read-special-images

Extracts text and content from oversized or text-dense images via deterministic overlapping tiles.

Updated Sep 16, 2026
One-click install
npx skills add https://github.com/Military-Veteran-Team-LPT-Realty/mvt-manus-public-skills --skill read-special-images-military-veteran-team-lpt-realty
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: read-special-images
Source: https://github.com/Military-Veteran-Team-LPT-Realty/mvt-manus-public-skills/tree/main/skills/read-special-images
Command: npx skills add https://github.com/Military-Veteran-Team-LPT-Realty/mvt-manus-public-skills --skill read-special-images-military-veteran-team-lpt-realty

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, and includes scripts (resource) components.

What problem does it solve? Whole-image previews of very tall, wide, high-resolution, or text-dense images get downscaled, making text unreadable and causing hallucinated content. This Skill tiles such images into readable overlapping crops so every region is inspected at full scale. ## Core Features & Use Cases - Dimension Inspection: Reads width, height, and aspect ratio from the original file before deciding whether tiling is needed. - Deterministic Tiling: Splits images into overlapping tiles in vertical, horizontal, or grid mode and writes a manifest.json with reading order. - Overlap Reconciliation: Guides merging of tile content by deduplicating overlap regions and flagging unresolved OCR conflicts instead of guessing. - Use Case: Given a long scrolling screenshot of a chat thread or a panoramic diagram, tile it with the script, read each tile in manifest order, and produce a faithful transcription with uncertainty clearly marked. ## Quick Start Use the read-special-images skill to extract all text from this long screenshot without guessing any unreadable parts.

Frequently Asked Questions about read-special-images

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

FAQPage Schema
How do I read text from a very long screenshot?

Slice the screenshot into overlapping vertical tiles with the slice_image.py script, then read each tile in manifest order top-to-bottom. Reconcile the 12% overlap between adjacent tiles to remove duplicates without dropping boundary text.

How to OCR a high-resolution image without losing detail?

Inspect the image dimensions first, then tile it into smaller crops so each region is viewed at full resolution. Images over 4096 pixels on a side or over 16 million pixels are tiled automatically in grid mode.

When should an image be split into tiles for reading?

Tile when the aspect ratio is at least 2:1, either side exceeds 4096 pixels, total pixels exceed 16 million, or text remains unreadable in the preview. Ordinary readable images should not be tiled.

Does the image tiling script require any Python libraries?

The script requires Pillow for image loading, EXIF orientation correction, and cropping. If Pillow is unavailable, it exits with a message rather than installing dependencies automatically.

What are the limitations of tiling images for OCR?

Tiling cannot recover content that is unreadable in every tile, and upscaling to guess is explicitly disallowed. Unresolved OCR conflicts between overlapping tiles are flagged, and only verified portions are reported.