CtrlK
BlogDocsLog inGet started
Tessl Logo

web-perf

Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.

93

1.15x
Quality

91%

Does it follow best practices?

Impact

95%

1.15x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is web-perf in cloudflare/skills

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete MCP tool calls, thresholds, and a clear phased workflow, and it opens with a useful retrieval-bias reminder. It loses points mainly for some inlined reference material (framework detection tables) that Claude largely already knows and for lacking an explicit post-trace validation feedback loop.

Suggestions

Add an explicit validate-fix-retry loop after Phase 1/2 (e.g., 'If LCPBreakdown insight returns empty, verify insightSetId and retry with a discovered insight name') to strengthen workflow_clarity.

Move the framework/bundler config-file detection table and Phase 5 codebase checks into a references/ file to improve progressive_disclosure and trim tokens Claude already knows.

Tighten the 'Be assertive' / 'Verify before recommending' guideline bullets, which partly restate each other and pad the Key Guidelines section.

DimensionReasoningScore

Conciseness

Mostly lean with tables and concrete tool calls rather than explanations of concepts, but sections like the framework/config-file table and Phase 5 codebase analysis add reference material Claude largely already knows and could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready tool calls (navigate_page, performance_start_trace, performance_analyze_insight) with parameters and a Quick Reference table, plus specific thresholds and concrete fix examples like 'compress hero.png (450KB) to WebP'.

5 / 5

Workflow Clarity

Clear five-phase sequence with a progress checklist and troubleshooting notes, plus an upfront MCP-availability validation gate; however there is no explicit validate-fix-retry feedback loop after the trace or insight steps.

4 / 5

Progressive Disclosure

Well-organized sections (Quick Reference, Workflow, Output Format) keep the body navigable, and retrieval sources are cleanly tabulated rather than inlined; minor gaps are the inlined framework/config tables that could live in a reference file.

4 / 5

Total

17

/

20

Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is excellent: it pairs concrete capabilities with explicit 'Use when...' trigger guidance covering natural user phrasing. It uses proper third-person voice and adds a retrieval-bias note that is concise rather than padded.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps') with comprehensive coverage across metrics and failure modes.

5 / 5

Completeness

Explicitly answers both what it does (measures vitals, identifies issues) and when to use it ('Use when asked to audit, profile, debug, or optimize page load performance...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural phrases users would say ('audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed') plus the technical metric names, giving comprehensive keyword coverage with synonyms.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (web performance via Chrome DevTools MCP) with distinct triggers around Lighthouse and Core Web Vitals; minimal conflict risk with unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.