reversa-writer

Name: reversa-writer
Availability: InStock
Author: Sandeco

Generate requirements.md, design.md, and tasks.md specifications from Reversa state and config artifacts.

1.5k|383|Updated Apr 26, 2026

Search Tags:#requirements #legacy systems #specification generation #reverse documentation #AI agent engineering #unit-based docs #design contracts

Ready to run

npx skills add https://github.com/sandeco/reversa --skill reversa-writer-sandeco

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: reversa-writer
Source: https://github.com/sandeco/reversa/tree/main/agents/reversa-writer
Command: npx skills add https://github.com/sandeco/reversa --skill reversa-writer-sandeco

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Reversa-writer turns extracted legacy system knowledge into operational, traceable specifications so AI coding agents can safely evolve existing software with fidelity.

Core Features & Use Cases

Executable spec generation for legacy units: Produces per-unit folders with canonical files (requirements, design, tasks) aligned to Reversa’s granularity settings.
Organization-aware unit layout: Creates unit structure by module, endpoint, use-case, feature, or custom folders using Reversa context outputs like surface.json.
Controlled scope and guardrails: Reads Reversa state/config, checks whether specs organization is decided, and follows a “never generate everything at once” workflow.

Quick Start

Run reversa-writer after Reversa has generated the prior context and extracted knowledge, so it can write requirements.md, design.md, and tasks.md for the selected units into 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 executable specifications from legacy system knowledge?▼

Executable specifications are generated from extracted legacy knowledge by creating unit-scoped folders containing canonical requirements.md, design.md, and tasks.md files. This process reads extracted knowledge artifacts and converts them into operational, traceable specifications.

What is reverse documentation for legacy systems and when do I need it?▼

Reverse documentation turns extracted legacy system knowledge into operational specifications so AI coding agents can safely evolve existing software. You need it when you must modernize legacy systems but lack original specifications for safe modifications.

How do I create unit-scoped specifications for different module granularities?▼

Unit-scoped specifications are created by organizing output into module, endpoint, use-case, feature, hybrid, or custom granularity folders. The process reads surface.json modules and features to enumerate units and generates aligned requirements, design, and tasks files.

Do I need prior context files before generating reverse engineering documentation?▼

Prior context files are required before generating documentation because the process reads .reversa/state.json and .reversa/config.toml for configuration. It must run after Reversa has generated prior context and extracted knowledge to produce accurate specifications.

Can I generate all legacy system specifications at once during reverse engineering?▼

Generating all legacy system specifications at once is intentionally prevented by controlled scope guardrails. The workflow follows a never generate everything at once approach, checking Reversa state and config to process only selected units at a time.