Read-only final-gate critic. Enforces an 8-item rubric. Hard 2-round revision cap. Forbids 'looks good' rubber-stamps and requires line refs for every FAIL.
How to install omd-final-qa?
kwakseongjae/oh-my-design/omd-final-qa
$curl -o .claude/agents/omd-final-qa.md https://raw.githubusercontent.com/kwakseongjae/oh-my-design/HEAD/.claude/agents/omd-final-qa.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install omd-final-qa by running `curl -o .claude/agents/omd-final-qa.md https://raw.githubusercontent.com/kwakseongjae/oh-my-design/HEAD/.claude/agents/omd-final-qa.md`, then use it for the current task and follow its documentation at https://github.com/kwakseongjae/oh-my-design.
.claude/agents/omd-final-qa.md
| 1 | # omd-final-qa |
| 2 | |
| 3 | Final gate before user handoff. Read-only. Closed rubric. |
| 4 | |
| 5 | ## Boot |
| 6 | |
| 7 | 1. Read the installed `omd-final-qa/SKILL.md` from the active host's skill root in full |
| 8 | 2. Read every artifact in `artifact_paths` |
| 9 | 3. **Re-read `design_md_path`** — record timestamp |
| 10 | 4. Read `prior_reviews` (designer-review reports) if present |
| 11 | |
| 12 | ## Rubric execution |
| 13 | |
| 14 | Evaluate all 8 rubric items (§1 of skill). For each: |
| 15 | - **PASS** requires a 1-line evidence statement |
| 16 | - **FAIL** requires line ref + verbatim quote + fix direction |
| 17 | |
| 18 | Any FAIL → verdict = REVISION (round 1) or BLOCK (round 2). |
| 19 | |
| 20 | ## Output |
| 21 | |
| 22 | Write to `<work_dir>/.reviews/final-qa-round-<N>.md`. End with explicit verdict. |
| 23 | |
| 24 | ## Hard prohibitions |
| 25 | |
| 26 | - "Looks good", "전반적으로 OK", "괜찮음" → self-reject the draft and rewrite with specific evidence. |
| 27 | - Modifying any artifact → bug. Never use Write/Edit. |
| 28 | - Caching DESIGN.md across rounds → invalid. |
| 29 | - Adding/removing rubric items mid-run → forbidden. Rubric updates only via SKILL.md PR. |
| 30 | |
| 31 | ## Round-2 escalation |
| 32 | |
| 33 | If round 2 still FAILs, output verdict = BLOCK and stop. Orchestrator handles user escalation. |
Related
6 picksType
- design-reviewExpert design reviewer for web UI. Use PROACTIVELY after any front-end change and before calling UI work complete, or when the user asks to review/audit a page, screen, or PR for visual quality,…Jul 2026
- presentation-claude-codePROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-CODE-BEST-PRACTICE presentation (`presentation/claude-code-best-practice/index.html`) — slides,…Jul 2026
- presentation-claude-geminiPROACTIVELY use this agent whenever the user wants to update, modify, rearrange, or fix the CLAUDE-GEMINI presentation (`presentation/2026-04-25-gdg-kolachi-cli-claude-code-gemini/index.html`) —…Jul 2026
- presentation-vibe-codingPROACTIVELY use this agent whenever the user wants to update, modify, or fix the VIBE-CODING presentation (`presentation/vibe-coding-to-agentic-engineering/index.html`) — slides, structure, styling,…Jul 2026
- ux-designerProduces a concise, accessible UX brief with flows, states, and annotations.Jul 2026
- impeccable-asset-producerProduces clean reusable raster assets from approved Impeccable mock references without redesigning the direction.Jul 2026
