visual-verdict 精选
Structured visual QA verdict for screenshot-to-reference comparisons
安装方式
cp -r skills/visual-verdict ~/.claude/skills/visual-verdict把该 skill 目录放进客户端 skills 目录。不同客户端的目录可能不同,Claude Code 默认是 ~/.claude/skills/
/plugin marketplace add Yeachan-Heo/oh-my-claudecode⚠️ 该命令形态随客户端版本变化,仅在检测到 .claude-plugin/marketplace.json 时展示;不可用时请用「目录复制」。
https://raw.githubusercontent.com/Yeachan-Heo/oh-my-claudecode/8262f9f790eed35e6cbd66572b36c2acba18f679/skills/visual-verdict/SKILL.md下载后另存为 ~/.claude/skills/visual-verdict/SKILL.md。链接锁定采集时的 commit,内容与本站展示一致。
整仓一次性获取:git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecode.git
依赖与权限
- 无需 API Key
- 无需联网
- 依赖外部命令:
convert - 以上为按正文与 frontmatter 自动推断的信号,仅供参考;安装前建议先阅读原文。
SKILL.md 正文
<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:
{
"score": 0,
"verdict": "revise",
"category_match": false,
"differences": ["..."],
"suggestions": ["..."],
"reasoning": "short explanation"
}
Rules:
score: integer 0-100verdict: short status (pass,revise, orfail)category_match:truewhen 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>
- Target pass threshold is 90+.
- If
score < 90, continue editing and rerun/oh-my-claudecode:visual-verdictbefore 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:
- Keep
$visual-verdictas the authoritative decision. - Use pixel-level diff tooling (pixel diff / pixelmatch overlay) as a secondary debug aid to localize hotspots.
- Convert pixel diff hotspots into concrete
differences[]andsuggestions[]updates.
</Debug_Visualization>
<Example>
{
"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}}
质量与来源
- 所属仓库
- Yeachan-Heo/oh-my-claudecode
- 仓库星标
- 4.0 万
- 最近更新
- 今天
- 采集时间
- 今天
- commit
- 8262f9f790ee
- 内容指纹
- sha256:c12387097005656
- 文件路径
- skills/visual-verdict/SKILL.md