بنقرة واحدة
visual-verdict
Structured visual QA verdict for screenshot-to-reference comparisons
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
Structured visual QA verdict for screenshot-to-reference comparisons
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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>