refactor-clean
Safely identifies and removes dead code with test verification and rollback capabilities
Install with Tessl CLI
npx tessl i github:sc30gsw/claude-code-customes --skill refactor-clean68
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/skillValidation for skill structure
Discovery
32%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description identifies a clear domain (dead code removal) with safety features mentioned, but lacks explicit trigger guidance and comprehensive action details. The absence of a 'Use when...' clause significantly weakens its utility for skill selection, and the trigger terms could be expanded to capture more natural user language.
Suggestions
Add a 'Use when...' clause with trigger terms like 'unused code', 'unreachable code', 'code cleanup', 'remove dead code', or 'find unused functions'
Expand specific actions to include concrete capabilities like 'analyze import dependencies', 'detect unused functions/variables', 'verify removal safety with tests'
Include common variations of terminology users might use: 'unused imports', 'orphaned code', 'code that's never called'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (dead code removal) and mentions some capabilities (test verification, rollback), but doesn't list comprehensive concrete actions like 'analyze dependencies', 'detect unused functions', or 'generate removal patches'. | 2 / 3 |
Completeness | Describes what it does (identifies and removes dead code) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes 'dead code' which is a relevant term, but misses common variations users might say like 'unused code', 'unreachable code', 'code cleanup', or 'remove unused functions'. | 2 / 3 |
Distinctiveness Conflict Risk | The 'dead code' focus provides some distinction, but 'test verification' and 'rollback capabilities' are generic enough to potentially overlap with refactoring or testing skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is well-structured with excellent workflow clarity including proper validation checkpoints and rollback procedures. It's concise and respects Claude's intelligence. The main weakness is lack of executable commands - tool names are listed but actual invocation syntax is missing, reducing immediate actionability.
Suggestions
Add executable command examples for each tool (e.g., 'npx knip', 'npx depcheck', 'npx ts-prune')
Include a sample output format or template for the .reports/dead-code-analysis.md report
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, listing only essential steps and tool names without explaining what dead code is or how the tools work internally. Every line serves a purpose. | 3 / 3 |
Actionability | Provides tool names and a clear process but lacks executable commands or code examples. 'Run dead code analysis tools' and 'knip' are mentioned but no actual command syntax like 'npx knip' is provided. | 2 / 3 |
Workflow Clarity | Clear sequential workflow with explicit validation checkpoints (run tests, verify pass, apply, re-run, rollback on failure). The feedback loop for error recovery is well-defined. | 3 / 3 |
Progressive Disclosure | Content is appropriately brief for a simple skill, but mentions generating a report to '.reports/dead-code-analysis.md' without linking to a template or example format. Could benefit from a reference to example output structure. | 2 / 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.