Web Performance Audit
CheckedHelps with web development, performance optimization, auditing as part of building frontend UIs and user experiences workflows.
Install on your platform
Showing Claude Code. One command installs this skill into any of the agents below.
- 1
Run this in your project
terminal$ npx skills add aj-geddes/useful-ai-prompts --skill web-performance-audit -a claude-code Uses the open-source
skillsCLI and needs Node.js. Add-gto install it for your user instead of this project.
What we know about this skill
Publisher
aj-geddes
Taken from the source listing. We haven't verified who controls this account.
Install target
Live repository
Not pinned. Installing fetches whatever the repository holds at the time you run the command.
Automated safety checks
This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No undeclared network calls: passed
Makes no network calls.
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned aj-geddes/useful-ai-prompts at 3f5182cfd7.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.
- Commit
- 3f5182cfd7
- Scanned
- 7 files, 390 lines
About this skill
web-performance-audit
What it does
This skill enables AI agents to analyze website loading speeds and identify specific bottlenecks affecting user experience. It provides actionable insights into performance metrics such as First Contentful Paint, Time to Interactive, and Largest Contentful Paint to help optimize frontend delivery.
When to use it
- Before launching a new marketing landing page to ensure fast load times on mobile networks.
- When Core Web Vitals scores drop below recommended thresholds in analytics dashboards.
- During the debugging phase of slow image or script rendering issues.
- To establish baseline performance metrics for regression testing after code deployments.
Key capabilities
- Analyzes critical path rendering and resource loading delays.
- Identifies render-blocking resources and large asset sizes.
- Evaluates server response times and network efficiency.
- Generates specific recommendations for reducing latency and improving throughput.
Example prompts
- "Audit the performance of my production homepage and list the top three reasons it's loading slowly."
- "Analyze this URL for Core Web Vitals compliance and suggest fixes for poor mobile scores."
- "Review the network waterfall for [domain] and identify any render-blocking JavaScript files."
Tips & gotchas
Ensure the target website is publicly accessible, as audit tools cannot analyze sites behind authentication walls without specific credentials. For accurate results, run the audit from a location geographically close to your primary user base to reflect real-world latency conditions.