mcpField
P
perf-theory-gatherer

perf-theory-gatherer

github.com/composio-communityDevelopment2.0k1.7k installsUpdated 13w ago
Repository

About perf-theory-gatherer

perf-theory-gatherer is a development skill that generates evidence-backed performance hypotheses for a specific scenario. It checks relevant git history and code paths first, and reports no more than five hypotheses with confidence levels.

Key features

  1. 01Reviews relevant git history first
  2. 02Identifies code paths for a scenario
  3. 03Produces up to five hypotheses
  4. 04Includes evidence and confidence levels
  5. 05Excludes optimization suggestions

Use cases

  1. 01Investigating possible causes of a slowdown
  2. 02Preparing evidence-backed performance hypotheses

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/composio-community/awesome-claude-plugins --skill perf-theory-gatherer

After installing, type/perf-theory-gathererin Claude Code to confirm it loaded.

Details

From the project README

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-map 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.

Comments

Markdown supported