Content
86%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 lean, actionable rule set with concrete size thresholds and a clear conditional staging directive, appropriately self-contained for a micro-skill. Its only gap is the absence of a worked staging example to make the guidance fully copy-paste-ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Four sentences with no padding and no explanation of concepts Claude already knows (diffs, dependencies, call sites); every token earns its place, matching the score-5 "lean and efficient; assumes Claude's competence" anchor. It is not below 5 because nothing is superfluous. | 5 / 5 |
Actionability | Concrete thresholds (800/500 lines) and a concrete staging directive ("identify the smallest coherent stage to land first", "base on the actual diff, dependencies, and affected call sites") give mostly executable guidance, but no worked example of staging a real diff, matching score 4. It is not 5 because the staging step lacks a copy-paste-ready example. | 4 / 5 |
Workflow Clarity | The rule and its conditional branch (exceed limit → propose split, identify smallest stage) are clear and unambiguous for an advisory skill; no validation checkpoint is required because the operation is non-destructive. It is not 5 because the staging sub-workflow is described abstractly rather than as an explicit sequenced/checkpointed process. | 4 / 5 |
Progressive Disclosure | This is a self-contained micro-skill (well under 50 lines, no bundle files, no external content to disclose), so the simple-skill exception applies and progressive disclosure is satisfied without file references or heavy sectioning. It is not below 5 because there is nothing that belongs in a separate file. | 5 / 5 |
Total | 18 / 20 Passed |