addyosmani/agent-skills

Production-grade engineering skills for AI coding agents.

What it solves

AI coding agents often lack the disciplined engineering rigor of senior developers, frequently skipping tests, ignoring quality gates, or rushing to implementation without a clear specification. This project provides a library of "skills"—structured workflows and best practices—that force agents to follow production-grade engineering standards across the entire software development lifecycle.

How it works

Skills are packaged as Markdown files (SKILL.md) that define a strict process for the agent to follow. Each skill includes a step-by-step workflow, verification gates (evidence requirements), and "anti-rationalization" tables that prevent agents from making common excuses to skip critical steps. These skills can be integrated into various AI agents (like Claude Code, Cursor, and GitHub Copilot) via a CLI or native plugins, and can be triggered by specific slash commands (e.g., /spec, /plan, /test) or automatically based on the task context.

Who it’s for

Developers who use AI coding agents and want to ensure the generated code meets professional standards for quality, security, performance, and maintainability.

Highlights

  • Comprehensive Lifecycle Coverage: Includes 25 skills covering everything from initial idea refinement and PRD writing to TDD, security hardening, and production deployment.
  • Agent-Agnostic: Compatible with a wide range of tools including Claude Code, Cursor, Codex, Copilot, and Windsurf.
  • Verification-First: Every skill requires concrete evidence (e.g., passing tests, runtime data) before moving forward.
  • Specialist Personas: Provides pre-configured personas like Senior Staff Engineer and Security Auditor for targeted reviews.

Related

  • Project
    waynesutton/builder-skills

    builder‑skills provides a set of concise, markdown‑based “skills” that teach AI coding assistants how to follow Convex best‑practice rules and disciplined project‑workflow habits (PRDs, task tracking, safe git). Installable via skills.sh, Claude plugins, or npm, it drops starter docs and lets agents load the appropriate SKILL.md on demand, keeping code, docs, and safety checks in sync.

  • Project
    OneWave-AI/claude-skills

    A library of 229 production-ready, single-file skills for AI agents to automate complex tasks across engineering, business operations, and design.

  • Project
    GPTomics/bioSkills

    bioSkills is a library of ready‑made code templates (“skills”) that teach LLM coding agents how to perform bioinformatics analyses—from sequence I/O to single‑cell, variant calling, structural biology, chemoinformatics, and workflow management. Installable via thin scripts for Claude Code, Codex, Gemini/Antigravity, OpenCode, and OpenClaw, the skills provide best‑practice command‑line flags, example scripts and usage guides, improving the correctness of AI‑generated bio‑informatics code.

  • Project
    MoizIbnYousaf/ai-agent-skills

    A genuine npm‑based CLI/TUI that ships a curated library of AI‑agent skills, lets you build and manage your own skill collections, and integrates with many LLM‑agents via the Agent Skills spec.

  • Project
    kangarooking/kangarooking-skills

    A collection of structured, open-source Agent Skills compatible with the Agent Skills standard, providing reusable workflows for content creation, image generation, and AI project engineering.