AI Agent Skills

A Claude Code skill that plays bouncer at the door of production: audits AI-built apps (Lovable, Bolt, v0, Cursor) across 5 domains and hands you a scored punch list wit…

Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.

A Claude/Codex skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice.

Official Agent Skills for coding agents, research, workflow orchestration, docs, ops, and skill authoring.

「說人話」：繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡，順手校正中國用語與半形標點，給 Claude Code / Codex / Cursor 用。

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguou…

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thr…

A powerful, minimal Python project template and agent skill for modern Python projects with uv

The skill layer for AI agents: npm for AI Agent Skills.

Delegate read-only investigation, debugging, audit, search, or code-understanding tasks to sub-agents; synthesize only from their structured reports.

narrow React component prop types to match live code paths

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adve…

System for managing collections of agent skills. Switch between skillsets seamlessly!

The Software Factory

Autonomous multi-batch development skill for Claude Code and Codex. They work while you sleep.

Minecraft AI agent skills and dual-target plugin bundle for Codex and Claude Code.