Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →composio-community/perf-analyzer
Use when synthesizing perf findings into evidence-backed recommendations and decisions.
Passed 18 of 22 test cases with the skill, and 7 of 22 without it.
and 22 more in the full report
14 fixed4 passed either way1 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
Go microservice pprof trace shows runtime.mallocgc consuming 42% CPU during high throughput. Hypothesis 1: switching sync.Pool for buffer allocations reduced CPU usage to 14%. Hypothesis 2: enabling GOGC=200 increased memory footprint without improving CPU utilization. Summarize this investigation.
| Checked | Without skill | With skill |
|---|---|---|
| The output is structured as YAML containing summary, recommendations, abandoned, and next_steps. | Missed | Passed |
| The recommendations section includes using sync.Pool for buffer allocations. | Passed | Passed |
| The abandoned section includes setting GOGC=200. | Missed | Passed |
The instructions your model reads when the skill loads.
Synthesize performance investigation results into clear recommendations.
Follow docs/perf-requirements.md as the canonical contract.
summary: <2-3 sentences>
recommendations:
- <actionable recommendation 1>
- <actionable recommendation 2>
abandoned:
- <hypothesis or experiment that failed>
next_steps:
- <if user should continue or stop>
test cases passed, vs 7 / 22 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.