Content
53%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 maximally lean but functionally hollow: it is a one-line pointer to @.claude/rules/imports.md, a file that is not shipped in the bundle, so the skill delivers no usable import guidance on its own. The cryptic qualifier 'regardless of path setting' further obscures the intended workflow.
Suggestions
Ship the import rules inside the skill (e.g., a references/imports.md listed in the bundle) or inline the key ordering rules directly in the body, so the pointer resolves to real content.
Clarify or remove 'regardless of path setting' — state plainly when the rules apply (e.g., 'Apply to all Python files in dlt/ and tests/, including test helpers') so the single action is unambiguous.
Add a short example of correct vs. incorrect import ordering so the skill remains actionable even if the referenced file is unavailable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is a single line with zero padding and no explanation of concepts Claude already knows — every token earns its place, matching the 'lean and efficient' anchor exactly. It cannot score higher and does not risk a lower anchor on a one-line body. | 5 / 5 |
Actionability | "Use @.claude/rules/imports.md" points at a specific file, but that file is not in the bundle and does not exist, so no executable import rules are actually delivered — 'minimal concrete guidance; missing the specific steps to execute' (anchor 2). It is above anchor 1 because the directive is specific rather than abstract, but below anchor 3 because there is no partially-complete executable guidance at all. | 2 / 5 |
Workflow Clarity | It is a single-action skill, but the action is not unambiguous ("regardless of path setting" is cryptic) and the workflow dead-ends at a missing file, so the simple-skill exception to score 5 does not apply. This lands at anchor 3: a stated step whose follow-through is broken. | 3 / 5 |
Progressive Disclosure | The sole reference is clearly signaled but points outside the skill bundle to a nonexistent path, leaving a broken, structureless stub — anchor 2 ('minimal structure'). It is not anchor 1 because there is no nested-reference chain, and not anchor 3 because there are no valid references or own sections to organize. | 2 / 5 |
Total | 12 / 20 Passed |