perf-theory-tester
SkillAI & modelsperf-theory-tester is a skill that lets your AI run controlled performance experiments to validate hypotheses. Once added, your AI can test one hypothesis at a time, so answers about performance come from evidence instead of guesswork.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding it, describe the performance hypothesis you want to check and ask your AI to run a controlled experiment to test it.
Then ask your AI: use the perf-theory-tester skill
What your AI can do with it
- Run controlled performance experiments
- Test one hypothesis at a time
- Validate performance hypotheses with results from controlled runs
- Rule out hypotheses that the experiments do not support
What this skill tells your AI
The instructions your AI receives, as published by composio-community/awesome-claude-plugins in perf/skills/theory-tester/SKILL.md and read by ahel’s review.
Test hypotheses using controlled experiments.
Follow docs/perf-requirements.md as the canonical contract.
Required Steps
- Confirm baseline is clean.
- Apply a single change tied to the hypothesis.
- Run 2+ validation passes.
- Revert to baseline before the next experiment.
Output Format
hypothesis: <id>
change: <summary>
delta: <metrics>
verdict: accept|reject|inconclusive
evidence:
- command: <benchmark command>
- files: <changed files>
Constraints
- One change per experiment.
- No parallel benchmarks.
- Record evidence for each run.
Signals
- GitHub stars
- 2k
- Forks
- 606
- Last commit
- Jul 2026
Advanced
- Catalog kind
- skill
- Gateway key
perf-theory-tester- Source
- github.com/composio-community/awesome-claude-plugins