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.
74
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/skills-catalog/skills/(quality)/web-quality-audit/SKILL.mdQuality
Discovery
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.
This is an excellent skill description that hits all the marks. It clearly defines the scope (multi-area web audit), provides natural trigger terms users would actually say, explicitly states when to use and when NOT to use it, and proactively distinguishes itself from related specialized skills to minimize conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete areas covered (performance, accessibility, SEO, best practices) and describes the action as a comprehensive audit covering multiple areas in a single review. Also clarifies it orchestrates specialized skills and distinguishes from single-area audits. | 3 / 3 |
Completeness | Clearly answers both 'what' (comprehensive web quality audit covering performance, accessibility, SEO, and best practices) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Also includes a 'Do NOT use' clause that further clarifies appropriate usage boundaries. | 3 / 3 |
Trigger Term Quality | Includes excellent natural trigger terms users would say: 'audit my site', 'review web quality', 'run lighthouse audit', 'check page quality', 'optimize my website'. These are realistic phrases covering multiple variations of how users would request this. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive — explicitly differentiates itself from related single-area skills (core-web-vitals, web-accessibility, seo, web-best-practices) and specifies it should only be used for multi-area audits. The 'Do NOT use' clause directly addresses potential conflicts. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a comprehensive web development reference guide than an actionable skill for Claude. It spends most of its token budget explaining standard Lighthouse audit concepts that Claude already knows well, rather than focusing on the unique value-add: how to orchestrate an audit, structure findings, and prioritize recommendations. The output format template and severity table are the strongest elements, but the bulk of the content should be dramatically condensed given the skill's stated purpose of orchestrating specialized sub-skills.
Suggestions
Drastically reduce the audit categories sections — Claude already knows what LCP, alt text, HTTPS, etc. are. Instead, provide a concise checklist of what to check and delegate details to the referenced specialized skills.
Add concrete executable examples for at least 2-3 common fixes (e.g., image optimization code, critical CSS extraction) since the skill promises 'code examples for fixes' but provides none.
Add validation/feedback steps to the workflow: after generating audit findings, verify issues exist in the actual code, and after suggesting fixes, describe how to confirm the fix resolved the issue.
Lean into the orchestration role described in the skill description — show how to invoke/reference the specialized sub-skills during the audit rather than duplicating their content inline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~150+ lines, largely restating well-known web development best practices that Claude already knows (what LCP is, what alt text is, what HTTPS is, etc.). The vast majority of content is explaining standard Lighthouse audit categories rather than providing novel, project-specific guidance. Almost every bullet point describes concepts Claude is already deeply familiar with. | 1 / 3 |
Actionability | The skill provides specific thresholds (LCP < 2.5s, contrast 4.5:1) and a structured output format template, which is useful. However, it lacks executable code examples for fixes despite claiming to 'Include code examples for fixes', and most guidance is descriptive rather than providing concrete commands or copy-paste-ready solutions. | 2 / 3 |
Workflow Clarity | The 4-step 'How it works' section provides a basic sequence, and the output format gives structure to results. However, there are no validation checkpoints, no feedback loops for verifying fixes, and no clear decision points for when to escalate or re-audit after changes are made. | 2 / 3 |
Progressive Disclosure | The References section at the end properly links to specialized skills for deeper dives, which is good progressive disclosure. However, the main body contains extensive inline content (all four audit categories fully detailed) that could have been kept much leaner with earlier references to the specialized skills, given the description explicitly says this skill 'orchestrates specialized skills for depth.' | 2 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- tech-leads-club/agent-skills
- Commit
906a57d
- Reviewed
Table of Contents
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.