refactor-clean

Safely identifies and removes dead code with test verification and rollback capabilities

Quality

33%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/refactor-clean/SKILL.md

Quality

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) and mentions useful capabilities like test verification and rollback, but lacks explicit trigger guidance ('Use when...') and misses common user-facing keywords like 'unused code', 'unreachable code', or 'code cleanup'. It would benefit from more specific concrete actions and an explicit 'when to use' clause.

Suggestions

Add a 'Use when...' clause with trigger terms like 'dead code', 'unused code', 'unreachable code', 'code cleanup', 'remove unused functions/imports'.

List more specific concrete actions such as 'detects unused functions, removes unreferenced imports, cleans up unreachable branches, eliminates commented-out code blocks'.

Include common keyword variations users might say: 'unused code', 'unreachable code', 'code cleanup', 'refactor unused', 'prune codebase'.

Dimension	Reasoning	Score
Specificity	Names the domain (dead code removal) and some actions (identifies, removes, test verification, rollback), but doesn't list specific concrete actions like 'detects unused functions, removes unreferenced imports, cleans up commented-out blocks'.	2 / 3
Completeness	Describes what it does (identifies and removes dead code with test verification and rollback) but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 2, and the 'what' is also not very detailed, placing this at 1.	1 / 3
Trigger Term Quality	Includes 'dead code' which is a natural term users would say, but misses common variations like 'unused code', 'unreachable code', 'code cleanup', 'remove unused functions/imports', or 'refactor'.	2 / 3
Distinctiveness Conflict Risk	The 'dead code' focus provides some distinctiveness, but could overlap with general refactoring skills, code cleanup skills, or code quality tools. The mention of rollback and test verification helps somewhat but isn't enough to fully distinguish it.	2 / 3
	Total	7 / 12 Passed

Implementation

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides a reasonable high-level workflow for dead code removal with a good safety-first approach including test verification and rollback. However, it lacks concrete, executable commands for the tools it references, making it more of an abstract checklist than actionable guidance. The rollback mechanism and report generation are described but not specified with actual code or commands.

Suggestions

Add executable command examples for each tool (e.g., `npx knip`, `npx depcheck`, `npx ts-prune`) with expected output formats

Provide a concrete rollback mechanism using git commands (e.g., `git stash`, `git checkout -- .`) rather than just stating 'rollback if tests fail'

Include a sample report format or template for .reports/dead-code-analysis.md so the output is well-defined

Add the actual test suite command placeholder (e.g., `npm test` or `yarn test`) to make step 5 copy-paste ready

Dimension	Reasoning	Score
Conciseness	Reasonably concise and doesn't over-explain concepts, but some items like 'Propose safe deletions only' and the final exclamation-mark warning are somewhat redundant given the workflow already describes test verification. Could be tighter.	2 / 3
Actionability	No executable commands or code examples are provided. Tool names are mentioned but without actual invocation syntax (e.g., `npx knip`, `npx depcheck`). The steps describe what to do abstractly rather than giving copy-paste ready commands or scripts.	1 / 3
Workflow Clarity	Steps are listed in a logical sequence and step 5 includes a validation/rollback feedback loop, which is good. However, the commands for each step are missing, the report generation step lacks specifics, and the rollback mechanism is not concretely defined (e.g., git stash, git checkout).	2 / 3
Progressive Disclosure	The content is organized with numbered steps and sub-bullets, which provides some structure. However, for a skill that involves multiple tools and a report format, it would benefit from referencing separate files for the report template or tool configuration. The severity categorization could also be linked to a more detailed reference.	2 / 3
	Total	7 / 12 Passed

Validation

100%

Warnings & errors only

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.

Repository: sc30gsw/claude-code-customes
Commit: 7aff694

Reviewed: 7 days ago

Table of Contents

Discovery Implementation Validation

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.