web-quality-audit

Comprehensive web quality audit covering performance, accessibility, SEO, and best practices. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".

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 ./src/resources/skills/web-quality-audit/SKILL.md

Quality

Content

42%

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

The content is well-structured and practical but over-relies on reference-style guidance Claude already knows and lacks executable detail for most checks. Progressive disclosure is the weakest point: the inline body is monolithic and its reference links are broken, with the actual bundled script unused.

Suggestions

Fix or remove the broken References links (../core-web-vitals, ../accessibility, ../best-practices) and reference the real bundled scripts/analyze.sh from the body so the tool is discoverable.

Add a validation checkpoint to the 'How it works' workflow (e.g. confirm each finding maps to a real file/line and re-run analyze.sh after fixes) to satisfy the batch-operation feedback-loop expectation.

Trim well-known threshold restatements (WCAG contrast ratios, Core Web Vitals numeric targets) into a concise reference or move them into a separate reference file to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is dense and well-organized rather than padded with conceptual filler, but much of it restates well-known thresholds (WCAG ratios, Core Web Vitals targets) Claude already knows, so it could be tightened.	2 / 3
Actionability	It supplies a concrete output template, a severity table, and a bundled analyze.sh script, but most category guidance is advisory ('set explicit dimensions', 'use font-display: swap') rather than executable code or commands.	2 / 3
Workflow Clarity	'How it works' lists four steps and an output format, but a batch audit lacks explicit validation/feedback checkpoints (e.g. verify findings before reporting), which the rubric caps at 2.	2 / 3
Progressive Disclosure	The body is a monolithic inline wall of text and its References point to sibling skills (../core-web-vitals/SKILL.md, ../accessibility/SKILL.md, ../best-practices/SKILL.md) that do not exist in the bundle, while the one real bundle file (scripts/analyze.sh) is never referenced from the body.	1 / 3
	Total	7 / 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, specific, and clearly answers both what the skill does and when to use it with natural trigger phrases. It is third person and avoids vague fluff, fully meeting the top anchors.

Dimension	Reasoning	Score
Specificity	Names the concrete domain (performance, accessibility, SEO, best practices) and explicit actions ('audit', 'review', 'check', 'optimize') in third person, matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly states what the skill does (comprehensive audit across four categories) and includes an explicit 'Use when...' clause with concrete triggers, answering both what and when.	3 / 3
Trigger Term Quality	Provides several natural phrasings users would actually say ('audit my site', 'run lighthouse audit', 'check page quality', 'optimize my website'), giving good coverage.	3 / 3
Distinctiveness Conflict Risk	Targets a distinct Lighthouse-based web-quality niche with specific triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: gsd-build/gsd-2
Path: src/resources/skills/web-quality-audit/SKILL.md
Commit: 33c00aa

Reviewed: about 13 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.