Agent Skills

elizaOS (crypto skills)

cryptoskills

TypeScript framework and character system for building autonomous, multi-platform AI agents with onchain (Solana) integrations and RAG memory.

DSPy — Declarative LM Programming

opengauss

Use DSPy to build declarative, modular LM pipelines, optimize prompts automatically, and assemble reliable RAG/agent systems with structured signatures and opti

Cognee

cognee

A lightweight knowledge engine for agent memory: build searchable knowledge graphs from documents and use graph-aware search to give agents persistent, temporal

AI Session Compression Techniques

claude-mpm-skills

Techniques and patterns to compress multi-turn AI conversations (summaries, RAG, hierarchical summarization) to reduce token costs and preserve key information.

GraphMemory

graphmemory

Embedded GraphRAG: DuckDB-backed hybrid graph + vector store for extracting, storing, deduping, and querying entity/relationship graphs with BM25, HNSW vectors,

RAG Implementation Patterns

claude-code-toolkit

Practical guide to building production Retrieval-Augmented Generation (RAG) systems: vector DB selection, chunking strategies, embedding model choices, retrieva

Synalinks Framework

synalinks-skills

Keras-inspired framework for building structured, neuro-symbolic LLM programs with DataModel schemas, modular Programs, and training/optimization tools.

Research Hub

research-hub

Operate Zotero, Obsidian and NotebookLM research workflows via CLI, MCP, and dashboard to collect, organize, and produce literature reviews and AI briefs.

Microsoft Foundry Classic — Expert Guidance

agent-skills

Comprehensive guidance for building, configuring, troubleshooting, and deploying Microsoft Foundry Classic agents and integrations.

py_mnn_kb — Local GraphRAG Knowledge Base

skills

Local GraphRAG knowledge base backed by SQLite + MNN embeddings; provides CLI tools to build, note, query, and check status for an on-device RAG KB.

OpenViking Memory Plugin

openviking

Provides automatic long-term memory capture and recall for OpenClaw agents: auto-capture, auto-recall, and memory management tools for more context-aware conver

libagent

claude-skill-registry

Agent orchestration library for conversational AI — coordinates LLM completions, memory, tool execution, and multi-turn flows; useful for building chat agents a

Exa — Semantic Search

refly-skills

Perform semantic (meaning-based) search over documents or collections to find similar content and neural search results.

Building Agent Systems

code-abyss

Reference guide for designing single- and multi-agent LLM systems, RAG pipelines, security hardening, and prompt engineering for production agents.

Maestro — Skill Knowledge Gateway

maestro

A knowledge gateway that routes coding questions to a focused skill search; call search_skills first to retrieve precise expertise from an indexed skill library

AI/ML Workflow Bundle

agent-skills-library

A comprehensive workflow bundle for designing, building, and operating LLM applications, RAG systems, AI agents, and ML pipelines.

Agent Memory Systems v2

awesome-omni-skills

Guides building and operating agent memory systems (semantic, episodic, procedural) with practical patterns for chunking, embeddings, retrieval, and decay.

RAG Architecture Patterns

claude-dev-suite

Comprehensive patterns for Retrieval-Augmented Generation, including chunking, hybrid search, re-ranking, and evaluation strategies.

Hybrid Search Implementation

awesome-skills-cn

Implement hybrid search by combining vector similarity and keyword-based retrieval for higher RAG recall.

Feast Feature Store Guide

feast

Comprehensive guide for managing AI/ML feature stores, including entity definition, feature retrieval, and RAG pipelines.

Universal Exam Cram Coach

universal-examprep-skill

A structured, anti-hallucination study coach that transforms course materials into a Wiki and quiz bank for rapid exam preparation.

MinerU PDF Parser

nebutra

AI-Native parser for PDF, Office and image files into clean Markdown with LaTeX and OCR.

Brave Search CLI (bx)

brave-search-skills

High-performance web search and RAG grounding tool optimized for AI agents with token-budgeted content and custom ranking.

Knowledge Pipeline

knowledge-pipline

Multimodal knowledge ingestion system that converts documents into a structured wiki with contradiction detection and knowledge graph visualization.

Multi-Agent System Orchestrator

power-ranger-toolkit

Framework for designing and orchestrating multi-agent AI systems with lifecycle management and ChromaDB-backed knowledge harvesting.

Engram Semantic Memory

engram-memory

Persistent semantic memory for AI agents using Qdrant and FastEmbed to store, search, and recall context across sessions.

LlamaIndex — Data Framework for LLMs

Awesome Omni Skill

Framework for building RAG and document-centric LLM applications: ingestion connectors, vector indices, query engines and agent integrations for document Q&A an