web-performance-audit
Audit web performance using Chrome DevTools MCP. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed.
86
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
89%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 solid description that clearly communicates when to use the skill with explicit trigger terms and a 'Use when' clause. Its main weakness is that the 'what' portion is somewhat high-level—it says 'audit web performance' but doesn't enumerate specific concrete actions or outputs. Overall it performs well for skill selection purposes.
Suggestions
Add more specific concrete actions to improve specificity, e.g., 'Measures Core Web Vitals, analyzes network waterfalls, identifies render-blocking resources, and runs Lighthouse audits using Chrome DevTools MCP.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (web performance) and the tool (Chrome DevTools MCP), and mentions actions like 'audit, profile, debug, optimize', but doesn't list specific concrete capabilities (e.g., 'measure Core Web Vitals, analyze network waterfall, identify render-blocking resources'). | 2 / 3 |
Completeness | Clearly answers both 'what' (audit web performance using Chrome DevTools MCP) and 'when' (explicit 'Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'audit', 'profile', 'debug', 'optimize', 'page load performance', 'Lighthouse scores', 'site speed'. These cover the most common ways users would phrase performance-related requests. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to web performance auditing via Chrome DevTools MCP, with distinct triggers like 'Lighthouse scores' and 'site speed' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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, actionable skill with excellent workflow clarity and concrete tool usage examples. Its main weakness is length—the codebase analysis section and some reference tables could be split into separate files to improve token efficiency. The key guidelines section effectively sets behavioral expectations with specific, non-obvious guidance.
Suggestions
Move Phase 5 (Codebase Analysis) details into a separate CODEBASE_ANALYSIS.md reference file, keeping only a brief summary and link in the main skill.
Consider moving the Core Web Vitals thresholds table to a reference file, as these are well-known values Claude likely already has access to.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some content that could be tightened—the framework/bundler detection table and tree-shaking/polyfill sections are somewhat verbose for things Claude already knows. The thresholds table and config file listings add bulk that could be referenced externally. | 2 / 3 |
Actionability | Provides concrete tool calls with exact function signatures and parameters, specific thresholds for metrics, detailed checklists, and clear examples of what to look for. The guidance is specific and directly executable (e.g., 'compress hero.png (450KB) to WebP' not 'optimize images'). | 3 / 3 |
Workflow Clarity | Clear 5-phase workflow with a progress checklist, explicit sequencing, troubleshooting steps for Phase 1, and conditional logic (skip Phase 5 for third-party sites). Includes verification at the start (check MCP tools available) and validation guidance throughout (verify claims before recommending, confirm unused before suggesting removal). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and phases, but Phase 5's codebase analysis content (framework detection tables, tree-shaking details, polyfill checks) is quite lengthy and could be split into a separate reference file. The skill is a monolithic document that would benefit from offloading detailed reference material. | 2 / 3 |
Total | 10 / 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
- warpdotdev/oz-skills
- Commit
6c08c49
- 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.