code2systemdoc

Convert source code into architecture documents with PlantUML sequence diagrams.

1|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/eatbreads/.agents --skill code2systemdoc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: code2systemdoc
Source: https://github.com/eatbreads/.agents/tree/main/skills/code2systemdoc
Command: npx skills add https://github.com/eatbreads/.agents --skill code2systemdoc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Convert unfamiliar source code into a clear, narratable system model and interview-ready architecture document so engineers can quickly understand end-to-end behavior and design tradeoffs.

Core Features & Use Cases

  • Canonical flow reconstruction: identify entrypoints, orchestration, and core execution paths with a high-signal caller-to-callee map.
  • Mechanism and responsibility extraction: summarize module responsibilities, state/IO models, reliability hooks, and 3–8 high-leverage function explanations.
  • UML and interview framing: produce a PlantUML sequence diagram and interview-style one-liner, 30s/2min answers, and follow-up Q&A for design reviews.

Quick Start

Convert the repository at /path/to/repo into a narratable system model with a PlantUML sequence diagram and interview-ready explanation.

Frequently Asked Questions about code2systemdoc

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

FAQPage Schema
How do I generate architecture documentation from source code?

Generating architecture documentation from source code involves reconstructing canonical flows and extracting module responsibilities to produce a narratable system model with PlantUML sequence diagrams and interview-ready explanations.

What is the best way to create a PlantUML sequence diagram from an existing codebase?

The best way to create a PlantUML sequence diagram from an existing codebase is to identify entrypoints and orchestration paths, mapping high-signal caller-to-callee relationships to visualize core execution flows.

Can I extract module responsibilities and core execution paths for a system design interview?

You can extract module responsibilities and core execution paths to generate interview-ready architecture explanations, including one-liner, 30-second, and 2-minute answers alongside follow-up Q&A for design reviews.

Does code analysis for architecture reconstruction work on a single file or an entire repository?

Code analysis for architecture reconstruction applies to a single file, module, or repository, producing module summaries, state and IO models, and reliability hooks alongside canonical flow maps.

How to analyze unfamiliar source code to understand design tradeoffs and reliability hooks?

To analyze unfamiliar source code for design tradeoffs, extract module responsibilities, state and IO models, and reliability hooks while distinguishing observed behavior from inferred claims.