Merge remote-tracking branch 'origin/main' into garrytan/gstack-eval-optimization

test/gen-skill-docs.test.ts

@@ -343,9 +343,10 @@ describe('REVIEW_DASHBOARD resolver', () => {
   test('resolver output contains key dashboard elements', () => {
     const content = fs.readFileSync(path.join(ROOT, 'plan-ceo-review', 'SKILL.md'), 'utf-8');
     expect(content).toContain('VERDICT');
-    expect(content).toContain('CLEARED TO SHIP');
-    expect(content).toContain('NOT YET RUN');
+    expect(content).toContain('CLEARED');
+    expect(content).toContain('Eng Review');
     expect(content).toContain('7 days');
     expect(content).toContain('Design Review');
+    expect(content).toContain('skip_eng_review');
   });
 });

test/skill-e2e.test.ts

@@ -894,6 +894,89 @@ Focus on reviewing the plan content: architecture, error handling, security, and
   }, 420_000);
 });
 
+// --- Plan CEO Review (SELECTIVE EXPANSION) E2E ---
+
+describeE2E('Plan CEO Review SELECTIVE EXPANSION E2E', () => {
+  let planDir: string;
+
+  beforeAll(() => {
+    planDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-plan-ceo-sel-'));
+    const { spawnSync } = require('child_process');
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: planDir, stdio: 'pipe', timeout: 5000 });
+
+    run('git', ['init']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+
+    fs.writeFileSync(path.join(planDir, 'plan.md'), `# Plan: Add User Dashboard
+
+## Context
+We're building a new user dashboard that shows recent activity, notifications, and quick actions.
+
+## Changes
+1. New React component \`UserDashboard\` in \`src/components/\`
+2. REST API endpoint \`GET /api/dashboard\` returning user stats
+3. PostgreSQL query for activity aggregation
+4. Redis cache layer for dashboard data (5min TTL)
+
+## Architecture
+- Frontend: React + TailwindCSS
+- Backend: Express.js REST API
+- Database: PostgreSQL with existing user/activity tables
+- Cache: Redis for dashboard aggregates
+
+## Open questions
+- Should we use WebSocket for real-time updates?
+- How do we handle users with 100k+ activity records?
+`);
+
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'add plan']);
+
+    fs.mkdirSync(path.join(planDir, 'plan-ceo-review'), { recursive: true });
+    fs.copyFileSync(
+      path.join(ROOT, 'plan-ceo-review', 'SKILL.md'),
+      path.join(planDir, 'plan-ceo-review', 'SKILL.md'),
+    );
+  });
+
+  afterAll(() => {
+    try { fs.rmSync(planDir, { recursive: true, force: true }); } catch {}
+  });
+
+  test('/plan-ceo-review SELECTIVE EXPANSION produces structured review output', async () => {
+    const result = await runSkillTest({
+      prompt: `Read plan-ceo-review/SKILL.md for the review workflow.
+
+Read plan.md — that's the plan to review. This is a standalone plan document, not a codebase — skip any codebase exploration or system audit steps.
+
+Choose SELECTIVE EXPANSION mode. Skip any AskUserQuestion calls — this is non-interactive.
+For the cherry-pick ceremony, accept all expansion proposals automatically.
+Write your complete review directly to ${planDir}/review-output-selective.md
+
+Focus on reviewing the plan content: architecture, error handling, security, and performance.`,
+      workingDirectory: planDir,
+      maxTurns: 15,
+      timeout: 360_000,
+      testName: 'plan-ceo-review-selective',
+      runId,
+    });
+
+    logCost('/plan-ceo-review (SELECTIVE)', result);
+    recordE2E('/plan-ceo-review-selective', 'Plan CEO Review SELECTIVE EXPANSION E2E', result, {
+      passed: ['success', 'error_max_turns'].includes(result.exitReason),
+    });
+    expect(['success', 'error_max_turns']).toContain(result.exitReason);
+
+    const reviewPath = path.join(planDir, 'review-output-selective.md');
+    if (fs.existsSync(reviewPath)) {
+      const review = fs.readFileSync(reviewPath, 'utf-8');
+      expect(review.length).toBeGreaterThan(200);
+    }
+  }, 420_000);
+});
+
 // --- Plan Eng Review E2E ---
 
 describeIfSelected('Plan Eng Review E2E', ['plan-eng-review'], () => {
@@ -962,7 +1045,7 @@ Replace session-cookie auth with JWT tokens. Currently using express-session + R
 
 Read plan.md — that's the plan to review. This is a standalone plan document, not a codebase — skip any codebase exploration steps.
 
-Choose SMALL CHANGE mode. Skip any AskUserQuestion calls — this is non-interactive.
+Proceed directly to the full review. Skip any AskUserQuestion calls — this is non-interactive.
 Write your complete review directly to ${planDir}/review-output.md
 
 Focus on architecture, code quality, tests, and performance sections.`,
@@ -1363,7 +1446,7 @@ export function main() { return Dashboard(); }
 
 Read plan.md — that's the plan to review. This is a standalone plan with source code in app.ts and dashboard.ts.
 
-Choose SMALL CHANGE mode. Skip any AskUserQuestion calls — this is non-interactive.
+Proceed directly to the full review. Skip any AskUserQuestion calls — this is non-interactive.
 
 IMPORTANT: After your review, you MUST write the test-plan artifact as described in the "Test Plan Artifact" section of SKILL.md. The remote-slug shim is at ${planDir}/browse/bin/remote-slug.
 
@@ -2261,6 +2344,269 @@ Review the site at ${serverUrl}. Use --quick mode. Skip any AskUserQuestion call
   }, 420_000);
 });
 
+// --- Test Bootstrap E2E ---
+
+describeE2E('Test Bootstrap E2E', () => {
+  let bootstrapDir: string;
+  let bootstrapServer: ReturnType<typeof Bun.serve>;
+
+  beforeAll(() => {
+    bootstrapDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-bootstrap-'));
+    setupBrowseShims(bootstrapDir);
+
+    // Copy qa skill files
+    copyDirSync(path.join(ROOT, 'qa'), path.join(bootstrapDir, 'qa'));
+
+    // Create a minimal Node.js project with NO test framework
+    fs.writeFileSync(path.join(bootstrapDir, 'package.json'), JSON.stringify({
+      name: 'test-bootstrap-app',
+      version: '1.0.0',
+      type: 'module',
+    }, null, 2));
+
+    // Create a simple app file with a bug
+    fs.writeFileSync(path.join(bootstrapDir, 'app.js'), `
+export function add(a, b) { return a + b; }
+export function subtract(a, b) { return a - b; }
+export function divide(a, b) { return a / b; } // BUG: no zero check
+`);
+
+    // Create a simple HTML page with a bug
+    fs.writeFileSync(path.join(bootstrapDir, 'index.html'), `<!DOCTYPE html>
+<html lang="en">
+<head><meta charset="utf-8"><title>Bootstrap Test</title></head>
+<body>
+  <h1>Test App</h1>
+  <a href="/nonexistent-page">Broken Link</a>
+  <script>console.error("ReferenceError: undefinedVar is not defined");</script>
+</body>
+</html>
+`);
+
+    // Init git repo
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: bootstrapDir, stdio: 'pipe', timeout: 5000 });
+    run('git', ['init']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'initial commit']);
+
+    // Serve from working directory
+    bootstrapServer = Bun.serve({
+      port: 0,
+      hostname: '127.0.0.1',
+      fetch(req) {
+        const url = new URL(req.url);
+        let filePath = url.pathname === '/' ? '/index.html' : url.pathname;
+        filePath = filePath.replace(/^\//, '');
+        const fullPath = path.join(bootstrapDir, filePath);
+        if (!fs.existsSync(fullPath)) {
+          return new Response('Not Found', { status: 404 });
+        }
+        const content = fs.readFileSync(fullPath, 'utf-8');
+        return new Response(content, {
+          headers: { 'Content-Type': 'text/html' },
+        });
+      },
+    });
+  });
+
+  afterAll(() => {
+    bootstrapServer?.stop();
+    try { fs.rmSync(bootstrapDir, { recursive: true, force: true }); } catch {}
+  });
+
+  test('/qa bootstrap + regression test on zero-test project', async () => {
+    const serverUrl = `http://127.0.0.1:${bootstrapServer!.port}`;
+
+    const result = await runSkillTest({
+      prompt: `You have a browse binary at ${browseBin}. Assign it to B variable like: B="${browseBin}"
+
+Read the file qa/SKILL.md for the QA workflow instructions.
+
+Run a Quick-tier QA test on ${serverUrl}
+The source code for this page is at ${bootstrapDir}/index.html — you can fix bugs there.
+Do NOT use AskUserQuestion — for any AskUserQuestion prompts, choose the RECOMMENDED option automatically.
+Write your report to ${bootstrapDir}/qa-reports/qa-report.md
+
+This project has NO test framework. When the bootstrap asks, pick vitest (option A).
+This is a test+fix loop: find bugs, fix them, write regression tests, commit each fix.`,
+      workingDirectory: bootstrapDir,
+      maxTurns: 50,
+      allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Glob', 'Grep'],
+      timeout: 420_000,
+      testName: 'qa-bootstrap',
+      runId,
+    });
+
+    logCost('/qa bootstrap', result);
+    recordE2E('/qa bootstrap + regression test', 'Test Bootstrap E2E', result, {
+      passed: ['success', 'error_max_turns'].includes(result.exitReason),
+    });
+
+    expect(['success', 'error_max_turns']).toContain(result.exitReason);
+
+    // Verify bootstrap created test infrastructure
+    const hasTestConfig = fs.existsSync(path.join(bootstrapDir, 'vitest.config.ts'))
+      || fs.existsSync(path.join(bootstrapDir, 'vitest.config.js'))
+      || fs.existsSync(path.join(bootstrapDir, 'jest.config.js'))
+      || fs.existsSync(path.join(bootstrapDir, 'jest.config.ts'));
+    console.log(`Test config created: ${hasTestConfig}`);
+
+    const hasTestingMd = fs.existsSync(path.join(bootstrapDir, 'TESTING.md'));
+    console.log(`TESTING.md created: ${hasTestingMd}`);
+
+    // Check for bootstrap commit
+    const gitLog = spawnSync('git', ['log', '--oneline', '--grep=bootstrap'], {
+      cwd: bootstrapDir, stdio: 'pipe',
+    });
+    const bootstrapCommits = gitLog.stdout.toString().trim();
+    console.log(`Bootstrap commits: ${bootstrapCommits || 'none'}`);
+
+    // Check for regression test commits
+    const regressionLog = spawnSync('git', ['log', '--oneline', '--grep=test(qa)'], {
+      cwd: bootstrapDir, stdio: 'pipe',
+    });
+    const regressionCommits = regressionLog.stdout.toString().trim();
+    console.log(`Regression test commits: ${regressionCommits || 'none'}`);
+
+    // Verify at least the bootstrap happened (fix commits are bonus)
+    const allCommits = spawnSync('git', ['log', '--oneline'], {
+      cwd: bootstrapDir, stdio: 'pipe',
+    });
+    const totalCommits = allCommits.stdout.toString().trim().split('\n').length;
+    console.log(`Total commits: ${totalCommits}`);
+    expect(totalCommits).toBeGreaterThan(1); // At least initial + bootstrap
+  }, 420_000);
+});
+
+// --- Test Coverage Audit E2E ---
+
+describeE2E('Test Coverage Audit E2E', () => {
+  let coverageDir: string;
+
+  beforeAll(() => {
+    coverageDir = fs.mkdtempSync(path.join(os.tmpdir(), 'skill-e2e-coverage-'));
+
+    // Copy ship skill files
+    copyDirSync(path.join(ROOT, 'ship'), path.join(coverageDir, 'ship'));
+    copyDirSync(path.join(ROOT, 'review'), path.join(coverageDir, 'review'));
+
+    // Create a Node.js project WITH test framework but coverage gaps
+    fs.writeFileSync(path.join(coverageDir, 'package.json'), JSON.stringify({
+      name: 'test-coverage-app',
+      version: '1.0.0',
+      type: 'module',
+      scripts: { test: 'echo "no tests yet"' },
+      devDependencies: { vitest: '^1.0.0' },
+    }, null, 2));
+
+    // Create vitest config
+    fs.writeFileSync(path.join(coverageDir, 'vitest.config.ts'),
+      `import { defineConfig } from 'vitest/config';\nexport default defineConfig({ test: {} });\n`);
+
+    fs.writeFileSync(path.join(coverageDir, 'VERSION'), '0.1.0.0\n');
+    fs.writeFileSync(path.join(coverageDir, 'CHANGELOG.md'), '# Changelog\n');
+
+    // Create source file with multiple code paths
+    fs.mkdirSync(path.join(coverageDir, 'src'), { recursive: true });
+    fs.writeFileSync(path.join(coverageDir, 'src', 'billing.ts'), `
+export function processPayment(amount: number, currency: string) {
+  if (amount <= 0) throw new Error('Invalid amount');
+  if (currency !== 'USD' && currency !== 'EUR') throw new Error('Unsupported currency');
+  return { status: 'success', amount, currency };
+}
+
+export function refundPayment(paymentId: string, reason: string) {
+  if (!paymentId) throw new Error('Payment ID required');
+  if (!reason) throw new Error('Reason required');
+  return { status: 'refunded', paymentId, reason };
+}
+`);
+
+    // Create a test directory with ONE test (partial coverage)
+    fs.mkdirSync(path.join(coverageDir, 'test'), { recursive: true });
+    fs.writeFileSync(path.join(coverageDir, 'test', 'billing.test.ts'), `
+import { describe, test, expect } from 'vitest';
+import { processPayment } from '../src/billing';
+
+describe('processPayment', () => {
+  test('processes valid payment', () => {
+    const result = processPayment(100, 'USD');
+    expect(result.status).toBe('success');
+  });
+  // GAP: no test for invalid amount
+  // GAP: no test for unsupported currency
+  // GAP: refundPayment not tested at all
+});
+`);
+
+    // Init git repo with main branch
+    const run = (cmd: string, args: string[]) =>
+      spawnSync(cmd, args, { cwd: coverageDir, stdio: 'pipe', timeout: 5000 });
+    run('git', ['init', '-b', 'main']);
+    run('git', ['config', 'user.email', 'test@test.com']);
+    run('git', ['config', 'user.name', 'Test']);
+    run('git', ['add', '.']);
+    run('git', ['commit', '-m', 'initial commit']);
+
+    // Create feature branch
+    run('git', ['checkout', '-b', 'feature/billing']);
+  });
+
+  afterAll(() => {
+    try { fs.rmSync(coverageDir, { recursive: true, force: true }); } catch {}
+  });
+
+  test('/ship Step 3.4 produces coverage diagram', async () => {
+    const result = await runSkillTest({
+      prompt: `Read the file ship/SKILL.md for the ship workflow instructions.
+
+You are on the feature/billing branch. The base branch is main.
+This is a test project — there is no remote, no PR to create.
+
+ONLY run Step 3.4 (Test Coverage Audit) from the ship workflow.
+Skip all other steps (tests, evals, review, version, changelog, commit, push, PR).
+
+The source code is in ${coverageDir}/src/billing.ts.
+Existing tests are in ${coverageDir}/test/billing.test.ts.
+The test command is: echo "tests pass" (mocked — just pretend tests pass).
+
+Produce the ASCII coverage diagram showing which code paths are tested and which have gaps.
+Do NOT generate new tests — just produce the diagram and coverage summary.
+Output the diagram directly.`,
+      workingDirectory: coverageDir,
+      maxTurns: 15,
+      allowedTools: ['Bash', 'Read', 'Write', 'Edit', 'Glob', 'Grep'],
+      timeout: 120_000,
+      testName: 'ship-coverage-audit',
+      runId,
+    });
+
+    logCost('/ship coverage audit', result);
+    recordE2E('/ship Step 3.4 coverage audit', 'Test Coverage Audit E2E', result, {
+      passed: result.exitReason === 'success',
+    });
+
+    expect(result.exitReason).toBe('success');
+
+    // Check output contains coverage diagram elements
+    const output = result.output || '';
+    const hasGap = output.includes('GAP') || output.includes('gap') || output.includes('NO TEST');
+    const hasTested = output.includes('TESTED') || output.includes('tested') || output.includes('✓');
+    const hasCoverage = output.includes('COVERAGE') || output.includes('coverage') || output.includes('paths tested');
+
+    console.log(`Output has GAP markers: ${hasGap}`);
+    console.log(`Output has TESTED markers: ${hasTested}`);
+    console.log(`Output has coverage summary: ${hasCoverage}`);
+
+    // At minimum, the agent should have read the source and test files
+    const readCalls = result.toolCalls.filter(tc => tc.tool === 'Read');
+    expect(readCalls.length).toBeGreaterThan(0);
+  }, 180_000);
+});
+
 // Module-level afterAll — finalize eval collector after all tests complete
 afterAll(async () => {
   if (evalCollector) {

test/skill-validation.test.ts

@@ -666,6 +666,36 @@ describe('Planted-bug fixture validation', () => {
   });
 });
 
+// --- CEO review mode validation ---
+
+describe('CEO review mode validation', () => {
+  const content = fs.readFileSync(path.join(ROOT, 'plan-ceo-review', 'SKILL.md'), 'utf-8');
+
+  test('has all four CEO review modes defined', () => {
+    const modes = ['SCOPE EXPANSION', 'SELECTIVE EXPANSION', 'HOLD SCOPE', 'SCOPE REDUCTION'];
+    for (const mode of modes) {
+      expect(content).toContain(mode);
+    }
+  });
+
+  test('has CEO plan persistence step', () => {
+    expect(content).toContain('ceo-plans');
+    expect(content).toContain('status: ACTIVE');
+  });
+
+  test('has docs/designs promotion section', () => {
+    expect(content).toContain('docs/designs');
+    expect(content).toContain('PROMOTED');
+  });
+
+  test('mode quick reference has four columns', () => {
+    expect(content).toContain('EXPANSION');
+    expect(content).toContain('SELECTIVE');
+    expect(content).toContain('HOLD SCOPE');
+    expect(content).toContain('REDUCTION');
+  });
+});
+
 // --- gstack-slug helper ---
 
 describe('gstack-slug', () => {
@@ -707,3 +737,225 @@ describe('gstack-slug', () => {
     expect(lines[1]).toMatch(/^BRANCH=.+/);
   });
 });
+
+// --- Test Bootstrap validation ---
+
+describe('Test Bootstrap ({{TEST_BOOTSTRAP}}) integration', () => {
+  test('TEST_BOOTSTRAP resolver produces valid content', () => {
+    const qaContent = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(qaContent).toContain('Test Framework Bootstrap');
+    expect(qaContent).toContain('RUNTIME:ruby');
+    expect(qaContent).toContain('RUNTIME:node');
+    expect(qaContent).toContain('RUNTIME:python');
+    expect(qaContent).toContain('no-test-bootstrap');
+    expect(qaContent).toContain('BOOTSTRAP_DECLINED');
+  });
+
+  test('TEST_BOOTSTRAP appears in qa/SKILL.md', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Test Framework Bootstrap');
+    expect(content).toContain('TESTING.md');
+    expect(content).toContain('CLAUDE.md');
+  });
+
+  test('TEST_BOOTSTRAP appears in ship/SKILL.md', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Test Framework Bootstrap');
+    expect(content).toContain('Step 2.5');
+  });
+
+  test('TEST_BOOTSTRAP appears in qa-design-review/SKILL.md', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa-design-review', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Test Framework Bootstrap');
+  });
+
+  test('TEST_BOOTSTRAP does NOT appear in qa-only/SKILL.md', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa-only', 'SKILL.md'), 'utf-8');
+    expect(content).not.toContain('Test Framework Bootstrap');
+    // But should have the recommendation note
+    expect(content).toContain('No test framework detected');
+    expect(content).toContain('Run `/qa` to bootstrap');
+  });
+
+  test('bootstrap includes framework knowledge table', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('vitest');
+    expect(content).toContain('minitest');
+    expect(content).toContain('pytest');
+    expect(content).toContain('cargo test');
+    expect(content).toContain('phpunit');
+    expect(content).toContain('ExUnit');
+  });
+
+  test('bootstrap includes CI/CD pipeline generation', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('.github/workflows/test.yml');
+    expect(content).toContain('GitHub Actions');
+  });
+
+  test('bootstrap includes first real tests step', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('First real tests');
+    expect(content).toContain('git log --since=30.days');
+    expect(content).toContain('Prioritize by risk');
+  });
+
+  test('bootstrap includes vibe coding philosophy', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('vibe coding');
+    expect(content).toContain('100% test coverage');
+  });
+
+  test('WebSearch is in allowed-tools for qa, ship, qa-design-review', () => {
+    const qa = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    const ship = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    const qaDesign = fs.readFileSync(path.join(ROOT, 'qa-design-review', 'SKILL.md'), 'utf-8');
+    expect(qa).toContain('WebSearch');
+    expect(ship).toContain('WebSearch');
+    expect(qaDesign).toContain('WebSearch');
+  });
+});
+
+// --- Phase 8e.5 regression test validation ---
+
+describe('Phase 8e.5 regression test generation', () => {
+  test('qa/SKILL.md contains Phase 8e.5', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('8e.5. Regression Test');
+    expect(content).toContain('test(qa): regression test');
+    expect(content).toContain('WTF-likelihood exclusion');
+  });
+
+  test('qa/SKILL.md Rule 13 is amended for regression tests', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Only modify tests when generating regression tests in Phase 8e.5');
+    expect(content).not.toContain('Never modify tests or CI configuration');
+  });
+
+  test('qa-design-review has CSS-aware Phase 8e.5 variant', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa-design-review', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('8e.5. Regression Test (design-review variant)');
+    expect(content).toContain('CSS-only');
+    expect(content).toContain('test(design): regression test');
+  });
+
+  test('regression test includes full attribution comment format', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('// Regression: ISSUE-NNN');
+    expect(content).toContain('// Found by /qa on');
+    expect(content).toContain('// Report: .gstack/qa-reports/');
+  });
+
+  test('regression test uses auto-incrementing names', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('auto-incrementing');
+    expect(content).toContain('max number + 1');
+  });
+});
+
+// --- Step 3.4 coverage audit validation ---
+
+describe('Step 3.4 test coverage audit', () => {
+  test('ship/SKILL.md contains Step 3.4', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Step 3.4: Test Coverage Audit');
+    expect(content).toContain('CODE PATH COVERAGE');
+  });
+
+  test('Step 3.4 includes quality scoring rubric', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('★★★');
+    expect(content).toContain('★★');
+    expect(content).toContain('edge cases AND error paths');
+    expect(content).toContain('happy path only');
+  });
+
+  test('Step 3.4 includes before/after test count', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Count test files before');
+    expect(content).toContain('Count test files after');
+  });
+
+  test('ship PR body includes Test Coverage section', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('## Test Coverage');
+  });
+
+  test('ship rules include test generation rule', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Step 3.4 generates coverage tests');
+    expect(content).toContain('Never commit failing tests');
+  });
+
+  test('Step 3.4 includes vibe coding philosophy', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('vibe coding becomes yolo coding');
+  });
+
+  test('Step 3.4 traces actual codepaths, not just syntax', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Trace every codepath');
+    expect(content).toContain('Trace data flow');
+    expect(content).toContain('Diagram the execution');
+  });
+
+  test('Step 3.4 maps user flows and interaction edge cases', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Map user flows');
+    expect(content).toContain('Interaction edge cases');
+    expect(content).toContain('Double-click');
+    expect(content).toContain('Navigate away');
+    expect(content).toContain('Error states the user can see');
+    expect(content).toContain('Empty/zero/boundary states');
+  });
+
+  test('Step 3.4 diagram includes USER FLOW COVERAGE section', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('USER FLOW COVERAGE');
+    expect(content).toContain('Code paths:');
+    expect(content).toContain('User flows:');
+  });
+});
+
+// --- Retro test health validation ---
+
+describe('Retro test health tracking', () => {
+  test('retro/SKILL.md has test health data gathering commands', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'retro', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('# 10. Test file count');
+    expect(content).toContain('# 11. Regression test commits');
+    expect(content).toContain('# 12. Test files changed');
+  });
+
+  test('retro/SKILL.md has Test Health metrics row', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'retro', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('Test Health');
+    expect(content).toContain('regression tests');
+  });
+
+  test('retro/SKILL.md has Test Health narrative section', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'retro', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('### Test Health');
+    expect(content).toContain('Total test files');
+    expect(content).toContain('vibe coding safe');
+  });
+
+  test('retro JSON schema includes test_health field', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'retro', 'SKILL.md'), 'utf-8');
+    expect(content).toContain('test_health');
+    expect(content).toContain('total_test_files');
+    expect(content).toContain('regression_test_commits');
+  });
+});
+
+// --- QA report template regression tests section ---
+
+describe('QA report template', () => {
+  test('qa-report-template.md has Regression Tests section', () => {
+    const content = fs.readFileSync(path.join(ROOT, 'qa', 'templates', 'qa-report-template.md'), 'utf-8');
+    expect(content).toContain('## Regression Tests');
+    expect(content).toContain('committed / deferred / skipped');
+    expect(content).toContain('### Deferred Tests');
+    expect(content).toContain('**Precondition:**');
+  });
+});