Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →florianbruniaux/validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing
Passed 18 of 22 test cases with the skill, and 11 of 22 without it.
and 5 more in the full report
8 fixed10 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
The automated diff evaluator returned a verdict of NEEDS_REVIEW with two medium-severity issues and a fix suggestion. What exact options must be presented to the user to choose how to proceed?
| Checked | Without skill | With skill |
|---|---|---|
| Offers option to fix issues and re-evaluate. | Missed | Passed |
| Offers option to commit anyway while acknowledging risks alongside option to abort. | Passed | Passed |
The instructions your model reads when the skill loads.
Evaluate staged git changes using the output-evaluator agent to catch issues before committing.
Run git diff --cached --stat to see what's staged. If nothing is staged, inform the user and exit.
Run git diff --cached to get the complete diff of all staged changes.
Use the Task tool to launch the output-evaluator agent with the diff:
Evaluate these staged changes for correctness, completeness, and safety.
Return a JSON verdict with scores and issues.
Changes:
[paste the git diff here]
Based on the evaluation result:
If APPROVE:
If NEEDS_REVIEW:
test cases passed, vs 11 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.