finding-duplicate-functions

Use when auditing a codebase for semantic duplication - functions that do the same thing but have different names or implementations. Especially useful for LLM-generated codebases where new functions are often created rather than reusing existing ones.

2.00x

Quality

68%

Does it follow best practices?

Impact

98%

2.00x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/finding-duplicate-functions/SKILL.md

Quality

Content

62%

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

This skill has a well-designed workflow with clear sequencing and a useful quick reference table, making the multi-step process easy to follow. However, it suffers from referencing numerous external scripts and prompt templates that aren't provided in the bundle, making the skill non-executable as-is. The content could be tightened by removing explanatory sections Claude doesn't need (like 'When to Use' and the overview paragraph) and by providing concrete subagent invocation syntax.

Suggestions

Provide the referenced bundle files (extract-functions.sh, categorize-prompt.md, find-duplicates-prompt.md, etc.) or inline the essential content so the skill is actually executable

Add concrete syntax for dispatching subagents in Phases 2 and 4 instead of the vague 'dispatch a subagent' instruction

Remove or condense the 'When to Use' and 'Overview' sections - Claude can infer applicability from the skill description and content

Dimension	Reasoning	Score
Conciseness	Generally efficient but includes some unnecessary sections like 'When to Use' (Claude can infer this) and the dot graph which adds visual noise without executable value. The 'Overview' paragraph explaining what semantic duplicates are is somewhat redundant given Claude's knowledge. However, the tables and structured content are well-organized.	2 / 3
Actionability	Provides concrete bash commands and a clear pipeline, but the actual scripts referenced (extract-functions.sh, categorize-prompt.md, etc.) are not provided in the bundle, making the guidance non-executable in practice. The subagent dispatch steps (Phases 2 and 4) lack concrete invocation syntax - they say 'dispatch a subagent' without showing how.	2 / 3
Workflow Clarity	The 6-phase workflow is clearly sequenced with a helpful quick reference table, explicit inputs/outputs for each phase, and Phase 6 includes a validation checklist (verify tests, update callers, delete, run tests). The pipeline flow is unambiguous with clear data dependencies between steps.	3 / 3
Progressive Disclosure	The skill references multiple external files (scripts/extract-functions.sh, scripts/categorize-prompt.md, scripts/find-duplicates-prompt.md, etc.) which is good progressive disclosure design, but none of these bundle files are actually provided. The SKILL.md itself is well-structured with sections, but without the referenced files, the skill is incomplete and the references are effectively broken.	2 / 3
	Total	9 / 12 Passed

Description

75%

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 has strong completeness with an explicit 'Use when' clause and good distinctiveness for its niche. However, it could benefit from listing more concrete actions beyond just 'auditing' and including more natural trigger terms that users might use when they need this capability.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Identifies semantically duplicate functions, suggests consolidation targets, and generates refactoring recommendations.'

Expand trigger terms to include natural variations like 'duplicate code', 'redundant functions', 'DRY violations', 'code deduplication', or 'dead code'.

Dimension	Reasoning	Score
Specificity	The description names the domain (semantic duplication auditing) and describes the general action (auditing for functions that do the same thing with different names/implementations), but doesn't list multiple concrete actions like 'identify duplicates, suggest consolidations, generate refactoring plans'.	2 / 3
Completeness	The description explicitly answers both 'what' (auditing for semantic duplication - functions doing the same thing with different names/implementations) and 'when' (when auditing a codebase for semantic duplication, especially for LLM-generated codebases) with a clear 'Use when' clause.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'semantic duplication', 'codebase', 'functions', and 'LLM-generated codebases', but misses common natural variations users might say such as 'duplicate code', 'redundant functions', 'code deduplication', 'DRY violations', or 'refactor'.	2 / 3
Distinctiveness Conflict Risk	The focus on semantic duplication detection is a clear, distinct niche that is unlikely to conflict with general code review, refactoring, or other code analysis skills. The mention of LLM-generated codebases further narrows the scope.	3 / 3
	Total	10 / 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: obra/superpowers-lab
Commit: 51111f7

Reviewed: about 1 month 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.