From bbe88b3f71c8a796f0e1b0a08ba773665feff756 Mon Sep 17 00:00:00 2001
From: Garry Tan <garrytan@gmail.com>
Date: Tue, 17 Mar 2026 11:01:38 -0700
Subject: [PATCH] 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                 |  2 +-
 ship/SKILL.md.tmpl            |  2 +-
 test/skill-validation.test.ts | 24 ++++++++++++++++++++++++
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/ship/SKILL.md b/ship/SKILL.md
index 9c48b942..8a3e8e2c 100644
--- a/ship/SKILL.md
+++ b/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."
 
diff --git a/ship/SKILL.md.tmpl b/ship/SKILL.md.tmpl
index cbf487ce..2c9707c1 100644
--- a/ship/SKILL.md.tmpl
+++ b/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."
 
diff --git a/test/skill-validation.test.ts b/test/skill-validation.test.ts
index 62ec3fdc..54e03a4d 100644
--- a/test/skill-validation.test.ts
+++ b/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 ---