AI coding agent skills / plugins
Comprehensive open-source library of 380+ skills, plugins, and agent skills for AI coding agents like Claude Code, Codex, Gemini CLI, and Cursor.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
When you want a general, actively maintained agent skills library with similar breadth.
数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
When you need Go-specific agent skills with a lightweight, MIT-licensed collection.
🧑🎨 A collection of Golang agentic skills that works
When you need a dedicated AI-research-focused skills library with emphasis on research workflows.
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.
When you need out-of-the-box AWS skills for architecting and deploying on AWS.
Agent Plugins for AWS equip AI coding agents with the skills to help you architect, deploy, and operate on AWS.
When you want agent rules/skills derived from classic software engineering books.
AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books.
When you need a focused PM skills marketplace for product workflows.
PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.
When you want lightweight, Markdown-only research skills for ML experiments without a heavy framework.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
These projects were analysed and named claude-skills among their alternatives. The relationship is not symmetric — how claude-skills rates them is a separate judgement, made when claude-skills is analysed in its own right.
calls claude-skills “Narrower: a large collection of skills/plugins for coding agents but no coherent SDLC process; choose it for broad individual skills rather than a guided methodology.”
An agentic skills framework & software development methodology that works.
calls claude-skills “A broad collection of skills/plugins but lacks the memory/security components of the seed.”
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.