reversa-visor

Extract screens, UI components, navigation flows, and states from screenshots.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/afsjr/secretaria_escola_csm --skill reversa-visor-afsjr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reversa-visor
Source: https://github.com/afsjr/secretaria_escola_csm/tree/main/.agents/skills/reversa-visor
Command: npx skills add https://github.com/afsjr/secretaria_escola_csm --skill reversa-visor-afsjr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the problem of documenting a legacy system’s user interface when you cannot (or do not want to) run the system, by turning screenshots into a structured map of screens, components, navigation flows, and states.

Core Features & Use Cases

  • Screenshot-driven UI documentation: Inventories each provided screen with its purpose, state (loading/empty/filled/error/confirmation), and user entry context.
  • Component extraction: Identifies forms (fields, validations, buttons), tables/listings (columns, per-row actions, filters/pagination), navigation elements (menus, breadcrumbs, links), and feedback mechanisms (messages, modals, tooltips).
  • Navigation and state mapping: Produces navigation flow relationships across screens and distinguishes the same screen in different states; maps each screen to the appropriate unit using the configured granularity and feature/module/endpoints.
  • Output organization for discovery: Saves per-unit screenshots and generates screens.md plus global inventory.md and a Mermaid flow.md that links units.

Quick Start

Send screenshots of the system screens you want documented (start with the main screens and key navigation flows).

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 application UI from screenshots without running the system?

You can document a legacy application UI from screenshots by extracting screens, components, and navigation flows directly from the images. This process builds a structured screen inventory without needing the system running.

What is the best way to map navigation flows and UI states from existing screenshots?

Mapping navigation flows and UI states from screenshots involves analyzing the images to identify relationships across screens and distinguish variations like loading, empty, or error states. This generates a visual flow map.

Can I extract forms and tables from legacy system screenshots for documentation?

Yes, you can extract forms and tables from legacy system screenshots. The process identifies form fields, validations, table columns, and per-row actions to produce a structured component inventory.

Do I need the application running to inventory UI components and states?

No, you do not need the application running to inventory UI components and states. The analysis reads directly from provided screenshots to reverse-engineer the interface without runtime access.

What output formats are generated when reverse engineering UI from screenshots?

Reverse engineering UI from screenshots generates per-unit screenshots, a screens.md file for detailed documentation, a global inventory.md, and a Mermaid flow.md linking the mapped units.