Merge branch 'main' into garrytan/team-supabase-store

Resolved 4 conflicts:
- scripts/gen-skill-docs.ts: kept ARTIFACT_SETUP + added main's new
  resolvers (SPEC_REVIEW_LOOP, DESIGN_SKETCH, BENEFITS_FROM,
  CODEX_REVIEW_STEP). Updated codex review-log to use new paths.
- ship/SKILL.md.tmpl: adopted {{CODEX_REVIEW_STEP}} macro from main
- test/skill-e2e.test.ts: added main's new E2E tests (office-hours
  spec review, plan-ceo benefits-from) + kept our E2E isolation cleanup

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-21 09:29:05 -07:00
96 changed files with 17868 additions and 342 deletions
+158 -4
View File
@@ -630,6 +630,59 @@ describe('office-hours skill structure', () => {
test('contains builder operating principles', () => {
expect(content).toContain('Delight is the currency');
});
// Spec Review Loop (Phase 5.5)
test('contains spec review loop', () => {
expect(content).toContain('Spec Review Loop');
});
test('contains adversarial review dimensions', () => {
for (const dim of ['Completeness', 'Consistency', 'Clarity', 'Scope', 'Feasibility']) {
expect(content).toContain(dim);
}
});
test('contains subagent dispatch instruction', () => {
expect(content).toMatch(/Agent.*tool|subagent/i);
});
test('contains max 3 iterations', () => {
expect(content).toMatch(/3.*iteration|maximum.*3/i);
});
test('contains quality score', () => {
expect(content).toContain('quality score');
});
test('contains spec review metrics path', () => {
expect(content).toContain('spec-review.jsonl');
});
test('contains convergence guard', () => {
expect(content).toMatch(/convergence/i);
});
// Visual Sketch (Phase 4.5)
test('contains visual sketch section', () => {
expect(content).toContain('Visual Sketch');
});
test('contains wireframe generation', () => {
expect(content).toMatch(/wireframe|sketch/i);
});
test('contains DESIGN.md awareness', () => {
expect(content).toContain('DESIGN.md');
});
test('contains browse rendering', () => {
expect(content).toContain('$B goto');
expect(content).toContain('$B screenshot');
});
test('contains rough aesthetic instruction', () => {
expect(content).toMatch(/rough|hand-drawn/i);
});
});
describe('investigate skill structure', () => {
@@ -842,6 +895,22 @@ describe('CEO review mode validation', () => {
expect(content).toContain('HOLD SCOPE');
expect(content).toContain('REDUCTION');
});
// Skill chaining (benefits-from)
test('contains prerequisite skill offer for office-hours', () => {
expect(content).toContain('Prerequisite Skill Offer');
expect(content).toContain('/office-hours');
});
test('contains mid-session detection', () => {
expect(content).toContain('Mid-session detection');
expect(content).toMatch(/still figuring out|seems lost/i);
});
// Spec review on CEO plans
test('contains spec review loop for CEO plan documents', () => {
expect(content).toContain('Spec Review Loop');
});
});
// --- gstack-slug helper ---
@@ -1174,18 +1243,36 @@ describe('Codex skill', () => {
expect(content).toContain('mktemp');
});
test('codex integration in /review offers second opinion', () => {
test('codex integration in /review has config-driven review step', () => {
const content = fs.readFileSync(path.join(ROOT, 'review', 'SKILL.md'), 'utf-8');
expect(content).toContain('Codex second opinion');
expect(content).toContain('Codex review');
expect(content).toContain('codex_reviews');
expect(content).toContain('codex review');
expect(content).toContain('adversarial');
expect(content).toContain('xhigh');
expect(content).toContain('Investigate and fix');
expect(content).toContain('CROSS-MODEL');
});
test('codex integration in /ship offers review gate', () => {
test('codex integration in /ship has config-driven review step', () => {
const content = fs.readFileSync(path.join(ROOT, 'ship', 'SKILL.md'), 'utf-8');
expect(content).toContain('Codex');
expect(content).toContain('Codex review');
expect(content).toContain('codex_reviews');
expect(content).toContain('codex review');
expect(content).toContain('codex-review');
expect(content).toContain('xhigh');
expect(content).toContain('Investigate and fix');
});
test('codex-host ship/review do NOT contain codex review step', () => {
const shipContent = fs.readFileSync(path.join(ROOT, '.agents', 'skills', 'gstack-ship', 'SKILL.md'), 'utf-8');
expect(shipContent).not.toContain('codex review --base');
expect(shipContent).not.toContain('Investigate and fix');
const reviewContent = fs.readFileSync(path.join(ROOT, '.agents', 'skills', 'gstack-review', 'SKILL.md'), 'utf-8');
expect(reviewContent).not.toContain('codex review --base');
expect(reviewContent).not.toContain('codex_reviews');
expect(reviewContent).not.toContain('Investigate and fix');
});
test('codex integration in /plan-eng-review offers plan critique', () => {
@@ -1244,3 +1331,70 @@ describe('Skill trigger phrases', () => {
});
}
});
// ─── Codex Skill Validation ──────────────────────────────────
describe('Codex skill validation', () => {
const AGENTS_DIR = path.join(ROOT, '.agents', 'skills');
// Discover all Claude skills with templates (except /codex which is Claude-only)
const CLAUDE_SKILLS_WITH_TEMPLATES = (() => {
const skills: string[] = [];
for (const entry of fs.readdirSync(ROOT, { withFileTypes: true })) {
if (!entry.isDirectory() || entry.name.startsWith('.') || entry.name === 'node_modules') continue;
if (entry.name === 'codex') continue; // Claude-only skill
if (fs.existsSync(path.join(ROOT, entry.name, 'SKILL.md.tmpl'))) {
skills.push(entry.name);
}
}
return skills;
})();
test('all skills (except /codex) have both Claude and Codex variants', () => {
for (const skillDir of CLAUDE_SKILLS_WITH_TEMPLATES) {
// Claude variant
const claudeMd = path.join(ROOT, skillDir, 'SKILL.md');
expect(fs.existsSync(claudeMd)).toBe(true);
// Codex variant
const codexName = skillDir.startsWith('gstack-') ? skillDir : `gstack-${skillDir}`;
const codexMd = path.join(AGENTS_DIR, codexName, 'SKILL.md');
expect(fs.existsSync(codexMd)).toBe(true);
}
// Root template has both too
expect(fs.existsSync(path.join(ROOT, 'SKILL.md'))).toBe(true);
expect(fs.existsSync(path.join(AGENTS_DIR, 'gstack', 'SKILL.md'))).toBe(true);
});
test('/codex skill is Claude-only — no Codex variant', () => {
// Claude variant should exist
expect(fs.existsSync(path.join(ROOT, 'codex', 'SKILL.md'))).toBe(true);
// Codex variant must NOT exist
expect(fs.existsSync(path.join(AGENTS_DIR, 'gstack-codex', 'SKILL.md'))).toBe(false);
});
test('Codex skill names follow gstack-{name} convention', () => {
const codexDirs = fs.readdirSync(AGENTS_DIR);
for (const dir of codexDirs) {
// Every directory should start with gstack
expect(dir.startsWith('gstack')).toBe(true);
// Root is just 'gstack', others are 'gstack-{name}'
if (dir !== 'gstack') {
expect(dir.startsWith('gstack-')).toBe(true);
}
}
});
test('$B commands in Codex SKILL.md files are valid browse commands', () => {
const codexDirs = fs.readdirSync(AGENTS_DIR);
for (const dir of codexDirs) {
const skillMd = path.join(AGENTS_DIR, dir, 'SKILL.md');
if (!fs.existsSync(skillMd)) continue;
const content = fs.readFileSync(skillMd, 'utf-8');
// Only validate if the skill contains $B commands
if (!content.includes('$B ')) continue;
const result = validateSkill(skillMd);
expect(result.invalid).toHaveLength(0);
}
});
});