Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →stevesolun/triage
Classify and advance issues or external pull requests through the configured triage workflow. Use explicitly to inspect queues, evaluate an item, recommend a state, or apply an authorized transition.
Passed 13 of 17 test cases with the skill, and 8 of 17 without it.
and 9 more in the full report
9 fixed8 passed either way3 still failing3 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.
Draft a triage comment for issue #1301 notifying the author that their bug report has been received and classified. Write out the exact comment text starting line.
| Checked | Without skill | With skill |
|---|---|---|
| The draft comment starts with the exact blockquote prefix '> *This was generated by AI during triage.*'. | Missed | Passed |
The instructions your model reads when the skill loads.
Use the repository's tracker configuration and label mapping. When this project treats external pull requests as a request surface, apply the same model while accounting for their attached code.
Prefix comments created during this workflow with:
> *This was generated by AI during triage.*
Use one category role:
bugenhancementUse one state role:
needs-triageneeds-infoready-for-agentready-for-humanwontfixThe configured tracker may map these roles to different label strings. Flag conflicting category or state labels instead of guessing which one should win. A maintainer may authorize an unusual transition.
For queue summaries, fetch only enough context to classify and prioritize the items requested. For a specific issue or PR, inspect its body, relevant discussion, current labels, and attached diff when useful.
Check code, tests, prior decisions, and .out-of-scope/ only to the depth needed
for a trustworthy recommendation. Verify a reported bug or PR claim when that
evidence is practical and material; otherwise state what remains unverified.
test cases passed, vs 8 / 17 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.