performance-optimization
Diagnose and fix web performance issues including Core Web Vitals (LCP, INP, CLS), bundle size, asset optimization, render performance, and runtime efficiency. Use this skill whenever the user wants to improve page speed, fix Core Web Vitals, optimize assets, reduce bundle size, debug slow renders, or systematically improve a site's performance. Triggers on performance, page speed, Core Web Vitals, LCP, INP, CLS, FID, TTFB, bundle size, code splitting, image optimization, lazy loading, render blocking, slow page, performance audit, Lighthouse score. Also triggers when traffic or conversion is dropping due to perceived slowness.
65
78%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/performance-optimization/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 thoroughly covers specific capabilities, provides comprehensive trigger terms users would naturally use, and clearly delineates both what the skill does and when it should be activated. The explicit 'Triggers on' list and the inclusion of indirect triggers (traffic/conversion dropping) demonstrate thoughtful design. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: diagnose and fix web performance issues, Core Web Vitals (LCP, INP, CLS), bundle size optimization, asset optimization, render performance, and runtime efficiency. These are clearly defined, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (diagnose and fix web performance issues across multiple dimensions) and 'when' (explicit 'Use this skill whenever...' clause plus a detailed 'Triggers on' list). Both are thoroughly addressed with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'page speed', 'Core Web Vitals', 'LCP', 'INP', 'CLS', 'FID', 'TTFB', 'bundle size', 'code splitting', 'image optimization', 'lazy loading', 'render blocking', 'slow page', 'Lighthouse score', and even the indirect trigger of 'traffic or conversion dropping due to perceived slowness'. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche of web performance optimization with highly specific trigger terms like Core Web Vitals acronyms, Lighthouse score, bundle size, and render blocking. Unlikely to conflict with general web development or other skills due to the performance-specific terminology. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a comprehensive performance optimization skill with good structure, clear metric targets, and well-organized progressive disclosure. Its main weaknesses are verbosity (explaining concepts Claude already understands like what Core Web Vitals measure) and lack of executable code examples — most guidance is descriptive rather than copy-paste actionable. The workflow is logical but could benefit from explicit validation gates.
Suggestions
Add executable code snippets for key fixes (e.g., a preload tag example, a dynamic import example, a scheduler.yield() usage pattern) instead of just describing them in bullet points.
Trim explanatory text that Claude already knows — remove 'What it measures' descriptions and focus on targets, causes, and fixes. The metric definitions add ~30 lines of low-value content.
Add explicit validation checkpoints to the workflow, e.g., 'After fix: re-run Lighthouse. If metric improved by <X>, investigate further. If regressed, revert and re-diagnose.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is well-organized but includes substantial explanatory content that Claude already knows (what LCP/INP/CLS measure, what TTFB is, general image optimization concepts). The 'common causes' and 'common fixes' lists are useful reference material but could be significantly tightened. The failure patterns section adds value but is somewhat verbose. | 2 / 3 |
Actionability | The skill provides specific metric thresholds, named tools, and concrete fix strategies (e.g., 'import { fn } from lib', 'loading="lazy"', 'font-display: swap'), but lacks executable code examples or copy-paste-ready commands. Most guidance is descriptive bullet points rather than concrete implementation snippets. | 2 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced and logically sound, with re-measurement after fixes. However, it lacks explicit validation checkpoints or feedback loops for error recovery — step 6 says 're-measure' but doesn't specify what to do if metrics regress or how to verify a fix actually worked before moving on. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled references to three separate files (audit-template.md, optimization-checklist.md, optimization-playbook.md) that are one level deep. The main content serves as an effective overview while pointing to detailed materials for deeper work. Cross-references to related skills (qa-testing, seo-technical) are also clear. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- rampstackco/claude-skills
- Commit
8e70d03
- 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.