mcpField
P
perf-analyzer

perf-analyzer

github.com/agent-shDevelopment1.0k87 installsUpdated today
Repository

About perf-analyzer

perf-analyzer synthesizes performance investigation evidence into a summary and recommendations for developers. It also identifies abandoned approaches and next steps, and requires evidence-backed reporting when data is insufficient.

Key features

  1. 01Summarizes performance findings
  2. 02Produces recommendations
  3. 03Lists abandoned approaches
  4. 04Suggests next steps
  5. 05Flags insufficient evidence

Use cases

  1. 01Reviewing profiling and experiment results
  2. 02Summarizing tested performance hypotheses

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/agent-sh/agentsys --skill perf-analyzer

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

Details

From the project README

perf-analyzer

Synthesize performance investigation results into clear recommendations.

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

Inputs

  • Baseline data
  • Experiment results
  • Profiling evidence
  • Hypotheses tested
  • Breaking point results

Output Format

summary: <2-3 sentences>
recommendations:
  - <actionable recommendation 1>
  - <actionable recommendation 2>
abandoned:
  - <hypothesis or experiment that failed>
next_steps:
  - <if user should continue or stop>

Constraints

  • Only cite evidence that exists in logs or code.
  • If data is insufficient, say so and request a re-run.

Comments

Markdown supported