Content
57%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.
The body is well-structured with clean progressive disclosure to a genuine, well-organized reference file, but it is thin on executable guidance — no code, commands, or concrete DevTools steps in-body — and it spends tokens explaining LCP and duplicating the fix list across sections. The auto-generated 'Explain' and 'Code Review' sections read as template filler.
Suggestions
Replace the generic Check/Fix guidance with one concrete in-body example, e.g., the exact DevTools/Lighthouse path to identify the LCP element and a preload snippet for a hero image.
Delete the LCP definition sentence and the redundant Quick Reference bullets (they restate the Fix section) to remove duplication and assumed-unknown concepts.
Add an explicit re-measure checkpoint after fixes ('re-run Lighthouse and confirm LCP < 2.5s') to close the workflow's validation gap.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body explains what LCP is ('LCP is the most important Core Web Vital for perceived load speed—it measures when the main content becomes visible'), a concept Claude already knows, and the Quick Reference bullets largely duplicate the Fix sentence ('preloading critical resources, optimizing images...'). Mostly efficient but with unnecessary explanation and internal duplication that could be tightened. | 3 / 5 |
Actionability | Some concrete guidance is present — the 2.5s threshold, named tools ('Lighthouse or PageSpeed Insights'), and named techniques (preload, CDN, TTFB) — but the body contains no executable steps or code; 'Optimize LCP by preloading critical resources, optimizing images, using CDN, and reducing server response time' is a high-level hint list with all executable detail deferred to the reference. | 3 / 5 |
Workflow Clarity | The Check → Fix → Explain → Code Review sections provide a rough measure-then-fix sequence, and 'Verify the largest visible element renders within 2.5 seconds' gestures at validation, but there are no explicit checkpoints or feedback loops (e.g., re-measure after each fix), matching anchor 3's 'steps listed but validation gaps'. | 3 / 5 |
Progressive Disclosure | The body is a concise overview that clearly signals a real, one-level-deep reference: 'For full implementation details, code examples, and framework-specific guidance, see references/rule.md', which exists and is well-organized (Code Examples, Troubleshooting Flow, Verification). Content is appropriately split and navigation is trivial. | 5 / 5 |
Total | 14 / 20 Passed |