con un clic
visual-verdict
Structured visual QA verdict for screenshot-to-reference comparisons
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
Structured visual QA verdict for screenshot-to-reference comparisons
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Use when changing CrispyTivi visual design, design tokens, Penpot assets, Widgetbook stories, component catalog coverage, or UI design-system docs.
Use when creating, resetting, publishing, or verifying CrispyTivi Penpot design-system artifacts through local Penpot MCP/REPL, including tokens, components, variants, assets, and editable screen patterns.
Use when adding or fixing CrispyTivi Widgetbook design-system coverage, especially official per-widget @UseCase annotations, fixture-backed use cases, design links, and Widgetbook build verification.
Run an anti-slop cleanup/refactor/deslop workflow
Full autonomous execution from idea to working code
Configure OMX notifications - unified entry point for all platforms
| name | visual-verdict |
| description | Structured visual QA verdict for screenshot-to-reference comparisons |
<Use_When>
<Output_Contract> Return JSON only with this exact shape:
{
"score": 0,
"verdict": "revise",
"category_match": false,
"differences": ["..."],
"suggestions": ["..."],
"reasoning": "short explanation"
}
Rules:
score: integer 0-100verdict: short status (pass, revise, or fail)category_match: true when the generated screenshot matches the intended UI category/styledifferences[]: concrete visual mismatches (layout, spacing, typography, colors, hierarchy)suggestions[]: actionable next edits tied to the differencesreasoning: 1-2 sentence summary<Threshold_And_Loop>
score < 90, continue editing and rerun $visual-verdict before any further code edits in the next iteration..omx/state/{scope}/ralph-progress.json with both:
score, threshold pass/fail)reasoning, suggestions, next_actions)
</Threshold_And_Loop><Debug_Visualization> When mismatch diagnosis is hard:
$visual-verdict as the authoritative decision.differences[] and suggestions[] updates.
</Debug_Visualization>