alt-text

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

Quality

62%

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/alt-text/SKILL.md

Quality

Content

57%

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

The body is well-structured with concrete good/bad alt-text examples and a clean one-level reference to a real rule.md, but it carries unnecessary motivational background and a redundant 'Explain' section, and lacks a concrete verification step for its batch review workflow. The Code Review section also drifts back into off-target performance language.

Suggestions

Remove the introductory statistics and screen-reader/WCAG explanations (concepts Claude already knows) and keep only the actionable Check/Fix guidance.

Merge or drop the redundant 'Explain' section, which restates the Quick Reference and Check content.

Add a concrete verification checkpoint (e.g., run an axe DevTools or Lighthouse accessibility audit, or grep the codebase for <img> elements missing alt) so the workflow has explicit validation and the Code Review section becomes actionable.

Dimension	Reasoning	Score
Conciseness	The Check and Fix sections are lean and useful, but the intro explains concepts Claude already knows ('Approximately 2.2 billion people worldwide have vision impairment. Screen readers read the alt attribute aloud') and the 'Explain' section restates WCAG 1.1.1 and decorative alt="" already covered in Quick Reference and Check.	2 / 3
Actionability	Check and Fix give concrete, copy-paste-ready good/bad examples (e.g., alt="Bar chart showing 40% increase in sales Q3 2024"), but the Code Review section is vague ('describe how to confirm the fix in DevTools') with no specific verification steps, leaving key details missing.	2 / 3
Workflow Clarity	The Check -> Fix -> Explain -> Code Review sequence is present, but for a batch codebase scan there is no explicit validation checkpoint (no axe/Lighthouse audit step or grep command); checkpoints are only implicit, so it caps at 2.	2 / 3
Progressive Disclosure	The body is a well-organized overview (Quick Reference, Check, Fix, Explain, Code Review) with a clearly signaled, one-level-deep reference to references/rule.md (a real file) for full implementation details and code examples, matching the score-3 anchor.	3 / 3
	Total	9 / 12 Passed

Description

67%

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 structurally complete with an explicit 'Use when...' trigger, but it is semantically misaligned with the skill: it frames an alt-text accessibility skill around image performance/CDN concerns it does not actually address. This over-claiming and the off-target trigger terms weaken specificity, trigger quality, and distinctiveness.

Suggestions

Rewrite the description around alt text: replace the image-performance framing ('CDN or build transforms', 'encoded size, rendered size, loading strategy, above-the-fold impact') with the skill's actual purpose of reviewing <img> alt attributes for accessibility.

Add natural trigger terms users would say for this skill — 'alt text', 'image accessibility', 'screen readers', 'WCAG 1.1.1' — instead of performance jargon.

Tighten the 'what' so it describes alt-text review only and does not over-claim checks (sizing, loading strategy) that the skill does not perform.

Dimension	Reasoning	Score
Specificity	It names concrete actions ('reviewing image assets, markup, and CDN or build transforms', 'Check encoded size, rendered size, loading strategy, and above-the-fold impact'), but these over-claim capabilities the alt-text skill does not perform, so they are concrete yet misaligned rather than a comprehensive fit.	2 / 3
Completeness	It explicitly answers both what ('reviewing image assets, markup, and CDN or build transforms related to Provide meaningful alt text for images') and when via a clear 'Use when...' trigger clause, matching the structure of the score-3 anchor.	3 / 3
Trigger Term Quality	'alt text' and 'image assets, markup' are natural, but the bulk of terms ('CDN or build transforms', 'encoded size', 'rendered size', 'loading strategy', 'above-the-fold impact') are image-performance jargon a user needing alt-text help would not say, and common a11y variations ('accessibility', 'screen reader', 'WCAG') are missing.	2 / 3
Distinctiveness Conflict Risk	It is image-domain specific and mentions 'alt text', but the dominant performance framing (CDN, sizing, loading, above-the-fold) overlaps strongly with other frontendchecklist image rules (sizing, lazy loading, responsive images), so it could trigger for the wrong skill.	2 / 3
	Total	9 / 12 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/alt-text/SKILL.md
Commit: 48405aa

Reviewed: about 8 hours 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.