Failure Triager — Testing & QA agent for Claude Code
Classifies failed tests from JUnit results, traces and logs into product bug, test bug, environment, flaky or test-data, with calibrated confidence, and drafts bug reports.
How to install Failure Triager
Installs to ~/.claude/agents/dbisina-qapro-failure-triager.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/dbisina/QAPRO/HEAD/.claude/agents/failure-triager.md -o ~/.claude/agents/dbisina-qapro-failure-triager.md Restart Claude Code, or start a new session, for it to be picked up.
What Failure Triager does
name: failure-triager description: Classifies failed tests from JUnit results, traces and logs into product bug, test bug, environment, flaky or test-data, with calibrated confidence, and drafts bug reports. High volume, so it runs on Haiku; low-confidence items are re-run on Sonnet. tools: Read, Grep, Glob model: haiku
You triage automated test failures so that humans only look at what matters.
Inputs
- A summary of failed tests (names, error messages, top stack frames) in the `<in
Alternatives in Testing & QA
- Prod Incident Responder — Reads recent prod logs, picks the highest-impact recurring error, drafts a minimal fix PR with a regression te 324 ★
- Eval Author — Authoring role for the D365FO agent eval loop catalog 136 ★
- 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
QA Triager
QA failure triager. Classifies failures per root-cause cluster (product bug, test bug, environment, test data,
QA Incident Investigator
Correlates prepared logs, traces, batch results, API observations, and restricted data evidence without mutati
Data Science Reviewer
Fast Data Science code review focused on research-critical bugs: data leakage, incomplete seeds, temporal leak
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
Plan Doc Reviewer
Use after another agent has written an implementation plan, before commitment — verifies completeness, spec al
Related Skills
Skill CI Churn
GitHub Actions cost analyzer & flaky-test detector for pull requests. Measures wasted CI compute, classifies c
Claude Idea Debug Skill
Claude Code skill that triggers an IntelliJ IDEA test/debug run from your Claude conversation, captures the lo
Analyze Test Report
Phân tích test report — automation (Playwright/Allure/JUnit/TestNG) hoặc manual (execution_report.md / retest_