code-pattern-extractor
Identifies recurring structural patterns in a codebase — idioms, copy-paste clones, homegrown abstractions — and characterizes each as a reusable template. Use when learning a codebase's conventions, when hunting for copy-paste that should be a function, or when documenting how this team does things.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill code-pattern-extractor100
Quality
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Discovery
100%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 excels across all dimensions. It uses third person voice correctly, provides specific concrete actions, includes natural trigger terms developers would use, and has an explicit 'Use when...' clause with multiple clear scenarios. The description carves out a distinct niche around pattern identification and convention documentation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'identifies recurring structural patterns', 'idioms, copy-paste clones, homegrown abstractions', and 'characterizes each as a reusable template'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Identifies recurring structural patterns...characterizes each as a reusable template') AND when ('Use when learning a codebase's conventions, when hunting for copy-paste that should be a function, or when documenting how this team does things'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'codebase', 'conventions', 'copy-paste', 'function', 'documenting', 'patterns', 'idioms', 'abstractions'. Good coverage of terms developers naturally use when discussing code patterns. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on pattern identification and convention documentation. The specific focus on 'recurring structural patterns', 'copy-paste clones', and 'homegrown abstractions' distinguishes it from general code analysis or refactoring skills. | 3 / 3 |
Total | 12 / 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 excellent skill that efficiently teaches pattern extraction with concrete algorithms, real code examples, and clear decision frameworks. The content respects Claude's intelligence while providing genuinely useful domain-specific knowledge about clone detection normalization and idiom vs clone distinction. The worked example demonstrating extraction from 23 copies to a shared helper is particularly effective.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is dense with actionable information and avoids explaining concepts Claude already knows. Every section earns its place—tables are used efficiently, examples are minimal but complete, and there's no padding or unnecessary context about what patterns are. | 3 / 3 |
Actionability | Provides concrete, executable guidance throughout: specific normalization algorithm steps, real code examples showing before/after extraction, clear output format template, and actionable tables distinguishing idiom from clone. The worked example is copy-paste demonstrable. | 3 / 3 |
Workflow Clarity | The four-step clone-finding process (tokenize → normalize → hash → group) is clearly sequenced. The skill provides explicit decision criteria (the idiom vs clone table) and clear output expectations. The 'Do not' section serves as validation guidance for avoiding common mistakes. | 3 / 3 |
Progressive Disclosure | Well-organized with clear sections progressing from concept (three pattern types) to technique (finding clones/idioms) to worked example to decision criteria to output format. Cross-references to related skills (code-refactoring-assistant, code-smell-detector) are appropriately signaled without deep nesting. | 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.
- 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.