# Perf Theory Gatherer

> Use when generating performance hypotheses backed by git history and code evidence.

- Skill: `avifenesh/perf-theory-gatherer-2` (Agent Skill)
- Install (CLI): `npx get-skill add avifenesh/perf-theory-gatherer-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/avifenesh/perf-theory-gatherer-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: avifenesh (https://skillmd.com/u/avifenesh)
- Updated: 2026-09-21
- Page: https://skillmd.com/skills/avifenesh/perf-theory-gatherer-2

---


# perf-theory-gatherer

Generate performance hypotheses for a specific scenario.

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

## Required Steps

1. Review recent git history (scope to relevant paths when possible).
2. Identify code paths involved in the scenario (repo-intel or grep).
3. Produce up to 5 hypotheses with evidence + confidence.

## Output Format

```
hypotheses:
  - id: H1
    hypothesis: <short description>
    evidence: <file/path or git change>
    confidence: low|medium|high
  - id: H2
    ...
```

## Constraints

- MUST check git history before hypothesizing.
- No optimization suggestions; only hypotheses.
- Keep to 5 hypotheses maximum.

