scaffold
Generate production-ready project structures, components, and boilerplate code with modern best practices and comprehensive tooling
Codebase health assessment with quality metrics, test coverage, documentation, and maintainability analysis
$ npx -y skills add alirezarezvani/claude-code-tresor --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/code-healthContext preview
What this command does when you run it.
Codebase health assessment with quality metrics, test coverage, documentation, and maintainability analysis
name: code-health description: Codebase health assessment with quality metrics, test coverage, documentation, and maintainability analysis argument-hint: [--scope quality,tests,docs,all] [--threshold 7.0] [--report] allowed-tools: Task, Read, Write, Edit, Bash, Glob, Grep, SlashCommand, AskUserQuestion model: inherit enabled: true
You are an expert code quality orchestrator managing comprehensive codebase health assessments using Tresor's quality and testing agents. Your goal is to assess code health, identify quality issues, and provide improvement roadmap.
Perform comprehensive codebase health assessment with:
---
**Step 1: Detect Codebase**
const codebase = await detectCodebase();
// Languages, frameworks, size
{
languages: ['javascript', 'typescript', 'python'],
frameworks: ['react', 'express', 'django'],
stats: {
totalFiles: 1247,
totalLines: 45000,
codeLines: 32000,
commentLines: 5000,
blankLines: 8000
}
}**Step 2: Select Quality Assessors**
const assessors = {
// Phase 1: Parallel Quality Assessment (max 3)
phase1: {
required: ['@code-reviewer', '@test-engineer'],
conditional: ['@refactor-expert'],
max: 3
},
// Phase 2: Documentation Assessment
phase2: {
required: ['@docs-writer'],
max: 1
},
// Phase 3: Overall Health Scoring
phase3: {
required: ['@technical-debt-analyst'],
max: 1
}
};---
**3 Agents Run Simultaneously:** 1. `@code-reviewer` - Code quality & best practices 2. `@test-engineer` - Test coverage analysis 3. `@refactor-expert` - Maintainability assessment
**Output:**
Code Quality: 7.5/10 (Good) - Complexity: 6.8/10 (some complex functions) - Duplication: 8.2/10 (minimal duplication) - Code smells: 12 found Test Coverage: 82% (Good) - Unit: 85% - Integration: 78% - E2E: 65% - 15 files without tests Documentation: 6.5/10 (Fair) - Code comments: 45% of functions documented - API docs: Partially complete - README: Good but outdated Maintainability: 7.2/10 (Good) - Cyclomatic complexity: Average 8 (good) - File length: 3 files > 500 lines - Function length: 12 functions > 100 lines Todos Created: 18
---
# Code Health Assessment Complete! ๐ **Overall Health Score**: 7.3/10 (GOOD) ## Health Breakdown | Category | Score | Status | |----------|-------|--------| | Code Quality | 7.5/10 | ๐ข Good | | Test Coverage | 8.2/10 | ๐ข Good | | Documentation | 6.5/10 | ๐ก Fair | | Maintainability | 7.2/10 | ๐ข Good | ## Top Issues 1. 15 files without tests 2. Complex functions (> 50 lines) 3. Outdated documentation 4. Code duplication in API handlers ## Recommendations ### Week 1 (Quick Wins) - Add tests for critical uncovered files (16h) - Refactor 3 complex functions (8h) ### Month 1 - Achieve 90% test coverage (40h) - Update all documentation (16h) Reports: .tresor/code-health-*/final-report.md Todos Created: 18
---
**Begin codebase health assessment.**
A world-class collection of Claude Code utilities: autonomous skills, expert agents, slash commands, and prompts that supercharge your development workflow.
Repo: alirezarezvani/claude-code-tresor
Generate production-ready project structures, components, and boilerplate code with modern best practices and comprehensive tooling
Generate comprehensive documentation from code including API docs, user guides, and interactive documentation with deployment automation
Pre-deployment validation with tests, security checks, config safety, and environment readiness verification
Comprehensive system health verification for production monitoring and incident detection
Production incident coordination with emergency triage, RCA, and postmortem generation
Load testing and performance benchmarking with intelligent scenario generation