Content
85%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 well-structured, actionable skill body with a clear four-phase workflow, explicit validation/feedback loops, and concrete commands across languages. Conciseness and actionability are strong with only minor gaps (non-portable sed syntax, named-but-unshown tools).
Suggestions
Note that `sed -i ''` is macOS-specific; show the GNU/Linux equivalent or recommend a portable language-specific tool (jscodeshift/rope/gorename) as the primary rename path.
Provide a one-line example invocation for jscodeshift/ts-morph and rope/bowler since they are named as recommended tools but never demonstrated.
Trim the 'Inspired by' attribution line and redundant inline comments to tighten token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Largely efficient and well-organized with no over-explanation of concepts Claude already knows, but a few inline comments and the closing 'Inspired by' line could be trimmed; above the midpoint but not perfectly lean. | 4 / 5 |
Actionability | Provides concrete, executable commands (grep, ast-grep, sed, tsc, mypy, go vet) and a language-tool table, but a couple of gaps remain: the `sed -i ''` form is macOS-only, and jscodeshift/ts-morph are named without example invocations. | 4 / 5 |
Workflow Clarity | Four clearly sequenced phases (Analysis, Plan, Execute, Verify) with explicit validation checkpoints (type check, build, test, diff review) and a feedback loop for failure recovery — appropriate for a destructive/batch refactoring operation. | 5 / 5 |
Progressive Disclosure | Single self-contained file with no bundle references and clean section headers (When to Use, What it Does, Approach by Language, Anti-Patterns, Example); well-organized structure with nothing that needs externalizing. | 5 / 5 |
Total | 18 / 20 Passed |