@agents-forge/qa-reviewer
v1.0.1
Published
AI QA Reviewer agent — reviews test cases and Playwright spec files as a Principal QA Engineer, writes a review_report.md
Maintainers
Readme
🔍 QA Reviewer Agent
Reviews your test cases and Playwright scripts as a Principal QA Engineer — checking coverage, selector quality, assertion depth, traceability, and more. Writes a review_report.md you can action before running tests.
Part of the @agents-forge AIQA pipeline:
analyst → qa-planner → qa-engineer → qa-reviewer → qa-reporterInstall
npm install @agents-forge/qa-reviewerQuick Start
# Run in your project root — auto-discovers everything
npx @agents-forge/qa-reviewerAuthentication
Auto-detected — no config needed:
| Method | Setup |
|---|---|
| Anthropic API key | ANTHROPIC_API_KEY=sk-ant-... in .env |
| Claude subscription | npm install -g @anthropic-ai/claude-code → claude login |
| GitHub Copilot | gh auth login |
What it reviews
Auto-discovers and reviews all these files:
| File | What's checked |
|---|---|
| test_plan.md | Coverage completeness vs feature areas |
| test-cases/*.md | Test IDs, steps clarity, expected results, tagging |
| tests/*.spec.ts | Selectors, assertions, independence, tags, env vars |
| playwright.config.ts | Reporters, browser matrix, retry config |
Features
- 🔴 Critical issues — must fix before release
- 🟡 Warnings — should fix for quality
- 🟢 Suggestions — nice to have improvements
- 📊 Traceability matrix — every TC ID mapped to its spec test
- 📋 Module-by-module coverage summary
- ✅ Sign-off checklist — clear gates before qa-reporter
CLI Usage
# Review current directory
npx @agents-forge/qa-reviewer
# Custom output filename
npx @agents-forge/qa-reviewer --output my_review.md
# Review a specific directory
npx @agents-forge/qa-reviewer --dir ./my-projectProgrammatic Usage
import { runQAReviewer } from "@agents-forge/qa-reviewer";
await runQAReviewer({
cwd: process.cwd(), // optional — defaults to process.cwd()
outputFile: "review_report.md", // optional — default filename
});Output: review_report.md
# QA Review Report
Status: PASSED / PASSED WITH WARNINGS / NEEDS REVISION
## Coverage Summary
| Module | Test Cases | Spec Tests | Traceability | Status |
## Issues Found
### 🔴 Critical Issues
### 🟡 Warnings
### 🟢 Suggestions
## Test Case Review (per module)
## Spec File Review (per module)
## Traceability Matrix
## Recommendations
## Sign-off checklistFull Pipeline
npx @agents-forge/analyst https://my-app.com requirements.md
npx @agents-forge/qa-planner requirements.md test_plan.md
npx @agents-forge/qa-engineer test_plan.md --url https://my-app.com
npx @agents-forge/qa-reviewer
npx @agents-forge/qa-reporter # coming soonTroubleshooting
| Error | Fix |
|---|---|
| No test files found | Run @agents-forge/qa-engineer first |
| Authentication failed | Set ANTHROPIC_API_KEY or run claude login |
| test_plan.md not found | Run @agents-forge/qa-planner first |
License
MIT
