software-engineering-docs

Generate structured software engineering documentation from codebases and existing docs.

Updated Apr 25, 2026
One-click install
npx skills add https://github.com/mnsgrosa/skills --skill software-engineering-docs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: software-engineering-docs
Source: https://github.com/mnsgrosa/skills/tree/main/skills/software-engineering-docs
Command: npx skills add https://github.com/mnsgrosa/skills --skill software-engineering-docs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Generate and maintain structured software engineering documentation for new or existing applications. Use when asked to create, update, or normalize requirements.md, use_cases.md, specification.md, architecture.md, uml.md, or tests.md from source code and existing docs, and when enforcing consistency and domain boundaries (for example, preventing endpoint-level details in high-level requirements).

Core Features & Use Cases

  • Generate documentation sets (requirements.md, use_cases.md, specification.md, architecture.md, uml.md, tests.md) from codebases and existing docs.
  • Enforce a canonical system model with stable IDs (FR-###, NFR-###, UC-###, CON-###) and maintain cross-file consistency.
  • Support full-generation and doc-grounded-retrieval workflows to adapt to missing or existing docs.
  • Use a stepwise workflow: build project context, construct canonical model, then generate and validate docs.

Quick Start

Instruct the system to generate a complete documentation set for a given project by deriving a canonical system model from code and existing docs and producing requirements.md, use_cases.md, specification.md, architecture.md, uml.md, and tests.md.

Frequently Asked Questions about software-engineering-docs

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

FAQPage Schema
How do I generate software engineering documentation from an existing codebase?

To generate software engineering documentation, this Skill derives a canonical system model from source code and existing files, producing structured outputs like requirements.md, architecture.md, and use_cases.md. It enforces cross-file consistency and domain boundaries to ensure reliable, aligned docs.

What is a canonical system model and why is it needed for architecture documentation?

A canonical system model is a unified representation of your application using stable IDs like FR-### and UC-###. It is needed for architecture documentation to maintain cross-file consistency, normalize requirements, and prevent endpoint-level details from appearing in high-level specifications.

How do I normalize requirements and use cases when existing project docs are out of sync?

You normalize requirements and use cases by applying a doc-grounded-retrieval workflow that extracts a canonical system model from existing files. It enforces stable IDs and cross-file consistency to align fragmented documentation with your actual codebase.

Can I generate UML and test cases directly from source code?

Yes, you can generate UML diagrams and test cases directly from source code. The workflow constructs a canonical system model and produces a complete documentation set including uml.md and tests.md to align specifications with implementation.

What is the best way to maintain consistency across multiple software specification files?

The best way to maintain consistency across specification files is by enforcing a canonical system model with stable identifiers. This approach prevents mismatched domain boundaries and keeps requirements, architecture, and use case documents perfectly aligned.

Does this documentation generation approach work for new applications with no existing docs?

Yes, this documentation generation approach works for new applications by using a full-generation workflow. It builds project context from the initial codebase to construct a canonical system model and generate a complete, consistent documentation set from scratch.