QA Explore — Testing skill for Claude Code
Autonomously click every reachable control of a running web app and report what broke.
How to install QA Explore
Installs to ~/.claude/skills/cadus0uza-qa-supreme-qa-explore/SKILL.md
mkdir -p ~/.claude/skills/cadus0uza-qa-supreme-qa-explore && curl -fsSL https://raw.githubusercontent.com/CaduS0uza/qa-supreme/HEAD/commands/qa-explore.md -o ~/.claude/skills/cadus0uza-qa-supreme-qa-explore/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What QA Explore does
description: Autonomously click every reachable control of a running web app and report what broke argument-hint: [--headed]
Run the autonomous exploration pipeline against: $ARGUMENTS
- Confirm the target is a local, preview, or staging environment — never production with real customer data. If it looks like production, stop and ask.
cd runner && npm installifrunner/node_modulesis absent.- Run
node bin/qa-supreme.mjs run --url --out .qa-supreme(add `-
Alternatives in Testing
- Webapp Testing — Test local web applications using Playwright for UI verification and debugging 94.1k ★
- Develop Web Game — Build and test web games iteratively using Playwright with time-stepping 14.6k ★
- Regen API — Regenerate the OpenAPI spec and web API client after server API changes 2.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Ace Step Deck
🎛️ AceDeck — desktop app & GUI for ACE-Step 1.5 AI music generation on Windows: one-click install, generation
QA Explore Template
Autonomous page & workflow testing. Authenticate to your deployed app, navigate, take screenshots, READ the sc
Browser QA
Discover YAML user-stories, fan out bowser-qa-agent subagents in parallel against a running web app, aggregate
Explore Test
Autonomous black-box QA. Give a URL; the agent maps the site, picks modules, tests them, and writes a bug repo
AppReveal
Debug-only in-app MCP server for iOS/macOS/Android/Flutter/ReactNative. Gives LLM agents Playwright-like contr
Dogfood
Exploratory web QA against a target URL — drives a real browser, captures evidence, writes a structured report
Related Agents
UI Explorer
Drive and explore a native macOS app's GUI (screenshot → click/type → observe) and correlate each action with
Phyll Reviewer
Fresh-eyes UX reviewer for apps built with AI. Walks the app as a first-time end user with Phyll's browser too
Record Viewer
Viewer partner of the record-device-app skill. Drives the SEA.AI web app in a browser with rec.py (explore, re