Liveqa — Testing & QA agent for Claude Code
Use this agent to test the live, deployed product in a real browser after Pipeman has pushed a sprint's code.
How to install Liveqa
Installs to ~/.claude/agents/chrishobbsrocks-fully-completely-liveqa.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/chrishobbsrocks/fully-completely/HEAD/.claude/agents/liveqa.md -o ~/.claude/agents/chrishobbsrocks-fully-completely-liveqa.md Restart Claude Code, or start a new session, for it to be picked up.
What Liveqa does
name: liveqa description: Use this agent to test the live, deployed product in a real browser after Pipeman has pushed a sprint's code. Use after every push and every re-push during the fix loop, never before code is live. model: opus color: purple
You are LiveQA, the Live Field Tester. You do not read code. You do not trust code. You trust what you see happen in a real, running browser, nothing else. A green checkmark on a diff is a claim, not a fact, your job is to turn the claim into
Alternatives in Testing & QA
- Test Fix Loop Agent — Автоматическое тестирование REST API в цикле с исправлением ошибок 571 ★
- Witness — Independently witness that an Allium loop's convergence claim is true and was reached honestly 474 ★
- Playwright Test Generator.Agent — Generates Playwright tests from test plans by recording real interactions 225 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Pipeman
Use this agent to push code to the remote repository after QA1's first gate passes, and to push follow-up fixe
QA Ticket
Independently QA a Jira ticket or GitLab merge request against a deployed build on the test server (normally s
Advisor Design Review
Senior product designer reviewing Altis output against the Altis design system. Use for visual QA on live URLs
Test Execution Agent
Single execution agent for every playwright-bdd test test-writer produces — browser tests (WAY 1) and API test
Manual QA
Use when a change needs to be exercised in a real running app — not unit tests, but a human-style check of the
Live Evaluator
Phase 3 of the grounded-persona-eval method — drives one persona through a real, live interaction with the pro
Related Skills
Sprint Reship
Pipeman: push a fix during the LiveQA live-test loop
Converge
Run an unattended review→fix→re-review loop on the current branch until the reviewer has no findings at or abo
Cfn Vote Implement
MUST BE USED after cfn-dry-review or cfn-alpha-launch:manifest produces a manifest. Also verification phase of