QA Triager — Testing & QA agent for Claude Code
Analyses a large failed or flaky Playwright run recorded by qa-kit (more than 15 distinct failures across 3 or more features), classifies each failure (app bug, test bug, permission/environment, flaky.
How to install QA Triager
Installs to ~/.claude/agents/mahmulp-qa-kit-qa-triager.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/MahmulP/qa-kit/HEAD/agents/qa-triager.md -o ~/.claude/agents/mahmulp-qa-kit-qa-triager.md Restart Claude Code, or start a new session, for it to be picked up.
What QA Triager does
name: qa-triager description: Analyses a large failed or flaky Playwright run recorded by qa-kit (more than 15 distinct failures across 3 or more features), classifies each failure (app bug, test bug, permission/environment, flaky, known bug) with evidence, and drafts fixes and per-feature bug reports. Smaller runs are triaged in the main session. tools: Read, Grep, Glob, Bash
You explain why tests failed. You do not change files; you return a diagnosis and concrete proposals.
- `qa-k
Alternatives in Testing & QA
- Bash32 Portability Reviewer — Reviews Mole shell and Bats diffs against the current macOS Bash 3.2, errexit, timeout, TTY, BSD-tool, and CI 72k ★
- Grid Tester — Use this agent for test strategy, TDD workflows, integration/e2e coverage, and flaky test hardening 523 ★
- Knowledge Base Builder — Phase 3 project model construction agent that classifies project type, maps attacker-controlled inputs and tru 125 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Failure Triager
Classifies failed tests from JUnit results, traces and logs into product bug, test bug, environment, flaky or
QA Triage
Classifies each failed Playwright test from a QA run (defect, flaky-suspected, env, test-bug, test-outdated, p
Flake Investigator
Establishes why a Playwright case failed intermittently and classifies the cause before anyone changes the tes
AI Tester
Runs the project's tests for a change and classifies the outcome as PASS, EXISTING TEST FAILURE, NEW REGRESSIO
E2e Writer
Writes Playwright/Maestro e2e specs and classifies failing runs. Runs ONLY against the test environment; never
AI Controls Author
AI system spec, eval suite, tool permission matrix, HITL workflow (taxonomy 4.15). Used by ai-controls-team.
Related Skills
CI Check
Analyze failed CI checks on a PR, determine if failures are flaky/infra, need a master merge, or require code
Skill CI Churn
GitHub Actions cost analyzer & flaky-test detector for pull requests. Measures wasted CI compute, classifies c
Beckon
Distinct sounds for your AI coding agent: know whether it finished, needs a decision, or failed, without watch