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.
A tight, actionable body that gives Claude exactly the API modes, include flags, result-handling steps, CLI equivalents, and error guidance needed to use Repowise code-health. It is efficient with tokens and well-structured, with only minor room to add a copy-paste code example and an explicit retry loop.
Suggestions
Add one short copy-paste-ready snippet (e.g., a `get_health()` call with sample output) to push actionability to fully executable.
Add an explicit validate→fix→retry feedback loop in the results-usage workflow for cases where `not_indexed` or `unresolved` entries appear.
Consider extracting the `include` flag reference table into a separate reference file if the marker list grows, to keep the overview lean.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient; assumes Claude's competence by listing markers (McCabe complexity, LCM4, god classes) without explaining what they are, and every section earns its place. | 5 / 5 |
Actionability | Provides concrete, executable API calls ('get_health(targets=[...], include=[...])') and CLI equivalents ('repowise health --refactoring-targets'), but lacks a full copy-paste-ready code snippet covering common cases, keeping it just under 5. | 4 / 5 |
Workflow Clarity | 'How to use the results' is a clearly sequenced numbered list with validation checkpoints ('Check unresolved before calling a file clean', 'cross-check get_risk'), plus an error-handling section, but lacks an explicit validate→fix→retry feedback loop. | 4 / 5 |
Progressive Disclosure | Single-purpose skill with no bundle files; content is well-organized into clearly headed sections (modes, include flags, results usage, CLI, errors) making navigation easy without external references. | 5 / 5 |
Total | 18 / 20 Passed |