perf-web-optimization
Optimize web performance: bundle size, images, caching, lazy loading, and overall page speed. Use when site is slow, reducing bundle size, fixing layout shifts, improving Time to Interactive, or optimizing for Lighthouse scores. Triggers on: web performance, bundle size, page speed, slow site, lazy loading. Do NOT use for Core Web Vitals-specific fixes (use core-web-vitals), running Lighthouse audits (use perf-lighthouse), or Astro-specific optimization (use perf-astro).
95
93%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 provides specific capabilities, rich natural trigger terms, explicit 'Use when' and 'Do NOT use' clauses, and clear boundaries with related skills. The inclusion of negative triggers (exclusions referencing other skills) is a best practice that significantly reduces conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: bundle size optimization, image optimization, caching, lazy loading, and page speed improvement. These are clearly defined, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (optimize bundle size, images, caching, lazy loading, page speed) and 'when' (explicit 'Use when' clause with specific triggers, plus a 'Do NOT use' clause that further clarifies boundaries). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'web performance', 'bundle size', 'page speed', 'slow site', 'lazy loading', 'layout shifts', 'Time to Interactive', 'Lighthouse scores'. These are all terms a user would naturally use when seeking performance help. | 3 / 3 |
Distinctiveness Conflict Risk | Exceptionally distinctive due to explicit 'Do NOT use for' exclusions that delineate boundaries with related skills (core-web-vitals, perf-lighthouse, perf-astro). This makes it very clear when this skill should and should not be selected. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured performance optimization skill. It excels at conciseness and actionability with concrete, executable examples across images, fonts, scripts, CSS, bundling, and caching. The main weakness is that the stated Measure→Verify workflow isn't fully realized in the body—there's no explicit 'after implementing, re-measure and compare' feedback loop, which is important for iterative performance work.
Suggestions
Add an explicit verification step after implementation (e.g., 're-run Lighthouse or check metrics to confirm improvements, compare before/after') to close the Measure→Verify loop stated in the introduction.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and practical. No unnecessary explanations of what images, fonts, or caching are—just concrete patterns and values. The metrics table is compact and useful. No padding or concept explanations Claude already knows. | 3 / 3 |
Actionability | Provides fully executable HTML snippets, bash commands, JavaScript patterns, and cache header configurations. Code examples are copy-paste ready with specific attributes, values, and package alternatives with sizes. | 3 / 3 |
Workflow Clarity | The opening states 'Measure → Identify → Prioritize → Implement → Verify' but the body doesn't follow this sequence with explicit validation checkpoints. The checklist at the end serves as a verification aid, but there's no feedback loop (e.g., 'measure again after changes, compare metrics'). For a performance optimization workflow, the verify step is underspecified. | 2 / 3 |
Progressive Disclosure | Clean overview with well-organized sections, appropriate cross-references to perf-lighthouse for audits, and one-level-deep references to detailed materials (core-web-vitals.md, bundle-optimization.md, image-optimization.md). Content is appropriately split between overview and detailed references. | 3 / 3 |
Total | 11 / 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
81e7e0d
- 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.