Performance Benchmark Baseline skill for Claude and Codex

Performance Benchmark Baseline as an AI skill. It asks for Application URL or local command, Pages or endpoints to test, Device and network profile and 3…

Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.

Download the skill (.zip) · View SKILL.md

When it is used

Use when a developer wants a repeatable measurement of page speed and server load before making optimisations, so later changes can be compared. Do not use for fixing performance problems or one-off speed checks with no recorded method. Related topics: coding, technical.

What it will ask you for

• Application URL or local command (free text, e.g. "Where it runs")
• Pages or endpoints to test (longer free text)
• Device and network profile (choose one: Desktop fast, Mobile mid-range 4G, Mobile slow 3G)
• Tooling (choose one: Lighthouse, WebPageTest, k6, Playwright traces)
• Traffic expected (free text, e.g. "Concurrent users at peak")
• Targets if any (free text, e.g. "LCP under 2.5 seconds")

How it works

1. Fix the method first: tool version, device and network profile, cache state, region, and run count.
2. Run each page at least five times and record median and spread for the Core Web Vitals, Time to First Byte, and transfer size.
3. Load test backend endpoints at expected concurrency and record throughput, p50, p95, p99, and error rate.
4. Compare results against the targets and published thresholds and write the numbers to beat.
5. List the top three suspected bottlenecks with the evidence for each.

What you get

A results table per page and endpoint, a numbers-to-beat list, three suspected bottlenecks, and a method section precise enough to rerun.

What it watches out for

• Reporting a single run, so noise looks like a regression later.
• Testing with a warm cache and a fast desktop profile, flattering the numbers.
• Leaving out the tool version, which makes future comparisons invalid.

How to install

Claude.ai and the Claude desktop app

1. Download the skill .zip.
2. Open Settings, then Capabilities, and find Skills.
3. Choose Upload skill and select the .zip.
4. Ask Claude for help with the task. It loads the skill when your request matches.

Claude Code

1. Download the skill .zip.
2. Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
3. Start a new session. Claude Code loads the skill when your request matches.

Codex

1. Download the skill .zip.
2. Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
3. Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.

Cursor

1. Download the Cursor rule (.mdc).
2. Save it in .cursor/rules/ inside your project.
3. Cursor's agent applies the rule when your request matches its description.

AGENTS.md (Codex, Cursor, and other coding agents)

1. Copy the AGENTS.md section.
2. Paste it into AGENTS.md at the root of your repository, creating the file if needed.
3. Coding agents that read AGENTS.md follow it when your request fits.