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.
91
87%
Does it follow best practices?
Impact
98%
2.00xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
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.
This description has strong completeness with explicit 'Use when' guidance and good distinctiveness for its niche. However, it could benefit from more specific concrete actions beyond 'auditing' and additional natural trigger terms that users might actually say when looking for this functionality.
Suggestions
Add specific concrete actions like 'identifies duplicate functions, suggests consolidations, maps redundant implementations'
Include more natural trigger terms users might say: 'duplicate code', 'redundant functions', 'DRY violations', 'code deduplication', 'find similar functions'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (semantic duplication auditing) and describes the general action (auditing for functions that do the same thing), but doesn't list multiple concrete actions like 'identify duplicates, suggest consolidations, generate reports'. | 2 / 3 |
Completeness | Clearly answers both what (auditing for semantic duplication - functions doing the same thing with different names/implementations) AND when (explicit 'Use when auditing a codebase' and 'Especially useful for LLM-generated codebases'). | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'semantic duplication', 'functions', 'LLM-generated codebases', but misses common variations users might say like 'duplicate code', 'redundant functions', 'code deduplication', 'DRY violations'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche - semantic duplication in code is distinct from general code review, refactoring, or other code analysis skills. The LLM-generated codebase context further narrows the use case. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exemplary skill document that efficiently teaches a complex multi-phase workflow. It combines visual aids (diagram, tables), concrete commands, and practical guidance (high-risk zones, common mistakes) without unnecessary verbosity. The structure supports both quick reference and detailed execution.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of concepts Claude already knows. Every section serves a purpose - no padding about what semantic duplicates are or why they matter beyond the brief context-setting. | 3 / 3 |
Actionability | Provides concrete, executable commands with specific flags and options. Each phase has clear bash commands, file paths, and expected outputs. The quick reference table makes the workflow immediately actionable. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (numbered phases 1-6), a visual diagram, and explicit validation in Phase 6 (verify tests, run tests). The 'Common Mistakes' section provides error recovery guidance. | 3 / 3 |
Progressive Disclosure | Well-structured with quick reference table upfront, followed by detailed phases. References external scripts and prompt files appropriately without deep nesting. High-risk zones and common mistakes are clearly separated sections. | 3 / 3 |
Total | 12 / 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.
- Repository
- obra/superpowers-lab
- Commit
59389b1
- 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.