web-performance-audit
Skill4 starsChanged 8 months agoMITView on GitHub
Web performance and Lighthouse audits. Use when checking storefront performance, Core Web Vitals, accessibility, SEO, or best practices. Triggers on: performance audit, Lighthouse, PageSpeed, Core Web Vitals, LCP, CLS, INP, accessibility check.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- Adonis0123/adonis-skillstheir own version, first seen Nov 7, 2026
- KMaruthi2002/universal-llm-skillstheir own version, first seen Oct 25, 2026
- davidanthonyn/claude-skillstheir own version, first seen Oct 20, 2026
- WST2002/claude-code-skillstheir own version, first seen Oct 17, 2026
- ai-moto/web-craft-skillstheir own version, first seen Aug 23, 2026
- omonuj/claude-skillstheir own version, first seen Jul 23, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- warpdotdev/oz-skills★ 825same name
- Adonis0123/adonis-skills★ 4same name
- WST2002/claude-code-skills★ 4same name
- KMaruthi2002/universal-llm-skills★ 1same name
- ai-moto/web-craft-skills★ 0same name
- davidanthonyn/claude-skills★ 0same name
- omonuj/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- wake-checkout-flowSkill
- wake-hotsite-bannersSkill
- wake-product-variantsSkill
- wake-scribanSkill
- wake-storefront-apiSkill
- wake-storefront-reference-patternsSkill
- wake-templateSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Run Lighthouse audits and performance traces on web pages using Chrome DevTools MCP.
- Very specific: line 23
Chrome DevTools MCP: must be installed (bundled via plugin .mcp.json)
- Distinctive: line 28
When Chrome DevTools MCP is unavailable, inform the user to install it and ensure Chrome is installed.
- Very specific: line 34
Use navigate_page with type: "url" and the target URL, or new_page to open in a new tab.
- Very specific: line 46
Lighthouse: Call lighthouse_audit with mode: "navigation" to reload and audit, or mode: "snapshot" to audit current state.
- Very specific: line 47
Performance: Call performance_start_trace with reload: true, autoStop: true.
- Very specific: line 75
No page selected: Use list_pages then select_page before running audits.
- Very specific: line 76
Trace not started: Call performance_start_trace before performance_stop_trace or performance_analyze_insight.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Web Performance Audit
Forbidden: api.fbits.net (and any *.fbits.net). Canonical source: https://wakecommerce.readme.io/docs/schema (for Wake API references in scope).
Run Lighthouse audits and performance traces on web pages using Chrome DevTools MCP. Covers accessibility, SEO, best practices, and Core Web Vitals (LCP, INP, CLS).
When to Use
- Auditing storefront or web app performance
- Checking Core Web Vitals (LCP, INP, CLS)
- Running Lighthouse accessibility, SEO, or best-practices audits
- Debugging slow page loads or layout shifts
- Comparing mobile vs desktop performance
Prerequisites
- Chrome DevTools MCP must be installed (bundled via plugin
.mcp.json) - Node.js v20.19+
- Chrome (stable or newer)
- npm (for
npx)
When Chrome DevTools MCP is unavailable, inform the user to install it and ensure Chrome is installed.
Workflow
1. Navigate to the URL
Use navigate_page with type: "url" and the target URL, or new_page to open in a new tab.
2. Choose Audit Type
| Goal | Tool | Notes |
| Accessibility, SEO, best practices | lighthouse_audit | Excludes performance; use device: "mobile" or "desktop" |
| Performance, Core Web Vitals | performance_start_trace | Set reload: true for fresh load; autoStop: true recommended |
| Detailed performance insight | performance_analyze_insight | Use after trace; requires insightSetId and insightName from trace results |
3. Run the Audit
- Lighthouse: Call
lighthouse_auditwithmode: "navigation"to reload and audit, ormode: "snapshot"to audit current state. - Performance: Call
performance_start_tracewithreload: true,autoStop: true. Navigate to the URL first if needed.
4. Summarize Results
Present scores, metrics, and actionable recommendations. For performance traces, highlight Core Web Vitals (LCP, INP, CLS) and any insight sets.
Tool Reference (Chrome DevTools MCP)
| Category | Tool | Purpose |
| Performance | performance_start_trace | Start trace; Core Web Vitals, LCP, INP, CLS |
| Performance | performance_stop_trace | Stop active trace |
| Performance | performance_analyze_insight | Deep dive on specific insight from trace |
| Performance | take_memory_snapshot | Capture heap for memory leak debugging |
| Debugging | lighthouse_audit | Accessibility, SEO, best practices (excludes performance) |
| Navigation | navigate_page | Go to URL, back, forward, reload |
| Navigation | new_page | Open URL in new tab |
| Debugging | take_snapshot | Text snapshot of page (a11y tree) |
| Debugging | take_screenshot | Screenshot of page or element |
| Network | list_network_requests | List requests since last navigation |
| Network | get_network_request | Get request/response details |
| Emulation | emulate | Throttle network, CPU, viewport, device |
| Emulation | resize_page | Resize viewport |
Error Handling
- MCP unavailable: Tell the user Chrome DevTools MCP is required; link to Chrome DevTools MCP.
- Chrome not found: User must install Chrome and ensure it is on PATH.
- No page selected: Use
list_pagesthenselect_pagebefore running audits. - Trace not started: Call
performance_start_tracebeforeperformance_stop_traceorperformance_analyze_insight.
References
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.