reversa-writer

Generate traceable requirements.md, design.md, and tasks.md per unit from Reversa state.

Updated May 13, 2026
One-click install
npx skills add https://github.com/cliffthelin/AXiomEngine --skill reversa-writer-cliffthelin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reversa-writer
Source: https://github.com/cliffthelin/AXiomEngine/tree/main/skills/reversa/reversa-writer
Command: npx skills add https://github.com/cliffthelin/AXiomEngine --skill reversa-writer-cliffthelin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Reversa-writer transforms extracted legacy knowledge into formal, traceable specifications that an AI agent can use to reimplement functionality without needing the original code.

Core Features & Use Cases

  • Folder-per-unit contract generation: Produces per-unit output with requirements.md, design.md, and tasks.md in the configured output folder.
  • Granularity-aware unit structure: Generates specs by module, endpoint, use-case, hybrid module+use-cases, feature, or custom folders based on config.toml and surface.json.
  • Controlled output completeness: Conditionally adds optional artifacts such as contracts.md, flows.md, edge-cases.md, decisions.md, and questions.md according to doc_level and discovered context.

Quick Start

Run reversa-writer after Reversa extraction artifacts are present so it reads .reversa/state.json, .reversa/config.toml (and config.user.toml if present), and .reversa/context/surface.json, then generates unit specification folders under the configured output_folder.

Frequently Asked Questions about reversa-writer

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

FAQPage Schema
How do I generate traceable operational specifications from legacy code?

To generate traceable operational specifications from legacy code, reversa-writer reads extracted state and context files, then produces per-unit folders containing requirements.md, design.md, and tasks.md for AI-driven reimplementation.

What is folder-per-unit spec generation for reverse engineering?

Folder-per-unit spec generation is an approach where each module, endpoint, or use-case gets its own output folder containing structured requirements, design, and task documents, enabling isolated and traceable analysis of legacy systems.

How do I control documentation completeness when generating specs for legacy modules?

You control documentation completeness by setting the doc_level parameter, which conditionally adds optional artifacts like contracts.md, flows.md, edge-cases.md, decisions.md, and questions.md alongside the core spec files.

Can I generate requirements and design docs by feature or use-case instead of module?

Yes, you can generate specifications by module, endpoint, use-case, hybrid structures, features, or custom folders, with the granularity governed by your config.toml and surface.json configuration files.

Do I need Reversa state files to generate operational specs?

Yes, you need Reversa state files to generate operational specs. The tool requires .reversa/state.json, .reversa/config.toml, and .reversa/context/surface.json to determine unit scope, language, and output configuration.

Why use traceable specifications for legacy modernization?

Traceable specifications allow an AI agent to reimplement legacy functionality without accessing the original code by providing formal, structured requirements and design documents that map directly to extracted system knowledge.