Content
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The SKILL.md body is a well-organized, lean overview that delegates detailed code to a single clearly-signaled reference, with an unambiguous review workflow. Its only weakness is that the most executable, copy-paste-ready guidance lives in the reference rather than the body itself.
Suggestions
Consider including one small inline try/catch wrapper snippet in the body so the core defensive pattern is immediately actionable without opening the reference.
The Check section could name a quick concrete way to locate storage accesses (e.g., grep for localStorage/sessionStorage) to make the first step more executable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is lean — a brief intro, a tight Quick Reference list, and short Check/Fix/Explain/Code Review sections — with no lecturing on concepts Claude already knows; every token earns its place. | 3 / 3 |
Actionability | The guidance is concrete and specific ('Always wrap localStorage access in try/catch', 'Never store sensitive data… use httpOnly cookies') but the actual executable code lives in the reference, leaving the body with directives rather than copy-paste-ready examples. | 2 / 3 |
Workflow Clarity | As a simple single-purpose review skill the Check/Fix/Explain/Code Review sections give an unambiguous sequence, and the Code Review section explicitly calls for stating how the change should be verified in the browser. | 3 / 3 |
Progressive Disclosure | The body is a clear overview that points to one well-signaled, one-level-deep reference ('see references/rule.md'), and that reference file exists and holds the detailed code, matching the clear-overview-with-one-level-references anchor. | 3 / 3 |
Total | 11 / 12 Passed |