Home › Rated skills › web-perf

web-perf

Name: SkillMOO rating: web-perf
Item: web-perf
Rating: 84
Author: SkillMOO

by cloudflare/skills · view source ↗

Autonomous CodingApache-2.02,047 tok/call

Clean — safe and lean

Safety grade

84/100 · gate: pass

Token cost

2,047

around median

Efficacy

—

Not yet measured

What it claims to do

Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, …

What we found · 1

Bloated: high token costmedium~2,047 tokens on every single call. Compress instructions and trim examples.

Conflicts with · 5

internal-comms	shadow	resourc, using
claude-api	overlap	mcp, cach
web-artifacts-builder	overlap	using, web
webapp-testing	overlap	web, using
agents-sdk	overlap	using, mcp

If you have both installed, they compete for the same triggers — the top cause of an agent picking the wrong skill.

Have you installed web-perf? Scan everything you run.

One command grades every skill in your Claude Code / Codex — safety, token bloat, and conflicts, 100% locally.

npx skillmoo scan

Browse all rated skills

Grade computed 2026-07-13 · rubric static-v1. Efficacy shown only when measured on a labeled model + task suite — never invented.

Show the badge

Add this independent grade to the skill's README — the badge links back to this rating and updates when we re-grade.

[![SkillMOO](https://skillmoo.com/badge/web-perf)](https://skillmoo.com/skill/web-perf/)

Does this rating match your experience with web-perf?

Anonymous & aggregate. We watch these as a trend and re-check flagged skills — a single click never moves a grade on its own.

Independent static analysis by SkillMOO — the Consumer Reports for agent skills. Safety, token, and conflict grades are computed, not opinions. Efficacy is only ever claimed when measured. We rate & link to the source; we do not rehost skill content.