Content
67%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A dense, actionable body with a solid measurement workflow and well-structured one-level references. The chief weaknesses are mild over-explanation of known concepts and an inline-heavy LCP section that slightly unbalances the progressive disclosure.
Suggestions
Trim or move explanations of concepts Claude already knows (the metric-definition sentences and the 'usually this is' LCP-element list) to tighten conciseness.
Flesh out the framework quick-fix entries that are currently comment-only (React CLS, Vue CLS) with actual code so every example is executable.
Consider moving the LCP eagerness table and caveats into references/LCP.md to balance the inline detail across the three metrics.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is mostly efficient with high-value actionable detail, but it explains concepts Claude already knows (metric definitions like 'LCP measures when the largest visible content element renders' and the list of typical LCP elements), which could be trimmed. | 3 / 5 |
Actionability | It provides copy-paste-ready HTML, JS, and framework examples plus an LCP checklist, but the framework quick-fix section includes comment-only entries (e.g. React CLS: 'Always specify dimensions in img tags') with no accompanying code, leaving minor gaps. | 4 / 5 |
Workflow Clarity | The 'Measure before optimizing' section gives a clear 4-step measure-diagnose-fix-re-measure sequence with a re-run verification step and a checklist, but validation is guidance rather than an explicit pass/fail gate, so it stops short of the top anchor. | 4 / 5 |
Progressive Disclosure | References to references/LCP.md, INP.md, and CLS.md are one level deep and well-signaled with 'read when ...' conditions, but the LCP section inlines a large amount of detail (eagerness table, caveats, checklist) that creates a minor organization imbalance versus the delegated INP/CLS sections. | 4 / 5 |
Total | 15 / 20 Passed |