MCP servers and skills: search, filter by where they run, and compare.
An agent skill for auditing and improving unit and integration tests through demonstrated regressions.
SkillMIT★ 4Few starsNo key
Make AI-written code production-ready, with proof. Agent skill for Claude Code, Codex, GitHub Copilot & Gemini CLI: locks behavior, finds bugs and security holes, fixes Big-O, adds property and mutati
SkillMIT★ 14No key
Catch AI coding agents cheating on tests: skipped tests, deleted asserts, CI made optional, and "all tests pass" with no receipts.
SkillMIT★ 1Few starsNo key
Agent Skill: turn any technology into a hands-on, auto-graded course — Claude Code, Codex, OpenCode, Gemini, Antigravity, Cursor…
SkillMIT★ 2Few starsNo key
A restricted, auditable handoff bridge between ChatGPT-compatible MCP clients and Codex-oriented local workers.
SkillMIT★ 4Few starsNo key
Use your ChatGPT or Claude Web quota for remote coding without a second server-side API token meter
SkillMIT★ 18No key
Claude skill that turns a book (EPUB, PDF, HTML, DOCX, Markdown) into an interactive beginner-friendly course: step-by-step lessons, animations, quizzes, chapter tests, flashcards and coding exercises
SkillMIT★ 67No key
Your agent feed — one place to see what your AI agents did.
Hosted by authorMITFew starsNo key
Node.jsMITFew starsNo key
Disclosure-first commission clearing for AI agents, via MCP (early pilot)
Hosted by authorMITFew starsNo key
MCP proxy that lets AI agents read and write a production SQL Server under their own login, with statement blocking and an audit log
SkillMIT★ 1Few starsNo key
MCP server for GroupDocs.Search for .NET — lets AI agents (Claude, Copilot, Cursor) index and run full-text search across documents on-premise. stdio transport, NuGet/Docker/GHCR/MCP Registry.
DockerMITFew starsNo key
Your coding agent says it's done. It says that a lot. A skill and a Claude Code hook that make it show receipts: no "tests pass" without a test run, no tests skipped to get green.
SkillMITFew starsNo key
Deterministic code quality gate for AI coding agents (Claude Code, Codex, pi): git hooks that block test tampering, hold the CRAP bar on changed functions, check diff coverage, secrets and dependencie
SkillMIT★ 18No key
OpenAPI spec in, chaos test harness out: WireMock stubs, contract tests and failure scenarios from a team of local LLM agents.
PythonMIT★ 2Few starsNo key
See what your coding agent actually did. A desktop pal and notch for Claude Code, Codex, Cursor, Gemini CLI and any agent: test results read from the output, faked passes caught, and an MCP server any
Node.jsMIT★ 52No key
Get trusted, get merged, come back: an open-source guide and MCP server for contributors in the AI era.
PythonMIT★ 1Few starsNo key
Point Claude at any game. Skills, tools and the fal MCP that let Claude Code mod almost any PC game you own: recon, reverse engineering, fal-generated art/3D/audio, in-game testing, showcase videos.
PythonMIT★ 8.1kNo key
Eleven free Claude skills that clone any app: reverse-engineer it, rebuild it, test it for bugs, then fix what its users hate. Free, MIT.
SkillMIT★ 3.2kNo key
易语言调试中转 MCP：本地 E5.95 IDE 的读取、可靠修改、编译与运行观测，通过 MCP 交给 AI 调用
PythonMIT★ 4Few starsNo key
A comprehensive logo-design skill for Claude, Gemini CLI, Codex and other AI agents: principles, process, SVG craft, testing tools and a 1,400+ logo reference library.
SkillMIT★ 3.6kNo key
Mutation-tests every test your coding agent writes and blocks 'done' until the score passes (default 80%, up to two rounds). Claude Code, Codex, OpenCode, Pi. Java, Kotlin, Python, TS/JS, Go, C#.
SkillMIT★ 4Few starsNo key
π (pi) coding-agent extension: project-aware system prompt for any repo (stack, commands, conventions, AGENTS.md/CLAUDE.md rules) and a verification gate that runs the project's own typecheck/lint/tes
SkillMITFew starsNo key
API de validation d'adresses avec paiement x402
Hosted by authorMITFew starsNo key
Who stands behind it
