Skip to content

feat: interactive /plan-design-review + CEO invokes designer + 100% coverage (v0.6.4)#149

Merged
garrytan merged 7 commits intomainfrom
garrytan/ceo-calls-designer
Mar 18, 2026
Merged

feat: interactive /plan-design-review + CEO invokes designer + 100% coverage (v0.6.4)#149
garrytan merged 7 commits intomainfrom
garrytan/ceo-calls-designer

Conversation

@garrytan
Copy link
Owner

Summary

  • /plan-design-review rewritten from report-only grading to interactive plan-fixer — rates each design dimension 0-10, explains what a 10 looks like, edits the plan to get there. Parallel structure with /plan-ceo-review and /plan-eng-review.
  • CEO review now detects UI scope and invokes a Design & UX section (Section 11) covering information architecture, interaction states, AI slop risk, and responsive intention.
  • Renamed /qa-design-review/design-review (the "qa-" prefix was confusing).
  • 14/15 skills now at full test coverage (E2E + LLM-judge + validation). Added LLM-judge for 10 skills, real E2E for gstack-upgrade, design-consultation validation.
  • CLAUDE.md now requires bisect commits.

Test Coverage

  • 271 free tests passing (validation + gen-skill-docs + touchfiles)
  • 10 new LLM-judge tests (~$0.20/run)
  • 1 new E2E test for gstack-upgrade (~$0.35/run)
  • 20 new validation tests (contributor mode, command validation, hardcoded branches)
  • setup-browser-cookies remains deferred (needs real browser)

Pre-Landing Review

No issues found. All changes are skill templates, test files, docs, and build scripts.

Design Review

No frontend files changed — design review skipped.

Test plan

  • All 271 free tests pass (0 failures)
  • No application code changed — evals skipped
  • grep -r 'qa-design-review' returns zero hits

🤖 Generated with Claude Code

garrytan and others added 7 commits March 17, 2026 20:23
The "qa-" prefix was confusing — this is the live-site design audit with
fix loop, not a QA-only report. Rename directory and update all references
across docs, tests, scripts, and skill templates.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Rewrite /plan-design-review from report-only grading to an interactive
plan-fixer that rates each design dimension 0-10, explains what a 10
looks like, and edits the plan to get there. Parallel structure with
/plan-ceo-review and /plan-eng-review — one issue = one AskUserQuestion.

CEO review now detects UI scope and invokes the designer perspective
when the plan has frontend/UX work, so you get design review
automatically when it matters.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add design-consultation to command/snapshot flag validation. Add 4
skills to contributor mode validation (plan-design-review,
design-review, design-consultation, document-release). Add 2 templates
to hardcoded branch check. Register touchfile entries for 10 new
LLM-judge tests and 1 new E2E test.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Add LLM-judge quality evals for all uncovered skills using a DRY
runWorkflowJudge helper with section marker guards. Add real E2E
test for gstack-upgrade using mock git remote (replaces test.todo).
Add plan-edit assertion to plan-design-review E2E.

14/15 skills now at full coverage. setup-browser-cookies remains
deferred (needs real browser).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
All commits should be single logical changes, split before pushing.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
@garrytan garrytan merged commit 78c207e into main Mar 18, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant