skills on this page are published in public GitHub repositories and cost nothing to download. Every one uses an open-source or open-content license, led by Apache-2.0 (9), MIT (5) and CC-BY-4.0 AND Apache-2.0 (1), so you can use and adapt the files at no cost under those terms. One skill names credentials for an outside service; each full page lists them under Before you install.
Do these RAG skills work with Codex and Cursor?
Yes. Each of the 15 RAG skills on this page is a SKILL.md folder in the Agent Skills format, which Claude Code, Codex and Cursor all read. The skills CLI (npx skills add) installs every one of them into Claude Code, Codex, Cursor and other agents, and each full skill page adds a project-level copy into .claude/skills for Claude Code and .agents/skills for Codex. 3 of them declare compatibility in the SKILL.md frontmatter.
How does SuedeAI.directory rank RAG skills?
By Suede Skill Check score from 0 to 99, which adds structure, description quality, instruction depth, bundled files, maintenance and curated-list citations, all read from each skill's published files. A skill joins this page when its name or summary matches the RAG and vector search keyword map; each repository fills at most three rows, so the table compares publishers.
Which RAG skills come from official publishers?
google-cloud-solution-rag-enterprise-search-gke-sqldb and agent-platform-rag-engine-management from Google, paidf-curation-and-retrieval, rag-eval and rag-perf from NVIDIA, qdrant-edge, qdrant-migration-tool and qdrant-model-migration from Qdrant, pinecone-rag and qdrant-scaling from GitHub and amazon-opensearch-service from aws are published by the company behind the tool, marked Official in the table.
More Claude Code skills by task
Presentations · Playwright and Browser Testing · Terraform · SEO · Code Review · Git and Pull Requests · MCP Servers · Data Analysis · Kubernetes · AWS · Security Audits · Email · Video · iOS and Swift · Flutter and Dart · React and Next.js · LLM Evals · SQL and Databases · Technical Documentation · UI Design
Browse by category: AI Agents and LLM Engineering · Data, Analytics and Databases · Developer Tools and Frameworks.