Skip to content
MMake Prompt AI Get Started
Home > ChatGPT Guide > /performance
Custom prompt shortcut / Software Development

/performance — ChatGPT Prompt Guide

Explore the /performance custom ChatGPT prompt shortcut with a practical template, examples, and review steps. Learn how to refine outputs for your workflow.

What does /performance do?

Purpose: Diagnose a slow article landing page.

This is a custom prompt convention, not a built-in or official ChatGPT slash command. Entering the slash text alone does not guarantee that ChatGPT will invoke a special tool. Use the complete structured prompt below or configure your own app to interpret this shortcut.

Key decision for this workflow

Use /performance when the task is diagnose a slow article landing page; specify the evidence needed to accept the result.

Copy-ready task brief

/performance Objective: Diagnose a slow article landing page Inputs: Supply waterfall trace, device profile, Core Web Vitals and asset sizes. Deliverable: Rank image, font, script and server bottlenecks with measurable fixes.

Reusable prompt template

/performance Objective: Diagnose a slow article landing page Available materials: Supply waterfall trace, device profile, Core Web Vitals and asset sizes. Required output: Rank image, font, script and server bottlenecks with measurable fixes. Acceptance test: Compare before/after LCP, CLS and INP under the same test conditions. Boundary: Lab speed gains do not guarantee identical real-user results. Return the requested deliverable first, then a brief verification checklist and any unresolved questions.

How to use this shortcut

  1. Collect the source inputs: Supply waterfall trace, device profile, Core Web Vitals and asset sizes.
  2. Run /performance with the copy-ready task brief above.
  3. Request the concrete output: Rank image, font, script and server bottlenecks with measurable fixes.
  4. Check the result: Compare before/after LCP, CLS and INP under the same test conditions.

Quality checks and limitations

Acceptance criteria: Compare before/after LCP, CLS and INP under the same test conditions. Limitation: Lab speed gains do not guarantee identical real-user results.

Related tools and learning

Continue with the 35 prompt generators, the technical AI Guides, and the Image Guides for deeper examples.

/code/debug/refactor/codeaudit/indexingaudit/crawlbudget

Worked example and expected output

Input materials: Supply waterfall trace, device profile, Core Web Vitals and asset sizes.

Requested result: Rank image, font, script and server bottlenecks with measurable fixes.

Acceptance test: Compare before/after LCP, CLS and INP under the same test conditions.

Worked example: Investigate a slow mobile landing page

Illustrative deliverable: List likely LCP, CLS and INP causes; propose image sizing, font loading and JavaScript changes in a prioritized test plan.

Review and limitations

Measure field and lab data before claiming speed gains.

Worked workflow: Diagnose a slow article landing page

Scenario: Diagnose a slow article landing page

Inputs to provide: Supply waterfall trace, device profile, Core Web Vitals and asset sizes.

Requested deliverable: Rank image, font, script and server bottlenecks with measurable fixes.

How to verify the result: Compare before/after LCP, CLS and INP under the same test conditions.

Boundary to respect: Lab speed gains do not guarantee identical real-user results.

Frequently asked questions

Is /performance an official ChatGPT command? No. It is a reusable custom shorthand from this catalog. Does it work without a plugin? You can copy the full prompt into an assistant; automatic slash-command routing requires application logic. Can the output be trusted without review? No. Review accuracy, safety, and suitability before use.