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.

99

1.15x
Quality

100%

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

100%

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

The content is a tightly organized, actionable audit playbook: concrete tool calls, a sequenced five-phase workflow with a progress checklist and an upfront tool-availability validation gate, and clean sectioning with no nested references or conceptual padding. It is a strong, self-contained skill body with no significant gaps.

DimensionReasoningScore

Conciseness

The body is dense reference material with no padding or explanations of concepts Claude already knows — tables for retrieval sources, tool calls, insight names, thresholds, and framework configs each earn their place, matching the level-3 'lean and efficient' anchor rather than the level-2 'could be tightened'.

3 / 3

Actionability

Real executable tool calls with parameters appear throughout (navigate_page, performance_start_trace, list_network_requests, get_network_request, take_snapshot) plus a copy-paste MCP config JSON and threshold tables, meeting the level-3 'fully executable, copy-paste ready' anchor rather than level-2 pseudocode.

3 / 3

Workflow Clarity

A clear five-phase sequence is backed by a copyable progress checklist, per-phase troubleshooting, and an explicit validation checkpoint ('Verify MCP Tools Available… STOP if unavailable'); since the audit is read-only with no destructive/batch writes, the lighter validation bar is satisfied, matching the level-3 anchor with checkpoints.

3 / 3

Progressive Disclosure

The skill is a single self-contained SKILL.md with no bundle files and no nested/deep references, organized into well-signaled sections (Retrieval Sources, Quick Reference, Workflow phases, Output Format) that aid navigation; per the rubric's simple-skills note, well-organized single-file structure scores 3 with no deep reference nesting.

3 / 3

Total

12

/

12

Passed

Description

100%

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 specific, complete, and well-triggered: it enumerates concrete capabilities and named metrics, gives an explicit 'Use when…' clause with natural user terms, and occupies a distinct, low-conflict niche. It is a strong, concise description with no notable weaknesses.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across one domain: 'Measures Core Web Vitals (FCP, LCP, TBT, CLS, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps' — comprehensive rather than naming just some actions, so it clears the level-3 anchor and is not the level-2 'names domain and some actions'.

3 / 3

Completeness

Explicitly answers both what ('Analyzes web performance… Measures… identifies…') and when ('Use when asked to audit, profile, debug, or optimize…') with an explicit 'Use when' trigger clause, matching the level-3 anchor and exceeding level-2 where 'when' is only implied.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered: 'audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed' — verbs and nouns users actually say; the technical terms (Core Web Vitals, Lighthouse) are themselves common user vocabulary, keeping it above the level-2 'missing common variations' anchor.

3 / 3

Distinctiveness Conflict Risk

The niche is sharply scoped to web-performance auditing via Chrome DevTools MCP with Lighthouse/Core Web Vitals triggers, making it unlikely to fire for unrelated skills and matching the level-3 'clear niche with distinct triggers' anchor.

3 / 3

Total

12

/

12

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.