Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
medmcqa
Datasets & benchmarksHugging Face dataset by openlifescienceai
openlifescienceai/medmcqa -
MetaMathQA
Datasets & benchmarksHugging Face dataset by meta-math
meta-math/MetaMathQA -
frame-trace-mcp
MCP serversBest AI QA Evidence Recorder MCP Server for Automated Testing 2026
git clone https://github.com/yashsindya2014-hash/frame-trace-mcp.git -
ppt-agent-skills
Agents & frameworksA code-driven presentation generation framework. 像构建软件工程一样生成演示文稿。
git clone https://github.com/sunbigfly/ppt-agent-skills.git -
qa
SkillsClaude Code plugin marketplace of reviewed QA skills and agents: test automation, API, load, security, accessibility, mobile and manual testing.
git clone https://github.com/testland/qa.git -
claude-qa-flow
SkillsQA workflow for AI coding agents: ticket → reviewed test plan → real-browser run with independent evidence review → bug tickets. Claude Code, OpenCode, any Agent Skills harness.
git clone https://github.com/QAMarcos/claude-qa-flow.git -
agentic-qa-boilerplate
SkillsAgentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, orchestrating the full QA lifecycle: shift-left planning, in-sprint testing, TMS documentation with ROI scoring, KATA automation, and regression with GO/NO-GO. Works across Claude Code, Opencode, etc.
git clone https://github.com/upex-galaxy/agentic-qa-boilerplate.git -
qa-skills
SkillsAI-powered QA framework built from reusable skills that teach AI agents (Claude, Copilot, Codex, Gemini) to do quality work like an experienced QA engineer
git clone https://github.com/Marina-Gajego/qa-skills.git -
claude-show-your-work
Agents & frameworksClaude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.
git clone https://github.com/iamumeransari/claude-show-your-work.git -
assay
Agents & frameworksAn agent-native QA CLI for web pages. Deterministic, no tests to write, no LLM.
git clone https://github.com/awss1i/assay.git -
IA-QA — 152 QA & Dev Tools for AI Agents
MCP servers152 free QA tools for agents: injection scan, evals, RAG, web audits. Smaller packs: /mcp/{pack}.
-
EhrAgent
Agents & frameworks[EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records
git clone https://github.com/wshi83/EhrAgent.git -
mmlu
Datasets & benchmarksHugging Face dataset by cais
cais/mmlu -
squad
Datasets & benchmarksHugging Face dataset by rajpurkar
rajpurkar/squad -
vibetest-use
MCP serversVibetest MCP - automated QA testing using Browser-Use agents
git clone https://github.com/browser-use/vibetest-use.git -
ISO country QA
MCP serversPublic ISO 3166-1 record for QA.
-
QA Test Server
MCP serversTesting publish command
-
Verdict QA
MCP serversRead-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.
verdict-qa-mcp@0.93.1 -
ghost-qa
MCP serversAutonomous headless browser QA & self-healing verification loop for AI coding agents.
ghost-qa@2.1.1 -
antigravity-bmad-config
PromptsAntigravity config template: BMad Method (BMAD-METHOD) AI agents via slash commands for PRD→Architecture→Stories→Dev→QA gate.
git clone https://github.com/salacoste/antigravity-bmad-config.git -
Magic 8 Ball QA Demo
MCP serversSkybridge demo for QA and playground validation
-
Venture Foundry QA
MCP serversPreflight QA for AI-agent deliverables with structured verdicts and repair guidance.
-
QA Wrap bridge
MCP serversRead-only MCP server: a coding agent reads test sessions recorded in QA Wrap. Local only.
qa-wrap-bridge@0.1.0 -
medical_dialog
Datasets & benchmarksHugging Face dataset by UCSD26
UCSD26/medical_dialog
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.