refactor-pass
Perform a refactor pass focused on simplicity after recent changes. Use when the user asks for a refactor/cleanup pass, simplification, or dead-code removal and expects build/tests to verify behavior.
85
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 97%
↑ 1.00xAgent success when using this skill
Validation for skill structure
Discovery
82%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid description that clearly communicates both purpose and trigger conditions. The explicit 'Use when...' clause with natural trigger terms is a strength. However, the description could be more specific about what concrete refactoring actions are performed and could better distinguish itself from other potential code improvement skills.
Suggestions
Add more specific concrete actions like 'consolidate duplicate code, remove unused functions, simplify complex conditionals' to improve specificity
Consider adding distinguishing context like 'post-feature refactoring' or mentioning specific patterns it targets to reduce potential overlap with general code review skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (refactoring) and some actions ('refactor pass', 'simplification', 'dead-code removal'), but lacks comprehensive concrete actions like specific refactoring techniques or what 'simplicity' entails. | 2 / 3 |
Completeness | Clearly answers both what ('Perform a refactor pass focused on simplicity after recent changes') and when ('Use when the user asks for a refactor/cleanup pass, simplification, or dead-code removal and expects build/tests to verify behavior'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'refactor', 'cleanup pass', 'simplification', 'dead-code removal'. These are terms developers commonly use when requesting this type of work. | 3 / 3 |
Distinctiveness Conflict Risk | Somewhat specific to refactoring/cleanup but could overlap with general code review skills or other refactoring-focused skills. The 'after recent changes' qualifier helps but 'refactor' is a broad term. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a concise, well-structured skill that efficiently communicates a refactoring workflow. However, it lacks concrete examples of what 'dead code' or 'excessive parameters' look like in practice, and the verification step needs a feedback loop for handling test failures.
Suggestions
Add 1-2 brief code examples showing before/after for common refactoring patterns (e.g., dead code removal, logic straightening)
Add a feedback loop for step 3: 'If tests fail: revert the problematic refactor, apply smaller changes, re-run tests'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient with no unnecessary explanation. Every line serves a purpose and assumes Claude understands refactoring concepts without explanation. | 3 / 3 |
Actionability | Provides clear categories of what to refactor but lacks concrete examples of code patterns to look for or specific commands. The guidance is directional rather than executable. | 2 / 3 |
Workflow Clarity | Steps are clearly sequenced (review → apply → verify → suggest), but lacks explicit validation checkpoints or feedback loops for when tests fail. No guidance on what to do if build/tests don't pass. | 2 / 3 |
Progressive Disclosure | For a simple, single-purpose skill under 50 lines, the content is appropriately organized with a clear workflow section. No external references needed for this scope. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.