Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →composio-community/perf-theory-tester
Use when running controlled perf experiments to validate hypotheses.
Passed 19 of 21 test cases with the skill, and 7 of 21 without it.
and 14 more in the full report
13 fixed7 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our test showed that switching from SHA-256 to Argon2id increased hashing latency by 400% without meeting our sub-100ms budget. Output the performance experiment outcome in the required structured code format.
| Checked | Without skill | With skill |
|---|---|---|
| The output uses the formatted block with keys hypothesis, change, delta, verdict, and evidence. | Missed | Passed |
| The verdict field value is reject. | Missed | Passed |
The instructions your model reads when the skill loads.
Test hypotheses using controlled experiments.
Follow docs/perf-requirements.md as the canonical contract.
hypothesis: <id>
change: <summary>
delta: <metrics>
verdict: accept|reject|inconclusive
evidence:
- command: <benchmark command>
- files: <changed files>
test cases passed, vs 7 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.