code-smell-detector
Identifies code smells — structural patterns that correlate with maintainability problems — and explains why each matters in context. Use when reviewing a PR for structural quality, when the user asks what's wrong with a piece of code that isn't buggy, or when prioritizing refactoring targets.
Install with Tessl CLI
npx tessl i github:santosomar/general-secure-coding-agent-skills --skill code-smell-detector100
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 an excellent skill description that clearly articulates what the skill does (identify code smells and explain their contextual importance) and provides explicit, varied trigger conditions. The description uses appropriate third-person voice, includes natural developer terminology, and carves out a distinct niche separate from bug-finding or general code review skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: 'Identifies code smells', 'structural patterns that correlate with maintainability problems', and 'explains why each matters in context'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('Identifies code smells...explains why each matters') AND when ('Use when reviewing a PR for structural quality, when the user asks what's wrong with a piece of code that isn't buggy, or when prioritizing refactoring targets'). Explicit 'Use when...' clause with multiple trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'code smells', 'PR', 'structural quality', 'what's wrong with', 'not buggy', 'refactoring targets'. Good coverage of terms developers naturally use when seeking this type of analysis. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on code smells and structural quality issues, distinct from general code review, bug finding, or formatting skills. The phrase 'code that isn't buggy' explicitly differentiates from debugging 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 exemplary skill that demonstrates expert-level content design. It provides a comprehensive smell catalog with concrete detection heuristics, prioritization methodology tied to real metrics (git churn), false-positive suppression rules, and a worked example that ties everything together. The skill respects Claude's intelligence while adding genuine domain expertise about when smells matter and when they don't.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The catalog table is dense with information, the worked example demonstrates rather than explains, and there's no padding about what code smells are or basic programming concepts Claude already knows. | 3 / 3 |
Actionability | Provides concrete detection heuristics ('>40 lines, >3 levels of nesting'), specific git commands for churn analysis, a complete worked example with real Python code, and a precise output format template. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | Clear workflow: detect smells using catalog → rank by churn × severity using git command → apply false-positive suppression checks → output in specified format → hand off to code-refactoring-assistant. The prioritization logic is explicit and the handoff to another skill provides a validation checkpoint. | 3 / 3 |
Progressive Disclosure | Well-structured with clear sections (catalog, ranking, false-positives, worked example, do-nots, output format). References external skill (code-refactoring-assistant) appropriately. Content is appropriately sized for a single file without needing external references. | 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.