fix: raise test gen cap to 20, add validation tests for user flow coverage

- Raise Step 3.4 test generation cap from 10 to 20 (code + user flow combined)
- Add 3 validation tests: codepath tracing, user flow mapping, diagram sections

ship/SKILL.md

@@ -557,7 +557,7 @@ If test framework detected (or bootstrapped in Step 2.5):
 - Run each test. Passes → commit as `test: coverage for {feature}`
 - Fails → fix once. Still fails → revert, note gap in diagram.
 
-Caps: 30 code paths max, 10 tests generated max, 2-min per-test exploration cap.
+Caps: 30 code paths max, 20 tests generated max (code + user flow combined), 2-min per-test exploration cap.
 
 If no test framework AND user declined bootstrap → diagram only, no generation. Note: "Test generation skipped — no test framework configured."
 

ship/SKILL.md.tmpl

@@ -288,7 +288,7 @@ If test framework detected (or bootstrapped in Step 2.5):
 - Run each test. Passes → commit as `test: coverage for {feature}`
 - Fails → fix once. Still fails → revert, note gap in diagram.
 
-Caps: 30 code paths max, 10 tests generated max, 2-min per-test exploration cap.
+Caps: 30 code paths max, 20 tests generated max (code + user flow combined), 2-min per-test exploration cap.
 
 If no test framework AND user declined bootstrap → diagram only, no generation. Note: "Test generation skipped — no test framework configured."
 

test/skill-validation.test.ts

@@ -891,6 +891,30 @@ describe('Step 3.4 test coverage audit', () => {
     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 ---