owainlewis/blueprint

The best agent skills in the world for software development.

What it solves

Blueprint provides a structured set of skills for coding agents to follow professional software engineering practices. Instead of scripting every single move, it gives agents clear outcomes, constraints, and evidence requirements for tasks like documenting systems, designing changes, and delivering pull requests.

How it works

It provides ten portable skill files that can be used by compatible coding agents (such as Codex and Claude Code). These skills act as instructions that guide the agent through specific engineering phases—such as architecture documentation, technical design, and testing—without requiring a dedicated agent framework or runtime.

Who it’s for

Developers who use AI coding agents and want them to produce work that is understandable, testable, and reviewable by humans.

Highlights

  • Ten focused skills: Covers the full lifecycle from documentation (/architecture) and design (/design, /plan) to delivery (/task-to-pr) and quality control (/test, /review, /improve).
  • Framework-agnostic: Works through portable skill files compatible with multiple agents.
  • Outcome-oriented: Focuses on what good work looks like and the evidence needed rather than rigid scripts.
  • Flexible process: Allows users to choose only the skills necessary for the specific task at hand.

Related

  • Project
    addyosmani/agent-skills

    Agent Skills is a library of 25 Markdown‑based engineering workflows (spec, plan, build, test, review, ship, etc.) that can be installed into many AI coding agents via a simple CLI. It provides slash commands, auto‑build mode, specialist personas, and reference checklists to make AI‑generated code follow senior‑engineer best practices across the entire development lifecycle.

  • 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.

  • Project
    bergside/awesome-design-skills

    A curated registry of design system skill files that provide AI coding agents with specific UI rules, tokens, and accessibility constraints to ensure consistent, high-quality design implementation.

  • Project
    xstongxue/best-skills

    A collection of high-quality SKILL.md files for AI agents (Cursor, Claude Code, etc.) that enable automatic task triggering for academic writing, diagramming, and development workflows.

  • Project
    MengTo/Skills

    A curated library of procedural agent skills and prompt playbooks designed to help AI coding agents build high-quality UIs, games, and frontend systems consistently.