MCP servers and skills: search, filter by where they run, and compare.
Shrink failing JSON into smaller reproducible fixtures. Portable Agent Skill, zero-dependency Node.js CLI, explicit failure signatures, protected values, and replay reports.
SkillMITFew starsNo key
程一镜 · MiniMax H3 Ref2VA 短剧工业化技能：把剧本落成可生成、可剪辑、可追踪的单镜任务
SkillMIT★ 1Few starsNo key
Official AgentTwin Node.js workflow-testing skills, coding-agent rules and public documentation MCP configuration
Node.jsMITFew starsNo key
Helps to customise DV360 bidding. Based on peer-reviewed literature, it build customs algos.
SkillMITFew starsNo key
A language-agnostic Agent Skill for evidence-based software architecture audits. It discovers the stack and domain, traces use cases, and evaluates boundaries, invariants, dependencies, and design cho
SkillMITFew starsNo key
Agent skill that shows every state of an app's UI on one page as live iframes of the real code over a fake backend.
SkillMITFew starsNo key
Free Roblox regression-check skill for AI coding agents. Executable Luau fixtures and inspectable before/after reports. MIT.
SkillMITFew starsNo key
Test whether coding agents load and follow your skills, in isolated Docker Sandboxes, traced with MLflow.
SkillMIT★ 2Few starsNo key
Daily Chinese academic digest from PubMed, Europe PMC, arXiv, Research Square and GitHub: a 3+7 report pushed to WeChat via ServerChan. Self-contained Agent Skill for Claude Code, Codex and DSH.
SkillMIT★ 1Few starsNo key
Local-only security checks for web apps you own: white-box scan (Semgrep/gitleaks/osv-scanner), black-box headers/traversal/CORS, signature-based attack (nuclei). 한국어/English.
SkillMIT★ 1Few starsNo key
Give your mobile app a security rehearsal before launch. An open-source agent skill for Flutter, React Native, iOS, Android, and their backends.
SkillMIT★ 1Few starsNo key
Cross-agent engineering workflows for planning, implementation, security, and evidence-backed verification.
SkillMIT★ 1Few starsNo key
Design review for Claude Code: checks UI and UX against Apple's Human Interface Guidelines, measures what it can, and flags template-made interfaces. iOS, iPadOS, macOS and the web.
SkillMITFew starsNo key
Trust layer for AI agents - deterministic, offline Agent Skills (open Agent Skills standard, stdlib-only, cross-client)
SkillMITFew starsNo key
Audit sitemap.xml and robots.txt for duplicate, blocked, noindex, and canonical-mismatched URLs — and report only the checks you actually ran.
SkillMITFew starsNo key
Who stands behind it
