web-performance-audit
Web performance audits with Core Web Vitals, bottleneck identification, optimization recommendations. Use for page load times, performance reviews, UX optimization, or encountering LCP, FID, CLS issues, resource blocking, render delays.
83
75%
Does it follow best practices?
Impact
96%
1.20xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/web-performance-audit/skills/web-performance-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 a strong skill description that concisely covers specific capabilities, provides explicit trigger guidance with a 'Use for' clause, and includes both technical and natural-language trigger terms. It uses proper third-person voice and clearly carves out a distinct niche around web performance auditing. The description is well-structured and would allow Claude to confidently select this skill when relevant.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Web performance audits with Core Web Vitals', 'bottleneck identification', 'optimization recommendations'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what (web performance audits, bottleneck identification, optimization recommendations) and when ('Use for page load times, performance reviews, UX optimization, or encountering LCP, FID, CLS issues, resource blocking, render delays'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'page load times', 'performance reviews', 'UX optimization', 'LCP', 'FID', 'CLS', 'resource blocking', 'render delays'. These cover both technical acronyms and plain-language phrases users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on web performance and Core Web Vitals specifically. The trigger terms like LCP, FID, CLS, render delays, and resource blocking are very specific to this domain and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable overview of web performance auditing with some useful reference data (Core Web Vitals thresholds, performance budget schema) and executable code examples. However, it falls short on actionability for the optimization strategies (which are generic bullet points Claude already knows), lacks a clear measure-optimize-validate workflow loop, and could benefit from better progressive disclosure by linking to detailed implementation guides for specific optimization techniques.
Suggestions
Replace the generic optimization bullet points with concrete, executable examples (e.g., specific webpack config for code splitting, nginx config for brotli compression, HTML attributes for lazy loading)
Add an explicit audit workflow with validation: measure baseline → identify worst metric → apply fix → re-measure → compare, with clear decision points
Move detailed code examples and optimization implementations to separate referenced files (e.g., LIGHTHOUSE.md, OPTIMIZATIONS.md) and keep SKILL.md as a concise overview with navigation
Remove explanatory content Claude already knows (metric full names, general concepts) and focus on project-specific thresholds, tool configurations, and decision criteria
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably efficient but includes some information Claude already knows (like what LCP/FID/CLS stand for in the table). The optimization strategies section is a list of general advice that Claude would already know, adding limited value. The Core Web Vitals thresholds table is genuinely useful reference data though. | 2 / 3 |
Actionability | The code examples for web-vitals and Lighthouse are executable and concrete, but the optimization strategies are vague bullet points ('Enable gzip/brotli compression', 'Implement code splitting') without specific implementation code or commands. The audit checklist lists tasks without showing how to accomplish them. | 2 / 3 |
Workflow Clarity | The audit checklist at the end provides a sequence, but there are no validation checkpoints or feedback loops. For a performance audit workflow, there's no guidance on what to do when metrics are poor, no explicit 'measure → optimize → re-measure' cycle, and no error recovery steps. The checklist is a flat list without clear sequencing or dependencies. | 2 / 3 |
Progressive Disclosure | The content is organized into logical sections with headers, but it's somewhat monolithic — the optimization strategies and detailed code examples could be split into separate reference files. There are no references to external files for deeper dives on specific topics like image optimization or code splitting. | 2 / 3 |
Total | 8 / 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
- secondsky/claude-skills
- Commit
88da5ff
- 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.