Skip to content
Back to skills

Theory Tester

ASecurity

Use when running controlled perf experiments to validate hypotheses.

  • 1,917 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added August 31, 2026
ai-agents

Security analysis

A100/100

Scanned August 31, 2026

npx -y skills add composio-community/awesome-claude-plugins --skill theory-tester --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Theory Tester?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Theory Tester
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/composio-community-theory-tester/badge)](https://www.skillsdirectory.com/skills/composio-community-theory-tester)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: perf-theory-tester
description: "Use when running controlled perf experiments to validate hypotheses."
version: 1.0.0
---

# perf-theory-tester

Test hypotheses using controlled experiments.

Follow `docs/perf-requirements.md` as the canonical contract.

## Required Steps

1. Confirm baseline is clean.
2. Apply a single change tied to the hypothesis.
3. Run 2+ validation passes.
4. 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.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.