analyze-system

Extract domain concepts, actors, roles, permissions, and domain-code mappings from design documents and source code.

8|Updated Dec 25, 2025
One-click install
npx skills add https://github.com/wfukatsu/refactoring-agent-for-claude-code --skill analyze-system
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: analyze-system
Source: https://github.com/wfukatsu/refactoring-agent-for-claude-code/tree/main/.claude/skills/analyze-system
Command: npx skills add https://github.com/wfukatsu/refactoring-agent-for-claude-code --skill analyze-system

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams quickly understand an existing system by extracting ubiquitous language, actors, roles, permissions, and the domain-code mappings from documentation and code.

Core Features & Use Cases

  • Ubiquitous Language Extraction: derive business terms from design docs, ER models, and source comments.
  • Actor/Role/Permission Mapping: identify stakeholders, access levels, and authorization points.
  • Domain-Code Mapping: connect domain concepts to code entities and packages to enable traceability.
  • Use Case: onboarding a new team member by generating a shared understanding of the system from current artifacts.

Quick Start

Run the analyze-system tool on your project path to generate analysis reports in reports/01_analysis/.

Frequently Asked Questions about analyze-system

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract ubiquitous language from existing source code and design documents?

To extract ubiquitous language from source code and design documents, you apply the analyze-system tool to your project path. It derives business terms from ER models and comments, saving the extracted domain concepts to reports/01_analysis.

What is the best way to map actor roles and permissions across a legacy codebase?

Mapping actor roles and permissions across a legacy codebase is done by invoking analyze-system on the target path. It identifies stakeholders, access levels, and authorization points from existing artifacts to generate a structured permissions report.

Can I generate domain-code mappings for an entire project directory?

Yes, you can generate domain-code mappings for an entire project directory by running analyze-system with the target path. It connects domain concepts to code entities and packages, producing traceability artifacts in reports/01_analysis.

Does ubiquitous language extraction work with both design docs and source comments?

Ubiquitous language extraction works with both design docs and source comments. The analysis applies across documentation and source code to derive business terms, producing a shared vocabulary for onboarding and downstream reports.

What format do the extracted domain concepts and actor roles get saved in?

Extracted domain concepts and actor roles are saved as artifacts in the reports/01_analysis directory. These outputs include ubiquitous language, domain-code mappings, and actor/role/permission structures for downstream consumption.