reversa-visor

Documents legacy system interfaces from screenshots into structured screen specs and navigation flows.

Updated Aug 14, 2026
One-click install
npx skills add https://github.com/Ruggery/OCR_Cartorio --skill reversa-visor-ruggery
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-visor
Source: https://github.com/Ruggery/OCR_Cartorio/tree/main/.agents/skills/reversa-visor
Command: npx skills add https://github.com/Ruggery/OCR_Cartorio --skill reversa-visor-ruggery

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Legacy systems often lack any documentation of their user interface, making modernization or reimplementation risky and slow. This Skill turns screenshots of a running or retired system into structured interface documentation without requiring the system to be running. ## Core Features & Use Cases - Screen Inventory: Catalogs each screenshot with its purpose, state (loading, empty, filled, error), and usage context. - UI Element Extraction: Documents forms, tables, navigation menus, and feedback elements (modals, messages, confirmations) per screen. - Navigation Flow Mapping: Produces a Mermaid diagram of navigation flows across screens, plus per-unit screen specs mapped to configurable granularity (module, endpoint, use-case, feature). - Use Case: A team modernizing a legacy back-office system sends screenshots of its main screens; the Skill produces an inventory, per-module screen specs, and a navigation flow diagram that feed directly into requirements writing. ## Quick Start Send screenshots of the legacy system's main screens and ask the agent to document the interface from these images.

Frequently Asked Questions about reversa-visor

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

FAQPage Schema
How do I document a legacy system UI from screenshots?▼

Send screenshots of the system's screens to the agent, one at a time or in batches, prioritizing main screens and key flows. The Skill inventories each screen, extracts forms, tables, and navigation elements, and writes structured Markdown specs per unit.

Does the legacy system need to be running to document its interface?▼

No. The Skill works entirely from static screenshots, so the system does not need to be running or accessible. This makes it suitable for retired systems or environments where access is restricted.

What output files does screenshot-based UI documentation produce?▼

It produces a screens.md spec per unit, the original screenshots stored under each unit folder, a global inventory.md listing all screens and their mapped units, and a flow.md with a Mermaid navigation diagram across units.

Can I use this with Claude Code, Cursor, or Gemini CLI?▼

Yes. The Skill declares compatibility with Claude Code, Codex, Cursor, Gemini CLI, and other agents supporting the Agent Skills format, as long as the underlying model supports image inputs.

What happens when a screen maps to more than one specification unit?▼

When the mapping is ambiguous, the Skill asks the user to decide before saving rather than guessing. The mapping follows the granularity setting (module, endpoint, use-case, feature, hybrid, or custom) read from the Reversa configuration files.