Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agent-sh/perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.
Passed 18 of 23 test cases with the skill, and 4 of 23 without it.
and 32 more in the full report
18 fixed1 passed either way2 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 18 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our monorepo contains over 200 services across Rust, Python, and Go. We need to identify candidate code paths for a database query bottleneck in `user-service`. Ensure your path map remains focused and does not flood the report with dozens of files.
| Checked | Without skill | With skill |
|---|---|---|
| The number of files listed under `paths:` does not exceed 15. | Missed | Passed |
| The response outputs candidate files using the `keywords:` and `paths:` YAML structure. | Missed | Passed |
The instructions your model reads when the skill loads.
Identify likely implementation paths for a performance scenario.
Follow docs/perf-requirements.md as the canonical contract.
keywords: <comma-separated list>
paths:
- file: <path>
symbols: [<symbol1>, <symbol2>]
evidence: <short reason>
test cases passed, vs 4 / 23 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.