Content
65%Reviews 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 rule index, but its actionability and progressive disclosure are undermined because the detailed rule files and AGENTS.md it points to are absent from the bundle, and no application workflow is given.
Suggestions
Include the referenced bundle files (rules/*.md and AGENTS.md) or remove the dangling references so progressive disclosure actually resolves.
Add a brief executable code snippet inline for the highest-impact rules (e.g. a minimal FlashList example) so the body is actionable without chasing external files.
Add a short application workflow — e.g. 'when diagnosing a performance issue, start with CRITICAL list-performance rules, then animation, then verify on device' — instead of the single 'read rule files' instruction.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | A lean rule catalog with one-line directives and a priority table; it assumes Claude's competence and avoids explaining concepts Claude already knows, so most tokens earn their place. | 3 / 3 |
Actionability | Rules are concrete directives ('Use FlashList for large lists', 'Animate only transform and opacity'), but no executable code or examples appear in the body — all implementation is deferred to the rule files, leaving the guidance incomplete. | 2 / 3 |
Workflow Clarity | The priority table provides rough sequencing (CRITICAL→LOW), but there is no workflow for applying the rules and the 'How to Use' section only says to 'read individual rule files' without a clear process or checkpoints. | 2 / 3 |
Progressive Disclosure | Structure is well-signaled and one level deep conceptually, but the referenced files (rules/*.md, AGENTS.md) are not present in the bundle, so the disclosed detail cannot actually be reached. | 2 / 3 |
Total | 9 / 12 Passed |