Awesome Agent Skills collection list, papers, tools, projects, and resources

Multi-agent systems, memory, planning, reasoning loops

SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.

50+ tutorials and implementations for Generative AI Agent techniques, from basic conversational bots to complex multi-agent systems.

A Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Agents.

Curated list of LLM-driven trading agents, MCP servers, and agent skills for market research, strategy, and execution.

Claude Code-style background agents for OpenCode – async delegation with context persistence

An MCP Multimodal AI Agent with eyes and ears!

AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems. Focuses on financial intelligence, RAG pipelines, observability, and secure governance. ACP Openclaw, Gemini CLI, Opencode

✨ A curated list of awesome GitHub instructions, prompt, skills, MCPs and agent markdown files for enhancing your GitHub Copilot AI experience.

34 FinOps specialist AI agents + 6 named-pattern playbooks. Drop into Claude Code, Copilot, Cursor, Windsurf, Aider, Gemini CLI. MIT.

Curated, trusted open catalog of AI agent skills for OpenClaw, Claude Code, Codex, GitHub Copilot, Gemini, Cursor, MCP, LangChain, and more. Browse, install, and verify reusable agent workflows.

Agent skills for daily use

The skill layer for AI agents: npm for AI Agent Skills.

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

From thought to skill. From signal to structure.

AI agents that act as your personal venture analyst - from startup idea brainstorming to full validation and go-to-market strategy. Built for developers who'd rather validate in 10 minutes than regret in six months. Powered by Claude Code, OpenAI Codex, and Cursor.

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

Better subagent experience for Codex and Claude users

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

Open source version of Claude Managed Agents. Fastest way to build and deploy reliable AI agents, MCP tools and agent-to-agent.

Where AI agents hire AI agents — hiring and coordination infrastructure for the agent economy

LLM agents as your hyperparameter optimizer.

Connect AI agents across any network — zero config, encrypted, skill-based routing