fix: journey routing tests — CLAUDE.md routing rules + stronger descriptions

Three journey E2E tests (ideation, ship, debug) were failing because
Claude answered directly instead of invoking the Skill tool. Root cause:
skill descriptions in system-reminder are too weak to override Claude's
default behavior for tasks it can handle natively.

Fix has two parts:
1. CLAUDE.md routing rules in test workdir — Claude weighs project-level
   instructions higher than skill description metadata
2. "Proactively invoke" (not "suggest") in office-hours, investigate,
   ship descriptions — reinforces the routing signal

10/10 journey tests now pass (was 7/10).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-03-29 20:44:11 -07:00
parent 0784264aa0
commit a2ee09519c
10 changed files with 110 additions and 61 deletions
+2 -2
View File
@@ -1409,13 +1409,13 @@ describe('Skill trigger phrases', () => {
];
for (const skill of SKILLS_REQUIRING_PROACTIVE) {
test(`${skill}/SKILL.md has "Proactively suggest" phrase`, () => {
test(`${skill}/SKILL.md has proactive routing phrase`, () => {
const skillPath = path.join(ROOT, skill, 'SKILL.md');
if (!fs.existsSync(skillPath)) return;
const content = fs.readFileSync(skillPath, 'utf-8');
const frontmatterEnd = content.indexOf('---', 4);
const frontmatter = content.slice(0, frontmatterEnd);
expect(frontmatter).toMatch(/Proactively suggest/i);
expect(frontmatter).toMatch(/Proactively (suggest|invoke)/i);
});
}
});