agent-analyze-code-quality
Agent skill for analyze-code-quality - invoke with $agent-analyze-code-quality
34
0%
Does it follow best practices?
Impact
94%
1.49xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-analyze-code-quality/SKILL.mdQuality
Discovery
0%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 is essentially just a skill name restated with invocation syntax, providing no meaningful information about capabilities, scope, or when to use it. It fails across all dimensions due to extreme vagueness and lack of any actionable detail or trigger terms.
Suggestions
Replace the label with specific concrete actions, e.g., 'Analyzes code for complexity metrics, code smells, duplication, and style violations across Python, JavaScript, and TypeScript files.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks for code review, static analysis, linting, code quality checks, or wants to identify code smells and technical debt.'
Remove the invocation syntax ('invoke with $agent-analyze-code-quality') from the description and focus on capability and trigger information that helps Claude select the right skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions. 'Analyze code quality' is vague and does not specify what kind of analysis is performed (e.g., linting, complexity metrics, code smells, test coverage). It reads more like a label than a description. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' (beyond a vague label) and 'when should Claude use it.' There is no 'Use when...' clause or any explicit trigger guidance. | 1 / 3 |
Trigger Term Quality | The only potentially relevant term is 'code quality,' which is generic. It lacks natural keywords users might say such as 'lint,' 'code review,' 'code smells,' 'complexity,' 'static analysis,' 'refactor,' or specific language/framework terms. | 1 / 3 |
Distinctiveness Conflict Risk | 'Analyze code quality' is extremely generic and could overlap with any code review, linting, testing, or refactoring skill. There are no distinct triggers or niche identifiers to differentiate it. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is dominated by extensive YAML frontmatter containing non-functional metadata (triggers, hooks, optimization settings, integration configs) that serve no practical purpose for Claude's execution. The actual body content is a shallow, generic list of code quality concepts and a markdown report template, with no concrete commands, executable code, or step-by-step workflow. It reads more like a configuration spec for a hypothetical agent framework than an actionable skill for Claude.
Suggestions
Remove or drastically reduce the YAML frontmatter to only essential metadata; move the body focus to concrete, step-by-step instructions for how to actually perform a code review using available tools (Read, Grep, Glob).
Add executable examples showing specific tool invocations, e.g., using Grep to find long functions, Glob to discover source files, and Read to inspect flagged files, with concrete patterns and thresholds.
Define a clear sequential workflow: 1) discover files, 2) scan for specific patterns, 3) analyze flagged files, 4) compile report—with explicit validation steps between phases.
Remove explanations of well-known concepts (SOLID, DRY, code smells) and instead provide specific detection heuristics and grep patterns that Claude should use during analysis.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The vast majority of the file is YAML frontmatter that is not actionable instruction content—it includes verbose metadata blocks (triggers, capabilities, constraints, hooks, optimization, integration, examples) that Claude cannot execute or use. The actual body content is generic and explains concepts Claude already knows (what code smells are, what SOLID means, what readability means). | 1 / 3 |
Actionability | The body provides no executable code, no concrete commands, and no specific step-by-step instructions. It lists abstract categories (readability, maintainability, etc.) and code smell names without concrete detection logic, thresholds, or tool invocations. The output format template is the only semi-concrete element but is still a static markdown template rather than actionable guidance. | 1 / 3 |
Workflow Clarity | There is no clear multi-step workflow for performing a code quality analysis. The body lists responsibilities and criteria but never sequences them into a process. There are no validation checkpoints, no decision points, and no guidance on how to iterate through files or handle edge cases. | 1 / 3 |
Progressive Disclosure | The content is a monolithic mix of excessive YAML frontmatter and a flat body with no references to supporting files. There is no bundle, no linked documentation, and the YAML metadata (which is not body content) dominates the file while the actual instructional body is thin and unstructured. | 1 / 3 |
Total | 4 / 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
- ruvnet/claude-flow
- Commit
e6dc21f
- 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.