reversa-visor

Documents legacy system interfaces from screenshots by extracting components, layouts, and navigation flows.

Updated Mar 23, 2026
One-click install
npx skills add https://github.com/Helcio-Nogueira/Painel_Inteligente_Hackaton_2026 --skill reversa-visor-helcio-nogueira
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: reversa-visor
Source: https://github.com/Helcio-Nogueira/Painel_Inteligente_Hackaton_2026/tree/main/.agents/skills/reversa-visor
Command: npx skills add https://github.com/Helcio-Nogueira/Painel_Inteligente_Hackaton_2026 --skill reversa-visor-helcio-nogueira

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Documenting the user interface of a legacy system is slow and error-prone when the system cannot be run or its source code is unavailable. This Skill turns user-provided screenshots into structured interface documentation without requiring the system to be running. ## Core Features & Use Cases - Screen Inventory: Catalogs each screenshot with its name, purpose, state (loading, empty, filled, error), and usage context. - Element Extraction: Identifies forms, tables, navigation menus, and feedback elements (modals, messages, tooltips) from images. - Flow and State Mapping: Maps navigation flows between screens in Mermaid and compares the same screen across different states. - Unit Mapping: Assigns each screen to a specification unit based on configurable granularity (module, endpoint, use-case, feature, hybrid, or custom). - Use Case: A team reverse-engineering a legacy ERP sends screenshots of its main screens; the Skill produces per-unit screen specs, a global inventory, and a Mermaid navigation flow diagram. ## Quick Start Send screenshots of the legacy system's main screens and ask the agent to document the interface, mapping each screen to its specification unit.

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 without access to the running system?▼

Provide screenshots of the system's screens to the Skill, which extracts components, layouts, states, and navigation flows from the images. It generates per-unit screen specifications, a global inventory, and a Mermaid flow diagram without executing the system.

How are screenshots mapped to specification units?▼

Each screen is mapped to a unit based on the granularity setting in the [specs] config section: module, endpoint, use-case, hybrid, feature, or custom folders. When mapping is ambiguous between two units, the Skill asks the user before saving.

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

Per unit it saves the original screenshots under screenshots/ and a screens.md spec file. Globally it creates ui/inventory.md listing all screens with their units and ui/flow.md with a Mermaid navigation diagram.

Does this Skill work with any AI agent or model?▼

It requires an agent compatible with Agent Skills and a model with image support, since screenshots must be visually analyzed. It declares compatibility with Claude Code, Codex, Cursor, and Gemini CLI.

What happens if I send the same screenshot twice?▼

The Skill follows a non-destructive directive and never overwrites existing files. Duplicate screens are saved with a numeric suffix, such as tela.png and tela-2.png.