RAG and Retrieval skills for Claude Code and Codex
Skills for retrieval-augmented generation: designing chunking, embeddings and reranking, building knowledge bases from web content and documents, and running RAG on LangChain, LlamaIndex, NVIDIA's RAG Blueprint and NeMo Retriever, Google's RAG Engine, Azure Foundry IQ and Redis semantic caching. They help an agent ground answers in your own content.
Highest-scoring RAG skills in the October 22, 2026 snapshot: google-cloud-solution-rag-enterprise-search-gke-sqldb from google/skills (87/100), qdrant-model-migration from qdrant/skills (84/100) and train-sentence-transformers from huggingface/skills (83/100). Scores come from the Suede Skill Check.
- 32 listed skills
- 14 repositories
- 8 with full pages
27 from official publishers. 2 bundle scripts. 3 connect to an outside service. Listed in AI Agents and LLM Engineering (21), Data, Analytics and Databases (9), Developer Tools and Frameworks (1), DevOps and Cloud (1).
All 32 RAG skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| google-cloud-solution-rag-enterprise-search-gke-sqldb 87/100 · B | google/skills | 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. |
| 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-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-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. |
| 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. |
| redis-semantic-cache 75/100 · C | redis/agent-skills | Guides semantic caching of LLM responses with Redis LangCache on Redis Cloud, including search and set calls, similarity threshold tuning, and per-task caches. |
| 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. |
| train-sentence-transformers 83/100 · B | huggingface/skills | Trains and fine-tunes sentence-transformers models, including bi-encoders, cross-encoders, sparse encoders, and multi-vector encoders, with guidance on loss selection, hard-negative mining, evaluators, and Hub publishing. |
| agent-platform-rag-engine-management 84/100 · B | google/skills | Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files… |
| 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… |
| firecrawl-knowledge-base 74/100 · C | firecrawl/skills | Build a knowledge base from web content with Firecrawl. Use for local reference docs, RAG-ready chunks, fine-tuning datasets, documentation mirrors… |
| firecrawl-knowledge-ingest 71/100 · C | firecrawl/skills | Export documentation portals, help centers and API reference sites into local markdown or JSON with Firecrawl browser, including pages that render… |
| foundry-iq 71/100 · C | microsoft/azure-skills | Foundry IQ knowledge bases. WHEN: make local or Blob documents searchable; create/diagnose KBs; triage unsupported connectors or multi-source KB… |
| langchain-rag 69/100 · D | langchain-ai/langchain-skills | INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings… |
| llamaindex 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Data framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector… |
| mini-context-graph 74/100 · C | github/awesome-copilot | A persistent, compounding knowledge base combining Karpathy's LLM Wiki pattern with a structured knowledge graph. Ingest documents once — the LLM… |
| 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… |
| nemo-retriever-mcp 68/100 · D | NVIDIA/skills | Use when a task needs to search or add documents through NeMo Retriever MCP. |
| nemotron-retrieval-recipes 79/100 · C | NVIDIA/skills | Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes. |
| neon-ai-gateway 79/100 · C | neondatabase/agent-skills | One API and one credential for frontier and open-source LLMs and embedding models, built into your Neon branch and powered by Databricks. Use when a… |
| 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-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-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-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-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… |
| 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… |
| rag-blueprint 77/100 · C | NVIDIA/skills | NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change… |
| rag-eval 81/100 · B | NVIDIA/skills | Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use… |
| rag-perf 81/100 · B | NVIDIA/skills | Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for… |
| retrieving-developer-knowledge 87/100 · B | google/skills | Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI/Gemini, Android, Chrome, Web, Flutter, Go… |
| 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 RAG skills
Choose by where your documents live and which stack you run. Framework skills (langchain-rag, llamaindex) fit an app you are writing; platform skills (RAG Engine, Foundry IQ, NVIDIA RAG Blueprint) manage a hosted corpus for you.
Retrieval quality is mostly embedding and chunking choices. rag-architect and the sentence-transformers skills cover those decisions, and rag-eval measures the result before you tune further.
Ingestion skills such as firecrawl-knowledge-base call a crawling service and read its API key. Respect each site's terms and keep the source list you crawl.
Ranked RAG shortlists
Related topics
Vector Databases and Embeddings 57SQL and Databases 116Google Cloud 146AI Agent Builders 56Context Engineering and Agent Memory 31Fine-Tuning and Model Training 127LLM APIs and SDKs 28Machine Learning 29
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