critical-images

Use when reviewing image assets, markup, and CDN or build transforms related to Prioritize loading critical images. Check encoded size, rendered size, loading strategy, and above-the-fold impact together.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/critical-images/SKILL.md

Quality

Content

71%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 exceptionally lean and well-structured with clean progressive disclosure to a real reference file. Its weakness is actionability: concrete markup/code examples are deferred entirely to the reference rather than appearing inline for the common cases.

Suggestions

Add one minimal inline code snippet for the highest-value action (e.g., the fetchpriority='high' + preload head markup) so the body is actionable without requiring the reference.

Tighten the Code Review step with a brief DevTools verification checklist (Network 'Priority' column, Lighthouse LCP element) to make the validate checkpoint explicit.

Dimension	Reasoning	Score
Conciseness	The ~34-line body is lean and assumes Claude's competence; it states impact in one earned line and delegates detail to references without padding, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	The Fix step gives high-level direction ('Add fetchpriority=high... and use preload') but no executable markup or code inline—all concrete examples live in references/rule.md—fitting the 'high-level hints but missing the specific steps to execute' anchor.	2 / 5
Workflow Clarity	A clear Check -> Fix -> Explain -> Code Review sequence with a DevTools verification cue is present for a single-purpose review skill; minor checkpoint gaps versus the explicit validate-fix-retry loop keep it just below 5.	4 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled, one-level-deep pointer to the real references/rule.md file, matching the 'clear overview with well-signaled one-level-deep references' anchor.	5 / 5
	Total	16 / 20 Passed

Description

71%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 clearly pairs an explicit 'Use when' trigger with a concrete review scope, giving strong completeness and good distinctiveness. Specificity and trigger-term quality are middling because the action list reads as review dimensions rather than discrete actions and omits natural phrases like 'hero images' or 'LCP'.

Suggestions

Reframe the review dimensions as discrete actions (e.g., 'Audit fetchpriority on LCP images, verify preload hints in the document head, remove loading=lazy from above-the-fold images') to lift specificity.

Add natural user-facing trigger terms such as 'hero images', 'LCP image', and 'above the fold' so the skill surfaces for the phrasings users actually say.

Dimension	Reasoning	Score
Specificity	Names the domain ('image assets, markup, and CDN or build transforms') and several review facets ('encoded size, rendered size, loading strategy, and above-the-fold impact'), but these are review dimensions rather than a comprehensive list of distinct skill actions, matching the 3-anchor of domain + 1-2 concrete actions.	3 / 5
Completeness	An explicit 'Use when reviewing image assets...' clause gives the trigger, and the concrete review scope ('Check encoded size, rendered size, loading strategy, and above-the-fold impact together') answers what, satisfying the explicit what-and-when anchor.	5 / 5
Trigger Term Quality	Relevant keywords like 'image assets', 'markup', and 'CDN or build transforms' appear, but common natural phrasings users would say ('hero images', 'LCP image', 'above the fold') and file extensions are absent, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Scoped specifically to critical-image loading priority with distinct triggers, but it overlaps with broader image-optimization skills, matching the 'mostly distinct; minor overlap with closely related skills' anchor.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: thedaviddias/Front-End-Checklist
Path: skills/critical-images/SKILL.md
Commit: 30756a7

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

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.