Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jaypokale/chisle-review
Review a diff or file through the Chisle lens: flag over-engineering, speculative abstractions, reinvented stdlib, and verbose code that a lazier approach would shrink. One finding per line, no praise.
Passed 7 of 22 test cases with the skill, and 15 of 22 without it.
and 1 more in the full report
4 fixed13 passed either way3 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Please review the PR diff in `src/utils/data-helpers.ts` for unnecessary complexity or over-engineered code that can be pruned or simplified. For each issue found, format your output as `filepath:line: <over-engineered code description>. <simpler alternative>.` with one finding per line, omitting any intro text or praise. Conclude with a final summary line stating total findings and estimated lines removable.
| Checked | Without skill | With skill |
|---|---|---|
| The final summary line strictly matches the format ending in 'findings. Est. X lines removable.' | Missed | Passed |
The instructions your model reads when the skill loads.
Review the diff/file for what could be deleted or simplified, not for style nits.
<input type>) does itOne finding per line. No preamble, no praise.
path:line: <what's over-built>. <the lazier replacement>.
Example:
cache.js:12: ApiCacheManager class for one call site. Replace with lru_cache / a Map.
search.js:40: hand-rolled debounce util. setTimeout+clearTimeout inline is enough.
End with a one-line verdict: N findings. Est. <X> lines removable.
test cases passed, vs 15 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.