Agent skill
repo-analyzer
Code repository analysis and technical documentation generation skill
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/data/repo-analyzer
SKILL.md
Repo Analyzer Skill
A comprehensive code repository analysis and technical documentation generation skill that scans repositories and generates detailed summary reports.
Purpose
This skill analyzes code repositories to generate comprehensive technical documentation including:
- Repository overview and purpose
- Directory structure and responsibilities
- Technology stack and dependencies
- Core modules and business domains
- Key execution workflows
- Architecture design and extension patterns
- Onboarding guidance
- Risk analysis and technical debt
When to Use This Skill
Use this skill when you need to:
- Understand a new codebase quickly
- Generate technical documentation for a repository
- Analyze repository architecture and dependencies
- Create onboarding guides for new developers
- Assess technical debt and maintenance risks
How It Works
The skill performs an 8-step analysis:
- Repository Global Scan - Scans directory structure, identifies languages, counts files
- Project Positioning - Infers project purpose from README, directory names, dependencies
- Directory Structure Mapping - Analyzes key directory responsibilities and relationships
- Tech Stack Analysis - Parses dependency files, analyzes technology choices
- Core Module Abstraction - Identifies core modules and business boundaries
- Execution Flow Analysis - Traces program startup and typical execution paths
- Onboarding Path Generation - Creates safe modification points and reading order
- Risk Assessment - Identifies potential maintenance risks and technical debt
Usage
Basic Usage
python repo_analyzer.py /path/to/repository
With Output File
python repo_analyzer.py /path/to/repository --output report.md
With Custom Depth
python repo_analyzer.py /path/to/repository --depth 3
Parameters
| Parameter | Description | Default |
|---|---|---|
repository_path |
Path to the repository to analyze | Required |
--output |
Output file path for the report | repo_analysis_report.md |
--depth |
Directory scanning depth | 2 |
--include-risks |
Include risk assessment section | true |
--verbose |
Enable verbose logging | false |
Output Format
The skill generates a comprehensive Markdown report with the following sections:
- Repository Overview - Project type, purpose, scale, complexity
- Project Structure - Core directory responsibilities and relationships
- Technology Stack - Core frameworks, infrastructure, middleware
- Core Modules & Business Domains - Key business modules and collaboration patterns
- Key Execution Workflows - Program startup and typical request paths
- Architecture Design - Architectural style, design patterns, extension paths
- Quick Start Guide - Recommended reading order, safe modification points
- Risk Points & Considerations - Potential maintenance risks and pitfalls
Installation
Project-Level Installation
# Copy skill to project .claude directory
cp -r generated-skills/repo-analyzer .claude/skills/
User-Level Installation
# Copy skill to user .claude directory
cp -r generated-skills/repo-analyzer ~/.claude/skills/
Files
repo_analyzer.py- Main analysis scriptrequirements.txt- Python dependenciesSKILL.md- This documentation fileexamples/- Example analysis reports
Dependencies
- Python 3.8+
pyyaml- For parsing YAML configuration filestoml- For parsing TOML configuration fileschardet- For file encoding detection
Examples
Analyze Current Repository
python repo_analyzer.py .
Generate Report for Specific Path
python repo_analyzer.py /projects/my-app --output my_analysis.md
Analyze with Custom Settings
python repo_analyzer.py /path/to/repo --depth 3 --include-risks false --verbose true
Limitations
- Analysis is based on static code structure, not runtime behavior
- Business logic inference is limited to code organization patterns
- Dependency analysis requires standard package manager files
- Complex monorepos may require deeper scanning depth
Best Practices
- Start with default settings - Use depth=2 for most repositories
- Review inferred information - Always validate inferred project purposes
- Customize for complex repos - Increase depth for deeply nested structures
- Combine with manual review - Use the report as a starting point for deeper analysis
Troubleshooting
Common Issues
- Permission errors - Ensure read access to the repository directory
- Encoding issues - The skill uses chardet to detect file encodings
- Missing dependencies - Install required packages from requirements.txt
- Large repositories - May take longer to process; consider increasing timeout
Debug Mode
Enable verbose logging for detailed processing information:
python repo_analyzer.py /path/to/repo --verbose true
Related Skills
code-reviewer- For detailed code quality analysisarchitecture-validator- For architectural pattern validationdependency-auditor- For security vulnerability scanning
Contributing
To contribute to this skill:
- Fork the repository
- Create a feature branch
- Implement your changes
- Add tests if applicable
- Submit a pull request
License
This skill is released under the MIT License.
Changelog
v1.0.0
- Initial release with 8-step analysis framework
- Support for multiple dependency file formats
- Markdown report generation
- Configurable scanning depth
Note: This skill generates documentation based on code structure analysis. Always validate the generated insights with domain experts and actual code behavior.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?