agentleFS
lza6lza6/claw-code-tingfeng/skills/visual-verdict/SKILL.md

visual-verdict

Skill5 starsChanged 17 days agoMITView on GitHub

Structured visual QA verdict for screenshot-to-reference comparisons

6 other projects use a version of this, 6 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 2 are common, 1 is distinctive, and 2 are very specific to this project.

  • 2

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

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

    line 7
  2. Very specific:

    If score < 90, continue editing and rerun $visual-verdict before any further code edits in the next iteration.

    line 46
  3. Common:

    When mismatch diagnosis is hard:

    line 53
  4. Very specific:

    Keep $visual-verdict as the authoritative decision.

    line 54
  5. Common:

    Use pixel-level diff tooling (pixel diff / pixelmatch overlay) as a secondary debug aid to localize hotspots.

    line 55

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<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 0-100
  • 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 $visual-verdict before any further code edits in the next iteration.
  • Persist the verdict in .omx/state/{scope}/ralph-progress.json with both:
    • numeric signal (score, threshold pass/fail)
    • qualitative signal (reasoning, suggestions, next_actions) </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>

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.