Visual Verdict

Yeachan-Heo/oh-my-claudecode/skills/visual-verdict

作者 Yeachan-Heo454bae017356ed1d056182cd929b6eb6cf6143ad無授權條款收錄於 2026年10月9日更新於 2026年10月9日

Structured visual QA verdict for screenshot-to-reference comparisons

AI 產生的概覽

將產生的 UI 截圖與參考圖比對,並回傳嚴格的 JSON 視覺品質判定。

功能
這個技能會指示代理將產生的 UI 截圖與一或多張參考圖比對,並只以 JSON 格式輸出判定結果。輸出包含 0-100 的分數、pass/revise/fail 判定、類別符合標記、具體視覺差異、可執行的修改建議,以及簡短的理由說明。它也定義了 90 分以上的通過門檻與重新編輯迴圈,像素差異工具僅被提及為輔助除錯手段。
適用情境
當任務有視覺還原度要求(例如版面配置、間距、字體排版或元件樣式),且你已有產生截圖和至少一張參考圖時使用。它用於在繼續修改之前取得確定性的通過或失敗指引。
執行需求
不隨附指令碼,僅為說明性內容。需要一張產生截圖與一或多張參考圖,可選提供類別提示。像素級差異工具為選用項目,僅作為輔助除錯手段。

<Purpose>

Use this skill to compare generated UI screenshots against one or more reference images and return a strict JSON verdict that can drive the next edit iteration.

</Purpose>

<Use_When>

  • The task includes visual fidelity requirements (layout, spacing, typography, component styling)
  • You have a generated screenshot and at least one reference image
  • You need deterministic pass/fail guidance before continuing edits

</Use_When>

<Inputs>

  • reference_images[] (one or more image paths)
  • generated_screenshot (current output image)
  • Optional: category_hint (e.g., hackernews, sns-feed, dashboard)

</Inputs>

<Output_Contract>

Return JSON only with this exact shape:

json
{  "score": 0,  "verdict": "revise",  "category_match": false,  "differences": ["..."],  "suggestions": ["..."],  "reasoning": "short explanation"}

Rules:

  • score: integer 0-100
  • verdict: short status (pass, revise, or fail)
  • category_match: true when the generated screenshot matches the intended UI category/style
  • differences[]: concrete visual mismatches (layout, spacing, typography, colors, hierarchy)
  • suggestions[]: actionable next edits tied to the differences
  • reasoning: 1-2 sentence summary

<Threshold_And_Loop>

  • Target pass threshold is 90+.
  • If score < 90, continue editing and rerun /oh-my-claudecode:visual-verdict before any further visual review pass.
  • Do not treat the visual task as complete until the next screenshot clears the threshold.

</Threshold_And_Loop>

<Debug_Visualization>

When mismatch diagnosis is hard:

  1. Keep $visual-verdict as the authoritative decision.
  2. Use pixel-level diff tooling (pixel diff / pixelmatch overlay) as a secondary debug aid to localize hotspots.
  3. Convert pixel diff hotspots into concrete differences[] and suggestions[] updates.

</Debug_Visualization>

<Example>

json
{  "score": 87,  "verdict": "revise",  "category_match": true,  "differences": [    "Top nav spacing is tighter than reference",    "Primary button uses smaller font weight"  ],  "suggestions": [    "Increase nav item horizontal padding by 4px",    "Set primary button font-weight to 600"  ],  "reasoning": "Core layout matches, but style details still diverge."}

</Example>

Task: {{ARGUMENTS}}

來源與署名

來源:Yeachan-Heo/oh-my-claudecode位於skills/visual-verdict提交454bae0

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架