Install any skill in seconds. Free to start, no credit card required.
Get Started Free →hyhmrright/brooks-review
PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on twelve classic engineering books.
Passed 11 of 22 test cases with the skill, and 6 of 22 without it.
and 4 more in the full report
7 fixed4 passed either way9 still failing2 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.
When reviewing `backend/analytics_job.py` for code decay, where are the symptom definitions and source attributions defined?
| Checked | Without skill | With skill |
|---|---|---|
| The review process references decay-risks.md for symptom definitions. | Missed | Passed |
The instructions your model reads when the skill loads.
Read in order:
../_shared/common.md — Iron Law, Project Config, Report Template, Health Score../_shared/source-coverage.md — book coverage, exceptions, tradeoffs../_shared/decay-risks.md — symptom definitions and source attributionspr-review-guide.md (this directory) — the analysis processScope: if the user did not specify files or paste code, apply Auto Scope Detection
(../_shared/common.md) first.
Mode line in report: PR Review
test cases passed, vs 6 / 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.