MCP servers and skills: search, filter by where they run, and compare.
ASD-STE100-style plans for AI coding agents, inspired by Karpathy's 80% STE tip: Claude Code, Codex or Cursor writes a short plan you approve before it codes.
SkillMIT★ 8No key
Free, open-source AI planning tool. Supercharge AI coding agents with Filament v5 best practices and spec driven planning, and automated implementation reviews inspired of Laravel Boost.
SkillMIT★ 8No key
MCP server that gives AI coding agents the WunderUI design system: tokens, component props, templates and starters.
Node.jsMIT★ 1Few starsNo key
🧰 48 Agent Skills: roast your GitHub, bisect bugs, record demo GIFs, write Playwright e2e tests, grill specs, catch AI slop and risky CI. Tested, one-line install. Claude Code, Cline, Cursor, Codex
SkillMIT★ 5No key
Agent skill for TRIZ problem solving: finds the contradiction, applies the 40 principles and contradiction matrix, and turns them into a validated action plan.
SkillMIT★ 2Few starsNo key
pstack for OpenCode v2: native port of cursor/plugins pstack (56 skills, 23 agents, 56 commands), with verification gates
SkillMIT★ 1Few starsNo key
Track whether ChatGPT, Perplexity, Claude, Gemini and Google AI Overviews recommend your product, every day on GitHub Actions, plus the agent skill that gets you into the answers. Template repo, MIT.
SkillMIT★ 1Few starsNo key
A personal AI investment committee for Claude Code: a CIO skill and 10 specialist agents, long-term Buffett/Munger style. Not financial advice.
SkillMIT★ 1Few starsNo key
SkillMITFew starsNo key
Free, scanned agent skills for Claude Code, Cursor, Codex and Gemini CLI, plus the proskills-cli installer and skill scanner.
SkillMITFew starsNo key
Claude Code skill: build, audit and ship websites from idea to launch, with specialist agents and anti-slop checks.
SkillMIT★ 1Few starsNo key
Visualize and understand the plans that your agents need
SkillMIT★ 1Few starsNo key
Agent skills that take a feature or a bug from a vague request to a reviewed pull request. 100% tested with AI agents. Please break it.
SkillMIT★ 2Few starsNo key
A skill for AI coding agents: plan with executable exit criteria, dispatch one milestone at a time to a subagent, and review with independent re-runs.
SkillMITFew starsNo key
SkillMITFew starsNo key
A composable skill suite for general legal work — six doors, one engine, one matter folder, one playbook layer. Apache-2.0.
SkillApache-2.0★ 1Few starsNo key
Claude Code skills as a plugin marketplace: GitHub roadmaps, parallel subagents, doc and skill audits, tech debt, Angular, SEO and token use
SkillMIT★ 1Few starsNo key
8 Claude Code and Codex skills for exotic, luxury and Turo car rental businesses: pricing with live market rates, competitor scans, rental agreements, damage inspections, listings, social posts, revie
SkillMIT★ 1Few starsNo key
6 Claude Code and Codex skills for renting exotic and luxury cars in the US: who rents a Lamborghini, Ferrari, Rolls-Royce or G-Wagon in your city at published daily rates, real cost, event cars, comp
SkillMIT★ 1Few starsNo key
Your agent forgets. Your repo doesn't. A docs-first workflow (work items, specs, plans, ADRs) that gives AI coding agents a durable project memory. Built to pair with Superpowers.
SkillMIT★ 1Few starsNo key
🩺 Audit vulnerable, outdated and unused packages with a safe upgrade plan - Agent Skill for Claude Code, Cline, Cursor, Codex
SkillMITFew starsNo key
🔥 Get your GitHub profile roasted with real data, then a scorecard and glow-up plan - Agent Skill for Claude Code, Cline, Cursor, Codex
SkillMITFew starsNo key
📐 Grill you on a feature plan against your real code, then write a testable SPEC.md - Agent Skill for Claude Code, Cline, Cursor, Codex
SkillMITFew starsNo key
Agent skill: expert-perspective crosscheck of plans before execution
SkillMITFew starsNo key
Who stands behind it
