Content
65%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 a well-organized, concise overview with excellent progressive disclosure via a real one-level-deep reference, and the Check/Fix guidance is concrete and actionable. Weaknesses are mild redundancy across sections and verification steps being only implicitly referenced in the body rather than explicitly sequenced.
Suggestions
Collapse the Quick Reference bullets into the Check/Fix sections (or vice versa) to remove the restated content and tighten the body.
Add an explicit inline verification checkpoint (e.g., 'Verify: confirm the meter exposes the label in the accessibility tree via axe/Lighthouse') rather than deferring all verification to the reference.
Trim the meta-instructional 'Explain' section or merge it into 'Why It Matters' in the reference to reduce padding.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient, but the Quick Reference bullets restate the Check and Fix sections, and the 'Explain' and 'Code Review' sections are somewhat padded and redundant with the description. | 3 / 5 |
Actionability | Concrete, specific guidance — check for '<meter>' or role='meter' elements lacking an accessible name, then add 'aria-label' or 'aria-labelledby' — though executable code examples are deferred to the reference file. | 4 / 5 |
Workflow Clarity | A Check→Fix→Code Review sequence is present, but validation/verification is only vaguely hinted ('note how to verify the fix with browser accessibility tooling') and the explicit verification steps live in the reference rather than the body. | 3 / 5 |
Progressive Disclosure | A concise, well-sectioned overview points via a clearly signaled one-level-deep reference ('see references/rule.md') to a real file holding the code examples, rationale, exceptions, and verification steps. | 5 / 5 |
Total | 15 / 20 Passed |