About perf-theory-gatherer
A skill that develops performance hypotheses for a specific scenario by reviewing relevant Git history and identifying involved code paths. It produces up to five evidence-backed hypotheses with confidence levels, without proposing optimizations.
Key features
- 01Reviews relevant Git history
- 02Identifies scenario-related code paths
- 03Produces up to five hypotheses
- 04Includes evidence and confidence
Use cases
- 01Investigate a scenario's performance behavior
- 02Form hypotheses before performance experiments
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ agent-sh/ agentsys --skill perf-theory-gathererAfter installing, type/perf-theory-gathererin Claude Code to confirm it loaded.
Details
From the project READMEperf-theory-gatherer
Generate performance hypotheses for a specific scenario.
Follow docs/perf-requirements.md as the canonical contract.
Required Steps
- Review recent git history (scope to relevant paths when possible).
- Identify code paths involved in the scenario (repo-intel or grep).
- 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.
Comments
Markdown supported