Production-grade engineering skills for AI coding agents.
agent-skills is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
npx skills add addyosmani/agent-skillsRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
This repository provides a set of skills that teach AI coding agents how to follow best practices used by senior engineers. It includes commands for planning, building, testing, reviewing, and shipping code, and works with many popular AI coding tools.
Agent Skills is a collection of structured workflows, quality gates, and best practices packaged for AI coding agents. It encodes the knowledge that senior engineers use when building software, so AI agents can follow them consistently across every phase of development. The repository includes 23 skills covering the entire development lifecycle: from specification and planning, through incremental building and testing, to code review and shipping. It also provides 7 slash commands that map to common development activities, each activating the right skills automatically. Skills are plain Markdown files, making them compatible with any agent that accepts system prompts or instruction files. The repository supports multiple AI coding tools including Claude Code, Cursor, Gemini CLI, Windsurf, OpenCode, GitHub Copilot, and Kiro IDE.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 51 days ago.
48845 GitHub stars indicate community interest.
98 open issues signal maintenance load.
MIT license detected.
Define what to build using the /spec command before writing any code.
Plan implementation with small, atomic tasks using the /plan command.
Build features incrementally with the /build command, one slice at a time.
Prove code works with the /test command, treating tests as proof of correctness.
Review code before merging using the /review command to improve code health.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing.
Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
48,845
Stars
5,433
Forks
98
Issues
MIT
License
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
Production-grade engineering skills for AI coding agents.
Senior software engineers who want to enforce best practices in AI-assisted development., AI coding agent users who want consistent, high-quality outputs from their tools., Development teams adopting AI pair programming and seeking standardized workflows.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing. Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Similar or complementary options to evaluate include anthropic-skills, bug-hunter, hyperframes.
Jun 7, 2026
2 security/trust notes recorded.
Setup difficulty is 2/5.
An open-source framework to turn HTML, CSS, and animations into deterministic MP4 videos.