122 Claude Code skills tagged Rag. Browse all AI provider, model, or runtime-related skills in the open ClaudSkills registry — free to install, one-click via the desktop app.
Showing all 122 skills.
Document chunking with multiple strategies including semantic, recursive, and fixed-size chunking
general
Batch embedding generation with caching, rate limiting, and multiple provider support
engineering
RAG 시스템 품질 평가 및 개선을 위한 스킬입니다. RAGAS 기반 LLM-as-Judge 평가, 사용자 페르소나 시뮬레이션, 합성 데이터 생성, 평가 결과 저장 및 분석 기능을 제공합니다.
general
RAG systems analyst and architect skill. Collects and clarifies requirements through structured dialogue, then transforms unstructured business or developer descriptions into forma
engineering
Cross-encoder reranking and MMR diversity filtering for improved retrieval quality
general
Retrieval-Augmented Generation patterns for grounded LLM responses. Use when building RAG pipelines, embedding documents, implementing hybrid search, contextual retrieval, HyDE, ag
general
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug,
general
LlamaIndex agent and query engine setup for RAG-powered agents
general
Query expansion, HyDE, and multi-query generation for improved retrieval
general
Medical AI paper optimization for AI search engines (Perplexity, ChatGPT web, Elicit, Consensus, SciSpace) and RAG-based literature tools. Applies when drafting or reviewing titles
science
Add Qdrant embedding support to v3 WordPress components for RAG chatbot. Implements component-level content chunking for searchable, structured embeddings. Use when adding embeddin
general
Composite skill — query, capture, improve, and persist knowledge in one workflow. Chains recall (RAG query) → sync-memories (write durable note) → rag-curate (improve weak retrieva
general
Audit corpus distribution by source type and repo; identify coverage gaps and underindexed topics
general
Manually improve corpus quality by adding missing docs and filling retrieval gaps
general
Detect and fix stale chunks (files that changed or were deleted since last indexing)
general
Build semantic vector search systems with AgentDB for intelligent document retrieval, RAG applications, and knowledge bases using embedding-based similarity matching
general
Erstellt eine portable KI-Arbeitsumgebung auf einem USB-Stick oder beliebigem Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurie
general
Use when designing or auditing a Salesforce data architecture to support AI features — Einstein, Agentforce, Data Cloud, or custom ML models. Covers field-level data quality requir
engineering
Implement AI Coaching best practices on AnalyticDB for PostgreSQL (ADBPG): Leverage Supabase projects (training data management) + ADBPG instances with vector optimization to build
engineering
Retrieval-Augmented Generation patterns including chunking, embeddings, vector stores, and retrieval optimization Use when: rag, retrieval augmented, vector search, embeddings, sem
general
Interactive Archon integration for knowledge base and project management via REST API. On first use, asks for Archon host URL. Use when searching documentation, managing — from col
general
Interactive Archon integration for knowledge base and project management via REST API. On first use, asks for Archon host URL. Use when searching documentation, managing — from col
general
Automatically intercepts and optimizes prompts using the prompt-learning MCP server. Learns from performance over time via embedding-indexed history. Uses APE, OPRO, DSPy patterns.
general
Use when running multi-skill pipelines — new-feature, marketing-launch, design-to-code, web-creation, full-audit, rag-setup workflows
growth
Scaffold, structure, and deploy the Physical AI textbook in Docusaurus with book-aware content and RAG-ready exports. Use when creating or updating the Docusaurus site, adding chap
general
Spezialfall RAG-Architekturen mit Mandantenakten: Embedding-Speicher, Vektor-DB im EU-Hosting, Loeschkonzept Embedding bei Mandantenwiderruf, Trennung pro Mandat. Pruefraster und t
general
An official MCP server for the Chroma open-source embedding database. Enables AI agents to create collections, add documents, perform vector search, full-text search, and metadata
general
Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying re — from an
general
Use to DESIGN or REVIEW software, docs, SDKs, and repos so AI agents can consume them as a first-class audience — agent experience (AX), the agent-facing analog of UX and DX. Cover
product
Dokumente in ueberlappende Token-Chunks aufteilen fuer RAG-Pipelines und LLM-Kontextfenster. Zero Dependencies.
general
PDF/DOCX/XLSX/PPTX generation and parsing on Cloudflare Workers. Covers CF Browser Rendering → PDF, pdf-lib Worker-native generation, docx/exceljs output, pptxgenjs slides, and RAG
engineering
Compute and analyze embeddings for dataset quality, distribution comparison, semantic deduplication, diversity measurement, and similarity-based filtering. Covers sentence-transfor
general
Embed an idea title+summary via HF inference; check cosine similarity vs the embeddings store.
general
Embedding backends (InsightFace/PyTorch+ONNXRuntime vs TensorRT). Use when optimizing embedding throughput or debugging drift/fallbacks.
engineering
Use when designing embedding strategies that fuse semantic and structural information for knowledge graphs. Invoke when user mentions node embeddings, structural embeddings, semant
general
Generate and manage text embeddings for semantic search, clustering, and similarity tasks
tools
Tune a vector index — HNSW graph parameters and quantization — to hit a recall target at the lowest latency and memory, by sweeping settings against a fixed query set instead of tr
general
Embedding Models — выбор, настройка и отладка моделей эмбеддингов. ИСПОЛЬЗУЙ когда выбираешь модель embeddings (E5, BGE, Jina, Giga), настраиваешь ONNX backend, исправляешь dimensi
general
Optimizing vector embeddings for RAG systems through model selection, chunking strategies, caching, and performance tuning. Use when building semantic search, RAG pipelines, or doc
engineering
Implement reusable embedding functions using Gemini embedding models via LangChain with proper error handling and batching for sitemap-crawled content.
general
Diagnose the health of an embedding set before blaming the retriever — checking normalization, dimensionality, near-duplicates, degenerate vectors, and corpus/query distribution mi
general
Guide to selecting and optimizing embedding models for vector search applications.
general
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embeddi — from bg
general
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embeddi — from ge
general
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embeddi — from ma
general
[STUB - Not implemented] Asymmetric embedding strategy with RETRIEVAL_DOCUMENT for ingestion and RETRIEVAL_QUERY for queries. PROACTIVELY activate for: [TODO: Define on implementat
general
Embed and execute external binaries (sidecars) in Tauri apps: configuration, cross-platform executable naming, and Rust/JavaScript spawn APIs. USE WHEN bundling a CLI or server bin
engineering
Forensische Pruefung Prompt-Injection-Risiko: Indirekte Prompt-Injection ueber hochgeladene Dokumente, RAG-Vergiftung, Datenexfiltration. Pruefraster fuer Reviewer-Audit, Sandbox-T
general
Citation discipline for AI-generated outputs. When to cite, what counts as a verifiable citation, URL + quote + file-path verification, marking inference vs fact, what NOT to cite.
science
Build RAG systems and semantic search with Gemini embeddings (gemini-embedding-001). 768-3072 dimension vectors, 8 task types, Cloudflare Vectorize integration. Prevents 13 documen
engineering
Image embedding size limits in markdown — base64 bloats 33%, use file references for images over 50KB
general
Build the internal link graph for a site, run PageRank-style authority distribution, detect orphan pages, and recommend new internal links via embedding-based semantic similarity (
engineering
Build and query vector stores with LangChain 1.0 without getting burned by flipped score semantics, embedding-dim mismatches, reranker quirks, and chunk-splitter bugs. Use when bui
general
Use when you need to reduce LLM API spend, control token usage, route between models by cost/quality, implement prompt caching, or build cost observability for AI features. Trigger
engineering
Design and implement ML operations — model registry, serving patterns, deployment strategies (shadow/canary/blue-green), drift detection, feature stores, retraining triggers, and p
engineering
Generate cross-modal embeddings with CLIP, SigLIP, and ImageBind for text-image-audio search. Activate on: multimodal search, text-to-image search, cross-modal embeddings, CLIP emb
tools
Queries Notion databases and pages via the Notion API v1, then renders content blocks into PDF via WeasyPrint. Extracts text, tables, and inline images and preserves heading hierar
general
Embeddings via OmniRoute using OpenAI /v1/embeddings format with auto-fallback across text-embedding-3-large, Voyage, Cohere, Gemini embeddings, Jina. Use when the user needs vecto
general
Use local Codex/Claude JSONL logs as evidence, then produce a human-written daily diary summary and write it into Obsidian. Keep directory filtering (for example rag-flow/rag-recal
general
pgvector performance optimization: HNSW vs IVFFlat index selection and tuning, ef_search / m / ef_construction parameters, iterative scanning for filtered queries, scalar and binar
general
Use when managing prompts in production at scale: versioning prompts, running A/B tests on prompts, building prompt registries, preventing prompt regressions, or creating eval pipe
general
Qdrant Operations — управление коллекциями Qdrant, sparse vectors, snapshots. ИСПОЛЬЗУЙ когда создаёшь/настраиваешь коллекции Qdrant, мигрируешь с ChromaDB, настраиваешь named vect
general
Optimize accuracy for RAG (Retrieval-Augmented Generation) systems. Covers: DB schema design, chunking strategies, retrieval optimization, accuracy testing, and anti-hallucination
engineering
Use when the user asks to design RAG pipelines, optimize retrieval strategies, choose embedding models, implement vector search, or build knowledge retrieval systems.
general
Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying re — from ma
general
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents — from vu
engineering
Evaluates RAG pipeline quality across retrieval (precision, recall, MRR) and generation (groundedness, hallucination rate). Triggers on: "audit RAG pipeline", "RAG quality", "hallu
engineering
Guide an agent through property search, buyer/renter preference capture, and evidence-backed shortlist notes from structured listing data.
science
RAG pipeline design — document chunking, embedding strategies, retrieval optimization, and answer generation
general
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales — from chr
general
RAG-grounded code generation with source citations. Triggers on: grounded code, ground this, cite sources, show me with sources, how do I with attune, reference attune docs, verify
general
Build RAG systems for construction knowledge bases. Create searchable AI-powered construction document systems
general
Curador do corpus RAG. Gerencia adição, organização e manutenção do conhecimento do projeto. Garante qualidade e acessibilidade.
general
Build production document ingestion pipelines with chunking, embedding, and vector DB storage. Activate on: document ingestion, chunking strategy, embedding pipeline, vector DB ing
engineering
Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use whe
general
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo
general
Retrieval-Augmented Generation patterns on Oracle Cloud Infrastructure — embeddings, vector stores, hybrid search, reranking, and production RAG architecture
engineering
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HN — from fa
general
Hybrid search combining semantic and keyword retrieval for RAG pipelines. Implement BM25 + dense vector search with fusion strategies.
general
Design and implement Retrieval-Augmented Generation systems — chunking strategy, embedding selection, vector store setup, retrieval pipeline, re-ranking, and evaluation
general
RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and retrieval optimization.
general
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building d — from bg
general
Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building d — from ma
general
Интеграция RAG (Retrieval Augmented Generation) с xAI Grok Collections и Google Gemini. Используй этот skill когда нужно добавить AI-чат с базой знаний, настроить RAG систему, инте
general
Build RAG (Retrieval-Augmented Generation) knowledge bases for businesses — turn documents, SOPs, policies, product manuals into AI assistants that answer questions accurately. Use
general
RAG architecture: embeddings, chunking strategies, hybrid search (BM25 + vector), reranking, CRAG/self-correcting, multi-hop reasoning, evaluation metrics. Triggers: RAG, embedding
engineering
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eva
general
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency — from Orc
general
Details on the Retrieval Augmented Generation pipeline, Ingestion, and Vector Search.
general
Design and architect RAG (Retrieval-Augmented Generation) pipelines. Covers vector DB selection, chunking strategies, hybrid retrieval (vector + knowledge graph), semantic caching,
engineering
Build retrieval-augmented generation systems that ground LLM responses in your data
general
Conception de pipelines RAG (Retrieval-Augmented Generation). Se déclenche avec "RAG", "retrieval augmented", "vector database", "embeddings", "knowledge base", "Pinecone — from ge
general
트리거: "RAG 파이프라인", "벡터 검색", "문서 임베딩", "RAG 만들어줘", "retrieval augmented generation" 수행: 문서 청킹 전략 설계 → 임베딩 → 벡터 DB 저장 → 검색 파이프라인 코드 생성 출력: 완전한 RAG 파이프라인 코드 (LangChain 또는 LlamaIndex 기반
general
RAG-specific prompt engineering techniques and best practices. RAG 專屬提示工程技術與最佳實踐。 Use when: building retrieval-augmented generation pipelines, grounding LLM answers in documents, h
general
High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid sear — from qd
engineering
Use when designing or fixing the retrieval side of a RAG system, choosing chunking strategy (fixed-size / recursive / semantic), implementing hybrid search (BM25 + dense) with RRF
general
Search RAG database for relevant content. Use for semantic queries over processed documents, code, or papers.
general
Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multil — from UK
general
Build Retrieval Augmented Generation (RAG) pipelines with vector databases, embeddings, and context-aware responses. Adapted from Anthropic's Claude Cookbooks.
general
Patterns for wrapping any agent with RAG context from Qdrant. Use to add persistent memory to imported or external agents.
tools
Research GitHub, GitLab, and Bitbucket repositories using DeepWiki MCP server. Use when exploring unfamiliar codebases, understanding project architecture, or asking questions abou
science
Explains, summarizes, and turns Matthias Luebken's talk on embedding Pi-style coding agents into safe product-design artifacts: tool-contract sketches, guardrail checklists, sessio
product
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies
general
Audit Vector DB coverage -- compares the live filesystem manifest against the ChromaDB index to identify coverage gaps.
general
Removes stale and orphaned chunks from the ChromaDB vector store for files that have been deleted or renamed. Use after files are removed or moved to keep the vector index in sync
general
Ingests repository files into the ChromaDB vector store. Builds or updates the vector index from a manifest or directory scan using ingest.py. Use when new files need to be indexed
general
Interactively initializes the Vector DB plugin. Guided discovery asks which folders to index, confirms the manifest, then scaffolds vector_profiles.json for high-performance In-Pro
general
Start the Native Python ChromaDB background server. Use when semantic search returns connection refused on port 8110, or when the user wants to enable concurrent agent read/writes.
engineering
Vector database operations — Pinecone, Weaviate, Qdrant, ChromaDB. Indexing, querying, filtering, and managing
general
Semantic search skill for retrieving code and documentation from the ChromaDB vector store. Use when you need concept-based search across the repository (Phase 2 of the 3-phase sea
general
This skill should be used to watch a long-running background job (ffmpeg/media encode, qmd or other embedding/vector-DB run, batch agent/LLM pipeline, or a real-browser/agent-brows
general
Efficiently perform web searches using the mcp-local-rag server with semantic similarity ranking. Use this skill when you need to search the web for current information, research t
science
Use this skill to audit RAG and AI application security, including retrieval boundaries, prompt injection, citations, memory, and data exposure. Do not use it as a scanner or explo
security
Comprehensive RAG evaluation with retrieval metrics, generation quality, and end-to-end testing. Use this skill when measuring and improving RAG system performance. Activate when:
engineering
Generates tailored giskard.checks evaluation suites for RAG (Retrieval-Augmented Generation) systems. Use whenever a user describes a Q&A bot grounded in documents, a knowledge-bas
security
Create and work with token embeddings for LLMs. Use this skill whenever you need to understand token embeddings, create embedding layers in PyTorch, add positional embeddings (abso
engineering
This skill should be used when a SKILL.md file needs compression, deduplication, or token reduction. It provides an embedding-based compression pipeline that detects and removes re
general
Trigger a full or incremental reindex of the RAG corpus
general
Examine what's actually stored in the index for specific items
general
Evaluate retrieval quality from the local RAG index
general
Storing images at embed size loses the original:
general
RAG architecture for academic knowledge retrieval and synthesis
science
SKILL.md files, not affiliated with, endorsed by, or sponsored by Anthropic.