Art & Design

🤖 Build adaptable AI agents with skill-based systems, enabling efficient context management and seamless integration across any framework.

🚀 An AI-driven QA workflow toolkit built on Claude Code Skills. Codifies testing disciplines—PRD-to-case generation, Playwright UI automation, XMind mindmap editing, hotfix verification, bug triage, and conflict analysis—as reusable kata. Features multi-project workspaces, layered rule inheritance, a knowledge base, and a unified kata CLI.

API Framework heavily relying on the power of DuckDB and DuckDB extensions. Ready to build performant and cost-efficient APIs on top of BigQuery or Snowflake for AI Agents and Data Apps

Build game dev skills for Claude Code, Codex, and Gemini CLI to audit, polish, and repair game projects with reusable workflows

Build a custom Claude Code dashboard in Obsidian to track project status, manage automation skills, and centralize your development workflow in one screen.

Security scanner for your Claude Code setup — flags risky skills, hooks, MCP servers & committed secrets. Zero dependencies, offline.

Drop a screenshot, get a pixel-faithful, actually-clickable HTML page back — an agent skill (Cursor / Claude Code / Codex) that rebuilds UI screenshots as self-contained, verified-interactive HTML.

Build production AI agents with Claude Code-style patterns, runnable Python examples, and a clear checklist for real-world use

Build Claude senior engineer skills for debugging, refactoring, optimization, hardening, and code review in Claude Code workflows

A searchable index of AI coding agent skills, deployed as a GitHub Pages static site. Kitfind crawls popular skills repos at build time, parses their SKILL.md files, generates a unified search blob (index.json), and creates a searchable static site.

Opinionated, agent-agnostic Agent Skills (SKILL.md) for CLI coding agents — coding standards, design diagnosis, agentic-CLI onboarding.

Find curated frontend agent skills repos with SKILL.md files for easy installation and use across frameworks, UI, testing, and more

Portable LazyingArt agent skills for AgInTiFlow, Codex, Claude, Gemini, Copilot, LazyEdit, AutoPublish, browser automation, books, and publishing workflows.

I-Lang skills for OpenClaw, Hermes, and any AI agent. 88 verbs, zero install, zero ambiguity.

Lint a Claude Skill SKILL.md file for spec compliance and triggering quality. Browser-only, single HTML file.

Six portable, framework-agnostic frontend Agent Skills (SKILL.md) for the React & React Native ecosystem: architecture, SEO, Lighthouse performance gate, typed data contracts, optimistic mutations, and observability. About Me : https://stareezy.tech

Cross-platform desktop Skills visual manager for AI coding assistants. Create, manage, deploy & test skills across 15+ tools (Cursor, Claude Code, Codex, Windsurf…). Features: dependency graph, drag-drop builder, LLM testing sandbox, marketplace, analytics. Built with Tauri 2 + React 19 + Rust + SQLite.

Open-source Codex design agent/skills system with PromptPacket v1.5, aesthetic quality gates, anti-fragmentation controls, and GitHub workflows.

Execute structured workflows using a collection of 155 specialized skills designed to turn Qwen models into high-performance AI agents.

Daily curated SKILL.md knowledge base for trending AI agent tools (Claude Code, OpenCode, Codex, Hermes, OpenClaw, AntiGravity). Daily commits to keep contributions green. Built autonomously.

AI 八字 + 紫微斗数排盘与综合印证 Skill：算法精准排盘（不靠 LLM 猜），三种分析模式，一键生成水墨风 HTML 命盘海报。兼容 Claude / Codex / Cursor / Workbuddy 等 SKILL.md Agent。

Learn Claude and Claude Code best practices for skills, MCP tools, and agentic workflows in one living guide

A suite of Claude Code Agent Skills for the design layer of a Ruby on Rails app — the look, feel, usability, and accessibility of a full-stack Hotwire web app on Ruby 4.0.x and Rails 8.1.x.

Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review each other's findings, and build accuracy profiles over time. Agents that catch real bugs get picked more often. Agents that hallucinate get deprioritized. MCP server for Claude Code, Cursor, and other IDEs.