MengTo/Skills

Agent skills for designers and builders using Codex, Claude, Cursor, and other AI coding agents

What it solves

This project provides a structured library of "agent skills" to help developers and designers move beyond one-off chat interactions with AI coding agents. It solves the problem of inconsistent AI output by turning successful prompts, design workflows, and technical implementation steps into versioned, reusable playbooks that agents can load and follow to produce high-quality, repeatable results.

How it works

The repository is organized as a collection of portable folders. Each skill contains a SKILL.md file—a procedural operating procedure that tells an AI agent (such as Codex, Claude, or Cursor) exactly when to use the skill, what steps to take, and which pitfalls to avoid. Some skills include optional references, articles, scripts, and standalone HTML demos to provide the agent with concrete visual or technical context.

Who it’s for

It is designed for designers and builders using AI coding agents to create rich user interfaces, playable browser games (Three.js), frontend systems, and automated workflows.

Highlights

  • Comprehensive Library: Contains over 150 skills across categories like Web Design, Game Development, UI, and Workflow.
  • Agent-Agnostic: Designed to work across different AI tools including Codex, Claude Code, and Cursor.
  • Procedural Approach: Focuses on "specs over vibes," using clear constraints, hierarchy, and references rather than vague paragraphs.
  • Specialized Technical Skills: Includes advanced recipes for WebGL, GSAP animations, Three.js game systems, and high-end CSS treatments.

Related

  • Project
    addyosmani/agent-skills

    A library of production-grade engineering workflows and quality gates for AI coding agents to ensure they follow senior-level software development best practices.

  • Project
    mxyhi/ok-skills

    OK Skills is a library of 31 ready‑to‑use *skill packs* for AI coding agents (Codex, Claude Code, Cursor, etc.). Each skill lives in its own directory with a `SKILL.md` that tells the agent how to run the underlying script (e.g., browser automation, docs lookup, planning, design). Install by cloning into `~/.agents/skills` (or the Autohand equivalent), copy the `CLAUDE_AGENTS.md` sections into your agent’s config, and then ask the agent to “Use <skill‑name> …”. The repo provides categories such as Research, Planning, Automation, Frontend, and Utilities, and serves developers who want portable, repeatable AI‑agent capabilities instead of ad‑hoc prompts.

  • 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.

  • Project
    Neeeophytee/finding-unknowns-skills

    A collection of 14 installable skills for AI coding agents that help developers identify requirements gaps and technical unknowns before implementation.