Analyze codebases to identify reusable code patterns, duplications, and implementation patterns for future development. Use when refactoring code, identifying technical debt, finding opportunities for abstraction, or documenting common patterns in a directory or module. Outputs pattern catalogs, refactoring suggestions, and reusable template code.
76
71%
Does it follow best practices?
Impact
76%
1.40xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/code-pattern-extractor/SKILL.mdQuality
Discovery
92%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 is a well-crafted skill description that clearly articulates specific capabilities and includes an explicit 'Use when...' clause with relevant trigger scenarios. The description uses appropriate third-person voice and covers both the what and when effectively. Minor weakness is potential overlap with other code analysis or refactoring skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'identify reusable code patterns', 'duplications', 'implementation patterns', 'pattern catalogs', 'refactoring suggestions', and 'reusable template code'. | 3 / 3 |
Completeness | Clearly answers both what ('Analyze codebases to identify reusable code patterns...') and when ('Use when refactoring code, identifying technical debt, finding opportunities for abstraction, or documenting common patterns'). Includes explicit 'Use when...' clause with multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'refactoring', 'technical debt', 'abstraction', 'patterns', 'duplications', 'codebase', 'directory', 'module'. These are terms developers naturally use when seeking this type of analysis. | 3 / 3 |
Distinctiveness Conflict Risk | While focused on pattern analysis, terms like 'refactoring' and 'technical debt' could overlap with general code review or linting skills. The focus on 'pattern catalogs' and 'reusable templates' helps distinguish it, but some conflict risk remains with other code analysis tools. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a comprehensive framework for code pattern analysis with clear structure and useful output templates. However, it's verbose in places, lacks executable tooling, and misses validation checkpoints for verifying pattern accuracy. The content would benefit from being more concise and providing actual runnable scripts rather than descriptive guidance.
Suggestions
Add a validation step after pattern identification (e.g., 'Review 2-3 detected patterns manually to verify accuracy before generating full catalog')
Provide an executable script or concrete tool commands for pattern detection rather than descriptive heuristics
Reduce verbosity by removing explanations of common patterns Claude already knows (e.g., what API call patterns or error handling look like)
Split detailed template formats and heuristics into separate reference files (e.g., TEMPLATES.md, HEURISTICS.md) and link from the main skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes some unnecessary verbosity, such as explaining what patterns to look for in detail that Claude would already understand. The markdown format examples and category explanations could be tightened. | 2 / 3 |
Actionability | Provides structured guidance with example formats and templates, but lacks fully executable code. The JavaScript example is illustrative rather than a complete, runnable tool. Most content describes what to do rather than providing copy-paste ready implementations. | 2 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced (1-7), but lacks validation checkpoints. For a pattern analysis task that could produce incorrect results, there's no verification step to confirm pattern accuracy or validate findings before generating the final report. | 2 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but it's a monolithic document (~150 lines) that could benefit from splitting detailed templates and heuristics into separate reference files. No external file references are provided. | 2 / 3 |
Total | 8 / 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.
0f00a4f
Table of Contents
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.