skill-review
A composable skill that wraps the Seven Sweeps + auxiliary review gates. /mb-site calls this at pre-lock and pre-publish.
Inputs
- The artifact under review (brief or copy draft)
- The dial (
convert | story | brand)
- Reference files (voice.md, audience.md, optional research/*)
- The brief's
do_not_state list (for archetype-fidelity check)
Outputs
A synthesized review report:
{
"ok": false,
"dial": "convert",
"sweeps_run": [1, 2, 3, 4, 5, 6, 7],
"findings": [
{"sweep": "Specificity", "priority": "P1", "line": 12, "note": "..."},
...
],
"panel_score": 7.2,
"blocking": ["specificity", "ai-tells"]
}
Flow
- Load the artifact and the dial.
- Pick sweeps from
references/review.md — dial-gated.
- Spawn one foreground subagent per active sweep, in parallel. Each returns short findings (P1/P2/P3 with line refs).
- Run auxiliary gates in parallel: De-AI'd, Framework-true, Archetype-fidelity.
- (Convert dial only) Run Expert Panel scoring across 3-5 personas.
- Synthesize findings into one report; group by sweep, P-priority, line.
- Return to caller (which surfaces to operator).
Dial-gated sweeps
| Dial |
Sweeps |
convert |
1, 2, 3, 4, 5, 6, 7 + Expert Panel |
story |
1, 2, 3, 5, 6 |
brand |
1, 2, 6 |
Cross-references
- references/review.md
- references/anti-patterns.md
1---2name: mb-skill-review3description: Pre-publish review / UI pass / design pass / design critique for a brief or copy draft: runs dial-gated Seven Sweeps + auxiliary gates and returns synthesized findings. Use when: the operator asks for a pre-publish review, a UI pass, a design pass, a design critique, or to review a page before publishing. Called by /mb-site at pre-lock and pre-publish; reusable by /mb-ads and sales-video workflows.4---56# skill-review78A composable skill that wraps the Seven Sweeps + auxiliary review gates. /mb-site calls this at pre-lock and pre-publish.910## Inputs1112- The artifact under review (brief or copy draft)13- The dial (`convert | story | brand`)14- Reference files (voice.md, audience.md, optional research/*)15- The brief's `do_not_state` list (for archetype-fidelity check)1617## Outputs1819A synthesized review report:2021```22{23 "ok": false,24 "dial": "convert",25 "sweeps_run": [1, 2, 3, 4, 5, 6, 7],26 "findings": [27 {"sweep": "Specificity", "priority": "P1", "line": 12, "note": "..."},28 ...29 ],30 "panel_score": 7.2,31 "blocking": ["specificity", "ai-tells"]32}33```3435## Flow36371. **Load the artifact** and the dial.382. **Pick sweeps** from [`references/review.md`](references/review.md) — dial-gated.393. **Spawn one foreground subagent per active sweep, in parallel.** Each returns short findings (P1/P2/P3 with line refs).404. **Run auxiliary gates** in parallel: De-AI'd, Framework-true, Archetype-fidelity.415. **(Convert dial only)** Run Expert Panel scoring across 3-5 personas.426. **Synthesize** findings into one report; group by sweep, P-priority, line.437. **Return** to caller (which surfaces to operator).4445## Dial-gated sweeps4647| Dial | Sweeps |48|---|---|49| `convert` | 1, 2, 3, 4, 5, 6, 7 + Expert Panel |50| `story` | 1, 2, 3, 5, 6 |51| `brand` | 1, 2, 6 |5253## Cross-references5455- [references/review.md](references/review.md)56- [references/anti-patterns.md](references/anti-patterns.md)
noontide-co