web-quality-audit

Comprehensive web quality audit covering performance, accessibility, SEO, and best practices in a single review. Use when asked to "audit my site", "review web quality", "run lighthouse audit", "check page quality", or "optimize my website" across multiple areas at once. Orchestrates specialized skills for depth. Do NOT use for single-area audits — prefer core-web-vitals, web-accessibility, seo, or web-best-practices for focused work.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

50%

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-organized and specific but verbose, relying heavily on standard web-quality knowledge Claude already has. Its biggest gaps are not referencing the bundled scripts/analyze.sh tool and lacking executable commands and validation checkpoints in its workflow.

Suggestions

Reference and invoke scripts/analyze.sh from the body so the skill's one executable tool is discoverable and used for the actual checking.

Trim the inline checklists of common-knowledge items (WCAG ratios, basic HTML best practices) and move detailed check lists into reference files, keeping SKILL.md as a lean overview.

Add validation/verification checkpoints to the 'How it works' workflow (e.g., confirm every category was audited and cross-check findings against the deploy checklist before reporting).

Dimension	Reasoning	Score
Conciseness	The ~180-line body largely restates standard web-quality knowledge Claude already has (WCAG contrast ratios, font-display:swap, set lang, use <!DOCTYPE html>, no duplicate IDs) plus percentage weights and long enumerated checklists. It is organized rather than a prose wall, so it is above a 1, but it is far from lean and adds much redundant common knowledge.	2 / 3
Actionability	Guidance is specific (named thresholds, named techniques like WebP/AVIF, srcset, code splitting) so it is above vague, but there are almost no executable commands and the bundled scripts/analyze.sh — the one concrete tool that performs checks — is never referenced or invoked from the body. Concrete guidance is present but incomplete.	2 / 3
Workflow Clarity	A clear 4-step sequence exists in 'How it works' (analyze, categorize, recommend, include examples), but there are no validation/verification checkpoints or error-recovery feedback loops. Sequence is present but checkpoints are missing or implicit.	2 / 3
Progressive Disclosure	Sections are organized and the References link one level deep to sibling skills, but the provided bundle file scripts/analyze.sh is never referenced from SKILL.md, and the large inline checklists across four categories are content that could be split into reference files. Structure exists but the in-bundle reference is missing and content that should be separate is inline.	2 / 3
	Total	8 / 12 Passed

Description

90%

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 strong: it has explicit natural-language triggers, answers both what and when, and clearly distinguishes itself from sibling single-area skills. The only mild weakness is specificity, since the concrete actions are mostly high-level ('audit', 'orchestrates') rather than a list of distinct operations.

Dimension	Reasoning	Score
Specificity	Names the four audit domains and a couple of actions ('audit...in a single review', 'orchestrates specialized skills'), but the actions are high-level and largely one verb repeated rather than a list of distinct concrete operations. Not a 3 because it lacks multiple specific concrete actions like extract/fill/merge; not a 1 because the domain and an action are clearly stated.	2 / 3
Completeness	Clearly answers both 'what' (comprehensive multi-area web quality audit) and 'when' (explicit 'Use when...' triggers), and adds exclusion guidance ('Do NOT use for single-area audits'). Both what and when are explicit.	3 / 3
Trigger Term Quality	Includes multiple natural phrases users would actually say ('audit my site', 'review web quality', 'run lighthouse audit', 'check page quality', 'optimize my website'), with good coverage of variations. Matches the anchor for good coverage of natural terms.	3 / 3
Distinctiveness Conflict Risk	Defines a clear niche ('multiple areas at once') and explicitly distinguishes itself from sibling skills ('Do NOT use for single-area audits — prefer core-web-vitals, web-accessibility, seo, or web-best-practices'). Unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 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: 5 suspicious	Warning

	Total	15 / 16 Passed

Repository: tech-leads-club/agent-skills
Commit: 9026164

Reviewed: 4 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.