RAG and vectors skills

damoqiongqiu/mcp-local-rag

Skill Claude CodeCodex

Tools for importing code and documents into a local search index, including source code, PDF, DOCX, TXT, and Markdown files.

dzmitrys-dev/supamem

Skill Claude CodeCodex

Project-agnostic dual-memory tooling — semantic + structural memory for AI coding agents.

datris/datris-platform-oss

Skill Claude CodeCodex

Use Datris as the data platform for this project. Load this skill whenever the work involves getting data in from a file, an API, a website, a database or a document set; validating, transforming or landing data in a database, warehouse, object store or vector store; building a RAG or semantic-search index; scheduling…

SylphxAI/coderag

Skill Claude CodeCodex

npx @sylphx/locus --root=/absolute/path/to/project.

Kromatic-Innovation/athenaeum

Skill Claude CodeCodex

Build a custom source → raw-intake adapter for Athenaeum. Use when someone wants to feed an external source (an API, an export file, a message feed, a scraper, another tool's output) into an Athenaeum knowledge base, asks "how do I write an adapter / integration for athenaeum", or wants to turn some data source into…

timwukp/agent-skills-best-practice

Skill Claude CodeCodex

Build production-ready AWS Bedrock AgentCore Harness agents end to end — declarative model + prompt, managed/BYO Memory, built-in Browser, Code Interpreter, Web Search and Knowledge Bases (RAG), Gateway/MCP tools + rate limits, inline functions, Skills (incl. AWS catalog), versioning + endpoints, advanced config…

imkohenauser/antigravity-starter-ja

Skill Claude CodeCodex

A skill that builds a searchable map of a code repository and traces how files and named pieces of code depend on one another.

papago2355/pharma-agent

Skill Claude CodeCodex

Inference-time system-prompt rules for Korean multi-turn RAG agents. Hard imperatives + Korean few-shots + decision tables for ambiguous phrasings — followup handling, persistent-filter durability, particle stripping, verifier cross-turn context, hedge-phrase suppression, LLM-over-regex routing. Distilled from Korean…

ui-insight/vandalizer

Skill Claude Code

Talk to the Vandalizer Management API — /api/mgmt/v1. Use when the user says "/vandalizer-api", asks to query the management API, pastes a vklive… key, asks to check Vandalizer dev/prod stats, validation runs, workflows, audit log, or wants to run a workflow/validation/extraction via the management surface.

mr-kelly/far

Skill Claude Code

File-Augmented Retrieval — generate persistent .meta sidecar files for PDFs, images, spreadsheets, videos and more, making every binary file readable to AI coding agents.

ivo-toby/postgram

Skill Claude CodeCodex

Use the pgm CLI (Postgram) to persist, search, and link knowledge across sessions. Invoke whenever the user wants to remember something across conversations, recall prior context, search their personal knowledge base, track tasks, or explore relationships between stored entities. Assumes pgm is on PATH, PGMAPIURL is…

bugrabilge/bilge-development-kit

Skill Claude CodeCodex

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, AI assistant design, prompt management, LLMOps monitoring, conversational interfaces, and context management.

DSmmartin/skills_talk_agent_camp_2026

Skill Claude CodeCodex needs its repo

Complete schema drift repair for the Ghost Contributors NL2SQL system. Patches all four layers (YAML contract, ChromaDB RAG chunks, NL2SQL prompt, RAG prompt) using validated tooling. Includes dry-run preview, step-by-step fallback, validation, and rollback.

BigCactusLabs/dead-letter

Skill Claude CodeCodex

Convert .eml email files (Gmail, Outlook, Apple Mail, Thunderbird exports, email archives) to Markdown with YAML front matter for reading, summarizing, RAG, or building a local email archive. Use when a task involves a .eml file or folder, exported email, or turning email into Markdown. Runs locally via uvx or the…

armelhbobdad/oh-my-skills

Skill Claude CodeCodex

Use when builds data transformation flows on top of cocoindex — a Python framework with a Rust engine for ultra-performant, incremental data indexing (ETL, RAG ingestion, knowledge graphs, vector search). Covers the flow-building public API: FlowBuilder, DataScope, DataSlice, Flow, FlowLiveUpdater, sources, targets…

Youchu-lawhub/legal-kb-builder

Skill Claude CodeCodex

A tool for turning legal documents and other source material into a searchable local knowledge base. It supports sources such as PDF, DOCX, images, Markdown, and question-and-answer sets.

jcode-works/jcode-ragmir

Skill Claude CodeCodex

Retrieve cited local project context for developer agents. Use Ragmir for document indexing, precise evidence, source audits, and MCP access to a repository corpus.

grandamenium/multimodal-rag

Skill Claude CodeCodex

Set up and manage a fully local multimodal knowledge base using Gemini Embedding 2 and ChromaDB. Use when user wants to create a business knowledge base, ingest videos/images/audio/docs for RAG, query their knowledge base, or set up multimodal embeddings for their Claude Code agent.

mickeyyaya/refactoring-skills

Skill Claude CodeCodex

Use when designing or reviewing AI/ML integration code — covers RAG pipeline design, prompt engineering, structured output with schema validation, tool use/function calling, LLM error handling, token budget management, hallucination mitigation, and AI/ML anti-patterns with examples in TypeScript and Python.

NOMARJ/sigil

Skill Claude CodeCodex

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.

hybridlabor-api/bdb-dev-optimized-agent-skills

Skill Claude CodeCodex

Production-ready patterns for building LLM applications, inspired by Dify and industry best practices.

masteryee-labs/Tool.Agent-Harness-Deploy

Skill Claude CodeCodex

Local hybrid retrieval (BM25 + ChromaDB vector + BGE-Reranker) over /.deep-memory hot and cold stores. Use when high-accuracy code/solution retrieval is needed and hallucination must be minimized. Typically invoked by deep-memory.

nuetzliches/powerbrain

Skill Claude CodeCodex

Use when searching company knowledge, querying internal documentation, checking policies, or accessing the Powerbrain knowledge base via MCP.

achaykovsky/Cursor-Usage-Templates

Skill Claude CodeCodex

Performs LLM system design review (not code review) across hallucination risks, context explosion, retrieval quality, prompt coupling, observability, evaluation, confidence calculation, deterministic business logic, tenant isolation, future tool calling, cost, and latency. Use for bot/RAG architecture review…