Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →yeachan-heo/visual-verdict
Structured visual QA verdict for screenshot-to-reference comparisons
Passed 20 of 20 test cases with the skill, and 12 of 20 without it.
and 10 more in the full report
9 fixed13 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
What are the allowed string values for the verdict property in the visual comparison JSON schema?
| Checked | Without skill | With skill |
|---|---|---|
| Lists 'pass' as an allowed verdict string. | Passed | Passed |
| Lists 'revise' as an allowed verdict string. | Missed | Passed |
| Lists 'fail' as an allowed verdict string. | Passed | Passed |
The instructions your model reads when the skill loads.
<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>
test cases passed, vs 12 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.