web-quality-audit

Run an evidence-led web quality audit covering performance, accessibility, SEO, best practices, and agentic browsing. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website".

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/web-quality-audit/SKILL.md

Quality

Content

73%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.

A well-structured audit skill with a clear sequenced workflow, concrete tool routing, and explicit verification. Its main weakness is conciseness: much of the categories section restates standard web-quality knowledge Claude already has.

Suggestions

Trim the Audit categories section to skill-specific nuances and thresholds, moving generic WCAG/SEO/performance primer content (e.g., 'Set lang attribute on <html>', 'Valid robots.txt') to a reference file or removing it.

Tighten generic fix bullets like 'Optimize images, fonts, and server response time' into concrete, executable steps or link to the relevant sibling-skill reference.

Consider splitting the per-category checklists into references/ files (e.g., ACCESSIBILITY.md, SEO.md) so SKILL.md stays a lean overview pointing one level deep, matching the existing References pattern.

Dimension	Reasoning	Score
Conciseness	Mostly organized, but roughly 90 lines of the Audit categories section re-state well-known WCAG, Core Web Vitals, and SEO practices Claude already knows; skill-specific nuances (Lighthouse 13+ insights, agentic-browsing caveats) earn some tokens but the bulk could be tightened.	3 / 5
Actionability	Provides concrete tool-routing commands (performance_start_trace, lighthouse_audit, take_snapshot), a runnable script (scripts/analyze.sh), specific thresholds (LCP<2.5s, INP<200ms, CLS<0.1, 4.5:1 contrast), and a copy-ready output template; some fix recommendations remain generic ('Optimize images', 'Use code splitting').	4 / 5
Workflow Clarity	The 'How it works' section gives a clear five-step sequence with an explicit re-run verification step, a feedback loop (runtime failures localize source inspection), and supporting checklists for the complex process.	5 / 5
Progressive Disclosure	Clear section headers and a well-signaled References section point one level deep to sibling skills and MEASUREMENT.md, with the only bundle file (scripts/analyze.sh) genuinely referenced; the large inlined category detail is appropriate as the core audit checklist but could partially move to reference files.	4 / 5
	Total	16 / 20 Passed

Description

83%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.

A strong, third-person description that clearly states what the skill does and when to use it with natural trigger phrases. Minor gaps in action-verb variety and synonym coverage, plus slight overlap risk with sibling domain skills, keep it just short of maximal scores.

Dimension	Reasoning	Score
Specificity	Names the domain and lists five specific coverage areas (performance, accessibility, SEO, best practices, agentic browsing), but relies on a single main action verb ('Run an evidence-led web quality audit') rather than multiple distinct concrete actions.	4 / 5
Completeness	Explicitly answers both 'what' (evidence-led web quality audit covering five domains) and 'when' with concrete trigger phrases in a 'Use when...' clause.	5 / 5
Trigger Term Quality	Provides five natural trigger phrases users would actually say ('audit my site', 'review web quality', 'run lighthouse audit', 'check page quality', 'optimize my website'); a few synonyms (e.g., 'page speed', 'accessibility check') are missing, keeping it just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Clear niche with distinct audit-focused triggers, but the body references separate performance/accessibility/SEO/best-practices skills, creating minor overlap risk with those closely related skills.	4 / 5
	Total	17 / 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
relative_links	Relative link issues: 6 suspicious	Warning

	Total	15 / 16 Passed

Repository: addyosmani/web-quality-skills
Path: skills/web-quality-audit/SKILL.md
Commit: afa8da9

Reviewed: 5 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.