Content
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is structurally organized but lacks actionable, concrete guidance. The instructions read as high-level principles rather than executable steps — there are no code examples, no specific refactoring patterns, and no concrete validation commands. The skill relies heavily on an external playbook file without providing enough substance in the main body to be independently useful.
Suggestions
Add at least 2-3 concrete code examples showing before/after refactoring patterns (e.g., extract method, replace conditional with polymorphism) to make the skill actionable.
Replace vague instructions like 'Identify high-impact refactor candidates' with specific heuristics or checklists (e.g., 'Look for methods >30 lines, classes with >5 dependencies, duplicated blocks >3 lines').
Add explicit validation steps with concrete commands, e.g., 'Run existing test suite before and after each refactoring step; diff output to confirm no behavioral changes.'
Remove the redundant 'Context' section and the repeated persona description to improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary framing (e.g., 'You are a code refactoring expert...' repeated from the description, 'The user needs help refactoring code' context section) and 'when to use/not use' sections that are somewhat verbose. However, the core instructions are reasonably tight. | 2 / 3 |
Actionability | The instructions are entirely abstract and vague — 'Identify high-impact refactor candidates,' 'Apply changes with a focus on readability' — with no concrete code examples, specific commands, patterns, or executable guidance. There's nothing copy-paste ready or specific enough to act on. | 1 / 3 |
Workflow Clarity | There is a rough sequence (identify → break into steps → apply → validate), but validation checkpoints are vague ('Validate with tests and targeted regression checks') with no explicit feedback loops or concrete verification steps. For a refactoring skill involving potentially destructive changes, this lacks sufficient rigor. | 2 / 3 |
Progressive Disclosure | There is a reference to `resources/implementation-playbook.md` for detailed patterns, which is good progressive disclosure. However, the main content itself is thin and abstract — the reference is doing heavy lifting for content that should have at least some concrete examples inline. | 2 / 3 |
Total | 7 / 12 Passed |