dead-code-eliminator

Identify and analyze unused or redundant code including unused functions/methods, unused variables/imports, unreachable code, and redundant conditions. Use when cleaning up codebases, improving maintainability, reducing technical debt, or conducting code quality audits. Analyzes Python code using AST analysis and produces markdown reports listing dead code locations with line numbers, severity ratings, and recommendations. Triggers when users ask to find dead code, remove unused code, identify unused imports, find unreachable code, or clean up redundant logic.

2.06x

Quality

90%

Does it follow best practices?

Impact

93%

2.06x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

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

The content is highly actionable with a clear, validated workflow and good progressive-disclosure structure via bundled scripts and a one-level reference. Its main weakness is conciseness: a lengthy inline report template and content duplicated with the reference inflate the token budget.

Suggestions

Move the full sample report template (lines ~256-455) into references/ and keep only a brief structural outline inline, cutting roughly 200 lines of illustrative output.

Trim or remove the 'Categorize Findings' detail that duplicates references/dead-code-patterns.md, leaving a pointer to the reference instead.

Drop basic explanations (e.g., 'Code after return statements', 'Always-true or always-false checks') that assume Claude lacks common programming knowledge.

Dimension	Reasoning	Score
Conciseness	The ~560-line body includes a large inline report template (~200 lines of illustrative output) and duplicated content between the 'Categorize Findings' section and the dead-code-patterns.md reference, plus basic explanations like 'Code after return statements'; mostly efficient but could be tightened substantially.	3 / 5
Actionability	Provides copy-paste-ready executable commands throughout: bundled script invocations with arguments, vulture/autoflake/pylint commands with flags, grep patterns, and Python verification snippets covering common cases.	5 / 5
Workflow Clarity	A clear 6-step sequenced workflow includes a dedicated 'Verify Findings' step with explicit validation checkpoints (dynamic-usage, external-usage, framework-convention checks) before any removal, satisfying the destructive/batch-operation feedback-loop requirement.	5 / 5
Progressive Disclosure	SKILL.md serves as an overview with a real one-level-deep reference (dead-code-patterns.md, linked twice) and directly invoked bundled scripts; however some categorization content duplicates the reference and the large report template is fully inlined, leaving minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

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 is comprehensive and well-structured, clearly stating capabilities, scope, trigger conditions, and output format in third person. It covers what, when, and natural trigger phrases with low conflict risk.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions across four dead-code categories (unused functions/methods, unused variables/imports, unreachable code, redundant conditions) plus concrete report outputs (line numbers, severity ratings, recommendations), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (identifies/analyzes dead code via AST analysis, produces markdown reports) and 'when' ('Use when cleaning up codebases...' and 'Triggers when users ask to find dead code...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say with synonyms ('find dead code', 'remove unused code', 'identify unused imports', 'find unreachable code', 'clean up redundant logic'), matching the comprehensive-synonym anchor.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear Python dead-code-elimination niche with distinct triggers ('dead code', 'unused imports', 'unreachable code') that minimally overlap with general code-quality skills.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (564 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ArabelaTso/Skills-4-SE
Path: skills/dead-code-eliminator/SKILL.md
Commit: 4f38503

Reviewed: 5 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.