Failure Triage — Testing & QA agent for Claude Code
Read-only QA analyst.
How to install Failure Triage
Installs to ~/.claude/agents/duchung1995-playwright-cucumber-ai-qa-failure-triage.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/Duchung1995/playwright-cucumber-ai-qa/HEAD/.claude/agents/failure-triage.md -o ~/.claude/agents/duchung1995-playwright-cucumber-ai-qa-failure-triage.md Restart Claude Code, or start a new session, for it to be picked up.
What Failure Triage does
name: failure-triage description: Read-only QA analyst. Given failed scenarios from a Cucumber run, gathers evidence (error, trace, screenshot, network, live page) and classifies each failure as product-bug, test-bug, flaky or environment with a root cause and recommended action. Use after any failed test run, before changing code. tools: Read, Grep, Glob, Bash model: inherit skills:
- parse-cucumber-report
- inspect-trace
- explore-page
- run-tests
You are the **Failure Triage**
Alternatives in Testing & QA
- Codex Debugger — Root-cause a failing test, crash, stack trace, or misbehaving feature by delegating the investigation to OpenA 249 ★
- Knowledge Base Builder — Phase 3 project model construction agent that classifies project type, maps attacker-controlled inputs and tru 125 ★
- Bm Doc Classifier — Classifies a single planning document as ADR, PRD, SPEC, DOC, or UNKNOWN 92 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
QA Triage
Classifies each failed Playwright test from a QA run (defect, flaky-suspected, env, test-bug, test-outdated, p
Failure Triager
Classifies failed tests from JUnit results, traces and logs into product bug, test bug, environment, flaky or
QA Triager
Analyses a large failed or flaky Playwright run recorded by qa-kit (more than 15 distinct failures across 3 or
Flake Investigator
Establishes why a Playwright case failed intermittently and classifies the cause before anyone changes the tes
Browser Executor
Browser automation agent that executes test scenarios using Chrome DevTools MCP integration with enhanced auto
Test Isolation Reviewer
Use this agent after adding or modifying any file in tests/ to verify the test will pass in CI (no parent-proj
Related Skills
Skills Test
Test skills against representative scenarios (positive, negative, ambiguous, incomplete-input, failure) — chec
Skill CI Churn
GitHub Actions cost analyzer & flaky-test detector for pull requests. Measures wasted CI compute, classifies c
CI Check
Analyze failed CI checks on a PR, determine if failures are flaky/infra, need a master merge, or require code