Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →rlaope/triage-sweep
Backfill labels across oh-my-hermes issues and pull requests. Run manually to sweep everything currently unlabeled, or pass a number to triage one item.
Passed 4 of 9 test cases with the skill, and 2 of 9 without it.
and 5 more in the full report
5 fixed4 passed either way12 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
Which shell commands should be executed to read the triage procedure and label schema prior to beginning issue evaluation?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies running cat docs/TRIAGE-SWEEP.md. | Missed | Passed |
| Specifies running cat .github/labels.yml. | Passed | Passed |
The instructions your model reads when the skill loads.
The procedure lives in docs/TRIAGE-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 /triage-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/TRIAGE-SWEEP.md
cat .github/labels.yml
Two things worth knowing before you open the procedure, because they are what the sweep gets wrong most often:
.github/labels.yml is the entire allowlist. Never apply a label that is
not in it, and never create one on the fly.--apply.Arguments pass through verbatim: a bare number triages one item, sync-labels
reconciles the repository against the manifest, --closed widens the sweep,
--apply writes.
test cases passed, vs 2 / 9 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.