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
- Lucface/claude-skillsedited, first seen Nov 16, 2026
- Yeachan-Heo/oh-my-claudecodeedited, first seen Nov 9, 2026
- LucasCooperBey/claude-skillsedited, first seen Oct 20, 2026
- Gopyr/gopyr-skills-hubedited, first seen Oct 11, 2026
- SHYXIN/skillsedited, first seen Oct 11, 2026
- Yeachan-Heo/oh-my-claude-sisyphusedited, first seen Oct 8, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 6
- Yeachan-Heo/oh-my-claudecode★ 41k88% same
- Yeachan-Heo/oh-my-claude-sisyphus★ 41k88% same
- SHYXIN/skills★ 611% same
- LucasCooperBey/claude-skills★ 111% same
- Lucface/claude-skills★ 111% same
- Gopyr/gopyr-skills-hub★ 020% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository119 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accessibilitySkill
- frontend-designSkill
- python-background-jobsSkill
- python-executorSkill
- python-testing-patternsSkill
- seoSkill
- ai-slop-cleanerSkill
- analyzeSkill
- api-and-interface-designSkill
- ask-claudeSkill
- ask-geminiSkill
- autopilotSkill
- browser-testing-with-devtoolsSkill
- build-fixSkill
- cancelSkill
- ci-cd-and-automationSkill
- clawd-change-workflowSkill
- code-review-and-qualitySkill
- code-reviewSkill
- code-simplificationSkill
- configure-notificationsSkill
- context-engineeringSkill
- debugging-and-error-recoverySkill
- deep-interviewSkill
- deepsearchSkill
- deprecation-and-migrationSkill
- doctorSkill
- documentation-and-adrsSkill
- ecomodeSkill
- frontend-ui-engineeringSkill
- frontend-ui-uxSkill
- git-masterSkill
- git-workflow-and-versioningSkill
- helpSkill
- hudSkill
- idea-refineSkill
- incremental-implementationSkill
- intent_routerSkill
- keyword_registrySkill
- mode_stateSkill
- noteSkill
- omx-setupSkill
- performance-optimizationSkill
- pipeline_orchestratorSkill
- pipelineSkill
- planning-and-task-breakdownSkill
- planSkill
- ralph-initSkill
- ralph_loopSkill
- ralphSkill
- ralplanSkill
- android-reverse-engineeringSkill
- api-securitySkill
- apk-reverseSkill
- attack-chainSkill
- binary-diffSkill
- browser-automationSkill
- The first 60 shown.
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
- Distinctive: line 7
Use this skill to compare generated UI screenshots against one or more reference images and return a strict JSON verdict that can drive the …
- Very specific: line 46
If score < 90, continue editing and rerun $visual-verdict before any further code edits in the next iteration.
- Common: line 53
When mismatch diagnosis is hard:
- Very specific: line 54
Keep $visual-verdict as the authoritative decision.
- Common: line 55
Use pixel-level diff tooling (pixel diff / pixelmatch overlay) as a secondary debug aid to localize hotspots.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<Purpose>
Use this skill to compare generated UI screenshots against one or more reference images and return a strict JSON verdict that can drive the next edit iteration.
</Purpose><Use_When>
- The task includes visual fidelity requirements (layout, spacing, typography, component styling)
- You have a generated screenshot and at least one reference image
- You need deterministic pass/fail guidance before continuing edits </Use_When>
<Inputs>
- `reference_images[]` (one or more image paths)
- `generated_screenshot` (current output image)
- Optional: `category_hint` (e.g., `hackernews`, `sns-feed`, `dashboard`)
</Inputs><Output_Contract> Return JSON only with this exact shape:
{
"score": 0,
"verdict": "revise",
"category_match": false,
"differences": ["..."],
"suggestions": ["..."],
"reasoning": "short explanation"
}Rules:
score: integer 0-100verdict: short status (pass,revise, orfail)category_match:truewhen the generated screenshot matches the intended UI category/styledifferences[]: concrete visual mismatches (layout, spacing, typography, colors, hierarchy)suggestions[]: actionable next edits tied to the differencesreasoning: 1-2 sentence summary
<Threshold_And_Loop>
- Target pass threshold is 90+.
- If
score < 90, continue editing and rerun$visual-verdictbefore any further code edits in the next iteration. - Persist the verdict in
.omx/state/{scope}/ralph-progress.jsonwith both:- numeric signal (
score, threshold pass/fail) - qualitative signal (
reasoning,suggestions,next_actions) </Threshold_And_Loop>
- numeric signal (
<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>
```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>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
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.

