RAG

Refresh Pinecone article embeddings after MDX article changes or RAG chunking and metadata changes. Use when content updates should be reflected in chat retrieval or when the vectorization pipeline changes.

AgentDB memory system with HNSW vector search. Use when: need to store patterns, search for solutions, semantic lookup. Skip when: no learning needed, ephemeral tasks.

Tenant-specific RAG service for company knowledge in the voice assistant platform.

Use this skill when the user asks to add a reference repo or index a GitHub repository for search. Clones, auto-detects file types, indexes with QMD, and embeds.

Creates an Ampi-ready SQLite vault from a folder of documents (md, markdown, txt, docx, doc) or an existing SQLite source table. Builds keyword search (FTS5), optional sparse semantic search, a search_schema contract, and an amplify_search_manifest so Ampi tools (search_vault_keyword, search_vault_semantic, search_vault_deep, lookup_vault_records) work immediately. Use when the user wants to build a new Ampi vault, ingest documents into a searchable SQLite database, check whether an existing vault passes the Ampi search contract, or re-build a vault from updated documents. Don't use for general SQLite database creation, non-Ampi document stores, CSV imports, querying an existing vault, or adding documents to an already-built vault without re-ingesting.

LLMs, prompt engineering, RAG systems, LangChain, and AI application development

This skill should be used when the user asks about "Docling chunking", "HybridChunker", "HierarchicalChunker", "structure-aware chunking", "Docling metadata extraction", "export modes", "DOC_CHUNKS vs MARKDOWN", "chunking strategies", or mentions preparing documents for RAG with Docling.

Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming

RAG Architect - POWERFUL

World-class expert in prompt engineering, LLM fine-tuning, RAG systems, and AI/ML workflows. Use when crafting prompts, designing AI agents, building knowledge bases, implementing retrieval systems, or optimizing LLM performance at production scale.

Evaluate LLM systems using automated metrics, LLM-as-judge, and benchmarks. Use when testing prompt quality, validating RAG pipelines, measuring safety (hallucinations, bias), or comparing models for production deployment.

Process and transform FAQ documents (xlsx, word, pdf, txt) into RAG-optimized format. Use when working with FAQ files, knowledge base documents, or when the user needs to analyze and restructure FAQ content for RAG systems.

Retrieval-Augmented Generation (RAG) system design patterns, chunking strategies, embedding models, retrieval techniques, and context assembly. Use when designing RAG pipelines, improving retrieval quality, or building knowledge-grounded LLM applications.

Build RAG systems and semantic search with Gemini embeddings (gemini-embedding-001). 768-3072 dimension vectors, 8 task types, Cloudflare Vectorize integration. Prevents 13 documented errors. Use when: vector search, RAG systems, semantic search, document clustering. Troubleshoot: dimension mismatch, normalization required, batch ordering bug, memory limits, wrong task type, rate limits (100 RPM).

AI session compression techniques for managing multi-turn conversations efficiently through summarization, embedding-based retrieval, and intelligent context management.

Build neuro-symbolic LLM applications with Synalinks framework. Use when working with DataModel, Program, Generator, Module, training LLM pipelines, in-context learning, structured output, JSON operators, Branch/Decision control flow, FunctionCallingAgent, RAG/KAG, or Keras-like LLM workflows.

Qdrant vector database integration patterns with LangChain4j. Store embeddings, similarity search, and vector management for Java applications. Use when implementing vector-based retrieval for RAG systems, semantic search, or recommendation engines.

Pattern for progressively refining context retrieval to solve the subagent context problem

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

基于用户画像和向量化笔记提供个性化对话。当用户需要个性化交流、上下文感知的回应，或希望 AI 记住并引用其之前的想法和笔记时使用。

Build document Q&A with Gemini File Search - fully managed RAG with automatic chunking, embeddings, and citations. Upload 100+ file formats, query with natural language. Use when: document Q&A, searchable knowledge bases, semantic search. Troubleshoot: document immutability, storage quota (3x), chunking config, metadata limits (20 max), polling timeouts, displayName dropped (Blob uploads), grounding lost (JSON mode), tool conflicts (googleSearch + fileSearch).

Build conversational AI voice agents with ElevenLabs Platform. Configure agents, tools, RAG knowledge bases, agent versioning with A/B testing, and MCP security. React, React Native, or Swift SDKs. Prevents 34 documented errors. Use when: building voice agents, AI phone systems, agent versioning/branching, MCP security, or troubleshooting @11labs deprecated, webhook errors, CSP violations, localhost allowlist, tool parsing errors.

LangChain implementation patterns with templates, scripts, and examples for RAG pipelines

Ingest documents into Elroy memory

Query the DeepWiki MCP server for GitHub repository documentation, wiki structure, and AI-powered questions.

Implements vector search with Pinecone for semantic similarity and RAG applications. Use when building embeddings-based search, recommendation systems, or retrieval-augmented generation.

Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

Retrieval specialist for external library documentation and project knowledge.

Build and maintain AI-accessible knowledge bases for projects

Comprehensive AI/ML development guide for LangChain, LangGraph, and ML model integration in FastAPI. Use when building LLM applications, agents, RAG systems, sentiment analysis, aspect-based analysis, chain orchestration, prompt engineering, vector stores, embeddings, or integrating ML models with FastAPI endpoints. Covers LangChain patterns, LangGraph state machines, model deployment, API integration, streaming, error handling, and best practices.

Intelligent token optimization through Qdrant-powered semantic caching and long-term memory. Use for (1) Semantic Cache - avoid LLM calls entirely for semantically similar queries with 100% token savings, (2) Long-Term Memory - retrieve only relevant context chunks instead of full conversation history with 80-95% context reduction, (3) Hybrid Search - combine vector similarity with keyword filtering for technical queries, (4) Memory Management - store and retrieve conversation memories, decisions, and code patterns with metadata filtering. Triggers when needing to cache responses, remember past interactions, optimize context windows, or implement RAG patterns.

Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. Prevents 10 documented errors including vector store upload bugs, temperature parameter conflicts, memory leaks. Deprecated (sunset August 2026); use openai-responses for new projects. Use when: maintaining legacy chatbots, implementing RAG with vector stores, or troubleshooting thread errors, vector store delays, uploadAndPoll issues.

Leverage Retrieval Augmented Generation to retrieve relevant information from a a LlamaCloud Index. Requires the llama_cloud_services package and LLAMA_CLOUD_API_KEY as an environment variable.

Build RAG systems - embeddings, vector stores, chunking, and retrieval optimization

Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production. This skill covers LLM integration patterns, RAG architecture, prompt engineering that scales, AI UX that users trust, and cost optimization that doesn't bankrupt you. Use when: keywords, file_patterns, code_patterns.

Build semantic search with Cloudflare Vectorize V2. Covers async mutations, 5M vectors/index, 31ms latency, returnMetadata enum changes, and V1 deprecation. Prevents 14 errors including dimension mismatches, TypeScript types, testing setup. Use when: building RAG or semantic search, troubleshooting returnMetadata, V2 timing, metadata index, dimension errors, vitest setup, or wrangler --json output.

CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.

Build and deploy production-ready generative AI agents using Vertex AI, Gemini models, and Google Cloud infrastructure with RAG, function calling, and multi-modal capabilities. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

LangChain JS/TS framework for building LLM-powered applications - models, chains, tools, and RAG patterns.

Build or update a code graph index for C#/.NET repositories using ragsharp-graph. Triggers: build index, update index, refresh index, code graph, dependency graph, static analysis, Roslyn, line numbers.

Document Q&A with RAG using Supabase pgvector store.

High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.

Build PRISMA 2020-compliant systematic literature review systems with RAG-powered analysis in VS Code. Use when researcher needs automated paper retrieval (Semantic Scholar, OpenAlex, arXiv), AI-assisted PRISMA screening (50% or 90% threshold), vector database creation (ChromaDB), or research conversation interface. Supports knowledge_repository (comprehensive, 15K+ papers, teaching/exploration) and systematic_review (publication-quality, 50-300 papers, meta-analysis) modes. Conversation-first workflow with 7 stages.

Search the Met Museum Open Access Paintings collection using semantic search, find similar artworks, and search by image. Use this when users ask about art, paintings, museum collections, or want to find artworks by description, visual similarity, or artist.

Build production-ready LLM applications with chains, agents, memory, tools, and RAG pipelines using the LangChain framework

Upload and process data into local Weaviate collections with support for single objects, batch uploads, and multi-modal content

Use this skill for semantic code search and codebase understanding. CCG-RAG provides intelligent retrieval using code embeddings and knowledge graphs.

Build production-ready Tavily integrations with best practices baked in. Reference documentation for developers using coding assistants (Claude Code, Cursor, etc.) to implement web search, content extraction, crawling, and research in agentic workflows, RAG systems, or autonomous agents.

Build document Q&A and searchable knowledge bases with Google Gemini File Search - fully managed RAG with automatic chunking, embeddings, and citations. Upload 100+ file formats (PDF, Word, Excel, code), configure semantic search, and query with natural language. Use when: building document Q&A systems, creating searchable knowledge bases, implementing semantic search without managing embeddings, indexing large document collections (100+ formats), or troubleshooting document immutability errors (delete+re-upload required), storage quota issues (3x input size for embeddings), chunking configuration (500 tokens/chunk recommended), metadata limits (20 key-value pairs max), indexing cost surprises ($0.15/1M tokens one-time), operation polling timeouts (wait for done: true), force delete errors, or model compatibility (Gemini 2.5 Pro/Flash only).