CtrlK
BlogDocsLog inGet started
Tessl Logo

web-performance-optimization

Optimize website and web application performance including loading speed, Core Web Vitals, bundle size, caching strategies, and runtime performance

48

Quality

52%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/web-performance-optimization/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

38%Scale 1-5

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

This skill is a comprehensive but severely bloated reference document that reads more like a web performance tutorial than a concise skill for Claude. While it contains genuinely useful, executable code examples (image optimization scripts, code splitting patterns, HTML picture elements), the massive volume of content—including explanations of well-known concepts, extensive do/don't lists, tool catalogs, and resource links—wastes significant token budget. The content would benefit enormously from being split into a lean overview with references to detailed sub-files.

Suggestions

Reduce the main file to ~80 lines: a brief workflow overview, one concise example, and references to separate files for image optimization, bundle optimization, and CWV details.

Remove all explanatory content Claude already knows: what Core Web Vitals are, what CDNs do, what lazy loading means, the 'When to Use This Skill' section, and the do/don't best practices lists.

Split the three large examples into separate bundle files (e.g., EXAMPLES_CWV.md, EXAMPLES_BUNDLE.md, EXAMPLES_IMAGES.md) and reference them from the main skill.

Add explicit validation commands to the workflow (e.g., 'Run `npx lighthouse URL --output=json > before.json`, implement changes, then run again and diff the scores') instead of vague 'Re-run Lighthouse audits' instructions.

DimensionReasoningScore

Conciseness

Extremely verbose at ~400+ lines. Extensively explains concepts Claude already knows (what Core Web Vitals are, what lazy loading is, what a CDN does). Lists of tools, best practices do/don't lists, and 'When to Use This Skill' sections are all padding. The 'Additional Resources' and 'Related Skills' sections add more bloat. Nearly every section over-explains rather than providing only novel, actionable information.

1 / 5

Actionability

The examples contain concrete, executable code snippets (sharp image optimization script, webpack config, HTML picture elements, Next.js dynamic imports). Code is mostly copy-paste ready. However, some guidance remains high-level (e.g., 'Use CDN for faster delivery', 'Optimize database queries') without concrete implementation details.

4 / 5

Workflow Clarity

The 5-step workflow (Measure → Identify → Prioritize → Implement → Verify) is listed but each step is vague bullet points rather than concrete commands. The verification step says 'Re-run Lighthouse audits' and 'Compare before/after metrics' without specifying how to capture and compare baselines. The examples show before/after results but don't demonstrate an actual validation feedback loop with error recovery.

3 / 5

Progressive Disclosure

No bundle files exist, yet the content is a monolithic wall of 400+ lines with three massive inline examples, full checklists, tool lists, and resource links all in one file. The image optimization script, bundle analysis examples, and detailed CWV examples should be in separate referenced files. References to other skills exist but the content itself desperately needs splitting.

2 / 5

Total

10

/

20

Passed

Description

66%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 does a good job listing specific performance optimization areas and includes relevant technical terms users would naturally use. Its main weakness is the absence of an explicit 'Use when...' clause, which limits Claude's ability to know precisely when to select this skill. Adding trigger guidance and a few more synonyms would elevate this description significantly.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about page speed, slow loading, performance audits, or optimizing web assets.'

Include common synonyms and related terms like 'page speed', 'LCP', 'CLS', 'code splitting', 'lazy loading', 'minification' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Lists several specific areas of optimization: loading speed, Core Web Vitals, bundle size, caching strategies, and runtime performance. These are concrete domains, though the actions themselves are implied ('optimize') rather than explicitly varied (e.g., 'analyze', 'reduce', 'configure').

4 / 5

Completeness

Clearly answers 'what' (optimize web performance across several dimensions) but has no explicit 'when' clause. There is no 'Use when...' guidance, which per the rubric caps this dimension at 3.

3 / 5

Trigger Term Quality

Includes strong natural keywords like 'Core Web Vitals', 'bundle size', 'caching strategies', 'loading speed', and 'runtime performance' that users would naturally mention. Missing some common synonyms like 'page speed', 'LCP', 'CLS', 'FID', 'lazy loading', 'code splitting', or 'minification'.

4 / 5

Distinctiveness Conflict Risk

Fairly distinct with its focus on web performance optimization specifically. Could have minor overlap with general web development skills or frontend skills, but the specific mention of Core Web Vitals, bundle size, and caching strategies narrows the scope well.

4 / 5

Total

15

/

20

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (650 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

9

/

11

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.