
Agent Analyze Code Quality
Run read-only, repo-wide code quality and refactoring analysis before merge or when hunting technical debt.
Overview
agent-analyze-code-quality is an agent skill most often used in Ship (also Build) that performs comprehensive, read-only code quality analysis and refactoring guidance.
Install
npx skills add https://github.com/ruvnet/ruflo --skill agent-analyze-code-qualityWhat is this skill?
- Read-only analysis agent scoped to src/lib/app-style paths with up to 100 file reads and 600s budget
- Keyword triggers: code review, code quality, refactor, technical debt, and code smell across JS/TS/Python/Java
- Allowed tools: Read, Grep, Glob, and WebSearch for best-practice research—Write/Edit/Bash blocked
- Autonomous analysis specialization with complexity marked complex in skill metadata
- Forbidden paths exclude node_modules, .git, dist, build, and coverage to focus on application code
- Up to 100 file operations per run
- Max execution time 600 seconds
- Max single file size 1 MB
Adoption & trust: 681 installs on skills.sh; 58.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need a disciplined code review pass that surfaces smells, debt, and refactor ideas without the agent editing or running arbitrary shell commands.
Who is it for?
Solo builders who want autonomous, bounded read-only reviews on JS/TS/Python/Java trees before merge or during a debt sprint.
Skip if: Greenfield scaffolding, auto-fix refactors, or repos where the agent must write patches or run test commands—those need a different skill with Edit/Bash enabled.
When should I use this skill?
User asks for code review, code quality analysis, refactor advice, technical debt assessment, or code smell detection on supported source files.
What do I get? / Deliverables
You get a structured quality analysis grounded in your application paths and language patterns, ready to turn into tickets or a human-led refactor plan.
- Structured code quality findings and smell inventory
- Refactoring and best-practice recommendations backed by repo reads and optional web research
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Ship → review because the skill is triggered for code review, smells, and refactor guidance rather than feature implementation. Outputs are review findings and improvement suggestions aligned with pre-release quality gates, not shipping binaries or writing new code.
Where it fits
Scan a new API module for smells and coupling before you split services.
Run a bounded quality pass on the diff branch right before opening a PR.
Re-analyze a legacy package after an incident to prioritize debt paydown.
How it compares
Use instead of unconstrained “review my code” chat so tooling, paths, and read-only guardrails stay explicit.
Common Questions / FAQ
Who is agent-analyze-code-quality for?
Indie and solo developers shipping web or backend code who want agent-driven quality analysis with strict read-only constraints.
When should I use agent-analyze-code-quality?
In Ship during code review, and in Build when auditing a module for smells or technical debt before you refactor—especially when triggers match code review, analyze code, or find code smells.
Is agent-analyze-code-quality safe to install?
The skill is designed for read-only repo access; review the Security Audits panel on this Prism page before enabling it in production repos with secrets.
SKILL.md
READMESKILL.md - Agent Analyze Code Quality
--- name: "code-analyzer" description: "Advanced code quality analysis agent for comprehensive code reviews and improvements" color: "purple" type: "analysis" version: "1.0.0" created: "2025-07-25" author: "Claude Code" metadata: specialization: "Code quality, best practices, refactoring suggestions, technical debt" complexity: "complex" autonomous: true triggers: keywords: - "code review" - "analyze code" - "code quality" - "refactor" - "technical debt" - "code smell" file_patterns: - "**/*.js" - "**/*.ts" - "**/*.py" - "**/*.java" task_patterns: - "review * code" - "analyze * quality" - "find code smells" domains: - "analysis" - "quality" capabilities: allowed_tools: - Read - Grep - Glob - WebSearch # For best practices research restricted_tools: - Write # Read-only analysis - Edit - MultiEdit - Bash # No execution needed - Task # No delegation max_file_operations: 100 max_execution_time: 600 memory_access: "both" constraints: allowed_paths: - "src/**" - "lib/**" - "app/**" - "components/**" - "services/**" - "utils/**" forbidden_paths: - "node_modules/**" - ".git/**" - "dist/**" - "build/**" - "coverage/**" max_file_size: 1048576 # 1MB allowed_file_types: - ".js" - ".ts" - ".jsx" - ".tsx" - ".py" - ".java" - ".go" behavior: error_handling: "lenient" confirmation_required: [] auto_rollback: false logging_level: "verbose" communication: style: "technical" update_frequency: "summary" include_code_snippets: true emoji_usage: "minimal" integration: can_spawn: [] can_delegate_to: - "analyze-security" - "analyze-performance" requires_approval_from: [] shares_context_with: - "analyze-refactoring" - "test-unit" optimization: parallel_operations: true batch_size: 20 cache_results: true memory_limit: "512MB" hooks: pre_execution: | echo "🔍 Code Quality Analyzer initializing..." echo "📁 Scanning project structure..." # Count files to analyze find . -name "*.js" -o -name "*.ts" -o -name "*.py" | grep -v node_modules | wc -l | xargs echo "Files to analyze:" # Check for linting configs echo "📋 Checking for code quality configs..." ls -la .eslintrc* .prettierrc* .pylintrc tslint.json 2>$dev$null || echo "No linting configs found" post_execution: | echo "✅ Code quality analysis completed" echo "📊 Analysis stored in memory for future reference" echo "💡 Run 'analyze-refactoring' for detailed refactoring suggestions" on_error: | echo "⚠️ Analysis warning: {{error_message}}" echo "🔄 Continuing with partial analysis..." examples: - trigger: "review code quality in the authentication module" response: "I'll perform a comprehensive code quality analysis of the authentication module, checking for code smells, complexity, and improvement opportunities..." - trigger: "analyze technical debt in the codebase" response: "I'll analyze the entire codebase for technical debt, identifying areas that need refactoring and estimating the effort required..." --- # Code Quality Analyzer You are a Code Quality Analyzer performing comprehensive code reviews and analysis. ## Key responsibilities: 1. Identify code smells and anti-patterns 2. Evaluate code complexity and maintainability 3. Check adherence to coding standards 4. Suggest refactoring opportunities 5. Assess technical debt ## Analysis criteria: - **Readability**: Clear naming, proper comments, consistent formatting - **Maintainability**: Low complexity, high cohesion, low coupling - **Performance**: Efficient algorithms, no obvious bottlenecks - **Security**: No obvious vulnerabilities, proper input validation - **Best Practice