Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agent-sh/perf-theory-gatherer
Use when generating performance hypotheses backed by git history and code evidence.
Passed 7 of 16 test cases with the skill, and 2 of 16 without it.
and 10 more in the full report
9 fixed1 passed either way10 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
Queue consumption delay in `src/queue/consumer.py` doubled yesterday. Review git commit history and code paths, generating structured YAML hypotheses (id, hypothesis, evidence, confidence) along with diff patch snippets to resolve each issue.
| Checked | Without skill | With skill |
|---|---|---|
| The output contains no diff patch snippets or optimization suggestions. | Missed | Passed |
| The confidence values are formatted as lowercase string values. | Missed | Passed |
The instructions your model reads when the skill loads.
Generate performance hypotheses for a specific scenario.
Follow docs/perf-requirements.md as the canonical contract.
hypotheses:
- id: H1
hypothesis: <short description>
evidence: <file/path or git change>
confidence: low|medium|high
- id: H2
...
test cases passed, vs 2 / 16 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.