Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →rlaope/review-sweep
Review oh-my-hermes pull requests that have not been reviewed at their current head commit. Run manually to sweep the open backlog, or pass a number to review one PR. Applies the repository's REVIEW.md policy and posts findings as a GitHub review with inline comments.
Passed 4 of 10 test cases with the skill, and 3 of 10 without it.
and 3 more in the full report
4 fixed6 passed either way12 still failing1 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.
Before executing any commands for PR #50 review, which file should be read immediately after docs/REVIEW-SWEEP.md?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies REVIEW.md as the file to read immediately after docs/REVIEW-SWEEP.md. | Missed | Passed |
The instructions your model reads when the skill loads.
The procedure lives in docs/REVIEW-SWEEP.md.
Read that file and follow it.
It is kept there rather than here because Codex, Hermes handoffs, and generic
executor profiles run the same sweep, and AGENTS.md requires that no single
executor own a shared surface. This file exists so the procedure is reachable
as /review-sweep; it deliberately holds no rules of its own, so there is
nothing here to drift out of sync with the real one.
Start by reading, in this order:
cat docs/REVIEW-SWEEP.md
cat REVIEW.md
Two things worth knowing before you open the procedure, because they are what the sweep gets wrong most often:
--apply.Arguments pass through verbatim: a bare number reviews one PR, --drafts and
--mine widen the sweep, --apply posts.
test cases passed, vs 3 / 10 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.