Explore
MCP servers and skills: search, filter by where they run, and compare.
ming-qamingdui
Local
MCP servers and skills: search, filter by where they run, and compare.
端到端 QA 验收编排器 · Agent Skill：上下文 → 风险 → 用例 → 脚本 → 执行 → 审查 → 报告，全程自动衔接，只在用例确认时停下等你审核。支持 Claude Code / Codex / Cursor
SkillMIT★ 41No key
50 QA and test-automation skills for Claude Code, Codex, Cursor, and any Agent Skills Standard runtime.
SkillMIT★ 189No key
让 AI 像资深测试工程师一样工作：面向 AI Agent 的测试工程 Skill 框架——11 Skills + 共享知识库 + 类型决策矩阵（Claude Code / dsh 等 Agent 可用）
SkillMIT★ 46No key
AI 測試大師 — MCP server driving pytest / Jest / Cypress / Go / Maestro. Analyze, generate, run, advise. Web + Mobile (iOS/Android/BlueStacks).
PythonMIT★ 37No key
DeepSeek Harness plugin that does QA: an agent explores your app like a real user and leaves evidence, then the explored path is exported as a deterministic replay scenario you run every release. Orch
SkillMIT★ 4Few starsNo key
QA Skills Directory QA Skills is a curated directory of testing-specific skills for AI coding agents (Claude Code, Cursor, Copilot, etc.).
Node.jsMIT★ 237No key
Autonomous web-app QA skill for Claude Code: Playwright E2E, visual regression, axe-core a11y. LLM-generated self-healing specs, zero-token test runs.
SkillMIT★ 5No key
Claude Code skills that turn an AI agent into a meticulous QA engineer. Evidence or it didn't happen.
SkillMIT★ 13No key
MCP server that runs goal-driven Playwright browser sessions with full action traces and aria-snapshots, so the calling LLM can verify whether a goal was met.
Node.jsMITFew starsNo key
Use this skill when a user needs a screenshot, website thumbnail, full-page capture, or PDF of a public HTTP(S) webpage saved as a local artifact through Latchshot, including report, QA, archive, and
OfficialSkillMIT★ 40k in collectionNo key
Adversarial QA for AI-generated software. Give your coding agent something that fights back.
SkillMIT★ 2Few starsNo key
AI logo animation skill: turn raster logos into smooth SVG animation, animated HTML demos, GIF/video previews, and motion QA evidence.
SkillMIT★ 2.4kNo key
🔭 Your coding agent, turned into a QA tester for any web app. Finds what is broken and shows you the proof: pictures, replays, journey videos and test reports. Over MCP, with Claude Code, Cursor, VS
Node.jsMIT★ 1Few starsNo key
Agent skills for source-grounded novel-to-game adaptation (小说改编游戏 / story to game): cited design docs, target-runtime builds, evidence-based QA. Three playable browser examples. For Claude Code, Codex
SkillMIT★ 882No key
Playwright + TypeScript agentic automation framework with a local LLM Wiki/codebase second brian. agent skills, UI/API testing, Page Objects, fixtures and reusable services
SkillMIT★ 12No key
Claude Code skill that produces Korean motion-graphics videos end to end: brief, research, script, ElevenLabs narration, music, images, deterministic HTML render, mix and automated QA.
SkillMIT★ 38No key
Migrates and converts test automation scripts between Selenium, Playwright, Puppeteer, and Cypress. Use when the user asks to migrate, convert, or port tests from one framework to another; rewrite tes
OfficialSkillMIT★ 376 in collectionNo key
Generates production-grade Reqnroll BDD automation scripts for web (Selenium 3/4) and mobile (Appium 2) testing in C#. Supports parallel NUnit execution locally and on TestMu AI cloud. Use when the us
OfficialSkillMIT★ 376 in collectionNo key
Generates production-grade Selenium WebDriver automation scripts and tests in Java, Python, JavaScript, C#, Ruby, or PHP. Supports local execution and TestMu AI cloud with 3000+ browser/OS combination
OfficialSkillMIT★ 376 in collectionNo key
Code-aware browser testing for AI coding agents. 14 MCP tools, CLI workflows, regression memory, and human-readable QA reports.
Node.jsMIT★ 16No key
Local-first MCP server for headless Blender asset QA: background script runs and FBX reimport verification. No add-on, no TCP port.
Node.jsMIT★ 2Few starsNo key
Accurate, on-brand motion-graphics videos of your real web app, made by your AI coding agent.
SkillMIT★ 6No key
Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.
SkillMIT★ 187No key
Who stands behind it
