document-vision-reader

Community

Convert rendered files to visual evidence.

AuthorLaiTszKin
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Convert rendered non-plain-text files into temporary screenshots and answer the user's requests from the visible content, ensuring you rely on visual evidence rather than unreliable text extraction.

Core Features & Use Cases

  • Create a dedicated temporary screenshot workspace and render only the necessary pages or regions.
  • Inspect screenshots as images to derive answers, summaries, or field lookups from what is visually shown.
  • Clean up temporary artifacts automatically after the answer is prepared, unless the user asks to keep them.

Quick Start

Use document-vision-reader to inspect a non-plain-text file by capturing its rendered pages as screenshots and answering from the visible content.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: document-vision-reader
Download link: https://github.com/LaiTszKin/apollo-toolkit/archive/main.zip#document-vision-reader

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.