CtrlK
BlogDocsLog inGet started
Tessl Logo

web-performance-optimization

Optimizes web application performance through code splitting, lazy loading, caching strategies, and Core Web Vitals monitoring. Use when improving page load times, implementing service workers, or reducing bundle sizes.

89

1.15x
Quality

86%

Does it follow best practices?

Impact

96%

1.15x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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 executable examples and well-structured progressive disclosure to real reference files. It is held back by redundancy (overlapping lists, repeated notes) and the absence of an explicit measure-optimize-verify workflow with checkpoints.

Suggestions

Collapse the 'Best Practices' and 'Optimization Checklist' sections into one to remove overlap, and state the INP-replaced-FID note once.

Trim the sendToAnalytics placeholder example implementation to a one-line signature note to save tokens.

Add a short measure→optimize→re-measure workflow with an explicit validation checkpoint (e.g., re-run Lighthouse/web-vitals and confirm the target metric improved before stopping).

DimensionReasoningScore

Conciseness

Mostly efficient code examples, but redundancy pads tokens: the 'Best Practices' and 'Optimization Checklist' sections overlap heavily, the INP-replaced-FID note is stated twice, and the sendToAnalytics placeholder includes a full example implementation that is filler. Not score 3 because clear tightening is possible; not score 1 because the bulk is lean, executable code.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code across React lazy loading, webpack splitChunks, the <picture> element, a service worker, PerformanceObserver monitoring, and nginx gzip, plus a concrete metrics table. Matches the score-3 anchor.

3 / 3

Workflow Clarity

Content is organized by technique and includes a checklist, but there is no sequenced measure→optimize→re-measure workflow with validation checkpoints, which is the natural feedback loop for this domain. Capped at 2 due to missing verification checkpoints rather than a clearly sequenced validated process.

2 / 3

Progressive Disclosure

SKILL.md is a clear overview with well-signaled, one-level-deep references to real bundle files (compression-monitoring.md, typescript-advanced.md), each annotated with its contents. Verified the referenced files exist in ./references/.

3 / 3

Total

10

/

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 concise, third-person, and clearly states both capabilities and explicit use-when triggers. It names concrete actions and natural trigger terms with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — 'code splitting, lazy loading, caching strategies, and Core Web Vitals monitoring' — matching the score-3 anchor rather than the partial coverage of score 2.

3 / 3

Completeness

Explicitly answers both what ('Optimizes web application performance through...') and when ('Use when improving page load times...') with an explicit 'Use when' clause, matching the score-3 anchor.

3 / 3

Trigger Term Quality

Natural user-facing triggers — 'improving page load times, implementing service workers, or reducing bundle sizes' — are terms developers actually say; coverage is relevant and natural, though a few common variations (e.g. 'slow site', 'make it faster') are absent, keeping it at the strong end rather than exceptional.

3 / 3

Distinctiveness Conflict Risk

Web performance optimization is a clear niche with distinct triggers (page load times, service workers, bundle sizes) unlikely to collide with other skills; third-person voice is used correctly.

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
secondsky/claude-skills
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.