read-large-md

Extract readable text from oversized markdown files by filtering base64 image lines.

4|Updated Feb 25, 2026

Search Tags:#markdown #grep #pagination #large files #document extraction #base64 images

Ready to run

npx skills add https://github.com/AMindToThink/claude-code-settings --skill read-large-md

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: read-large-md
Source: https://github.com/AMindToThink/claude-code-settings/tree/main/skills/read-large-md
Command: npx skills add https://github.com/AMindToThink/claude-code-settings --skill read-large-md

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you read markdown files that are too large for normal tools because they contain embedded base64 images on long lines.

Core Features & Use Cases

Text-Only Extraction: Filters out image payload lines so you can access the readable markdown content.
Chunked Reading: Supports paging through very large files in manageable sections.
Targeted Section Lookup: Lets you jump straight to headers or keywords when you only need part of a document.
Use Case: A Google Docs export with inline images can be inspected for its text without loading the massive image data into context.

Quick Start

Use the read-large-md skill to extract the readable text from a large markdown file while skipping embedded base64 image lines.

Frequently Asked Questions about read-large-md

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

FAQPage Schema

How do I read a large markdown file that fails to load because of base64 images?▼

To read a large markdown file blocked by base64 images, you filter out image payload lines using Grep. This extracts readable text and paginates sections without loading binary image data into context.

What is the best way to extract text from a Google Docs markdown export with inline images?▼

The best way to extract text from a Google Docs markdown export with inline images is line filtering. You skip image payload lines and paginate text sections to inspect readable content without loading massive image data.

Can I paginate through oversized markdown documents without exceeding tool limits?▼

Yes, you can paginate through oversized markdown documents without exceeding tool limits by using chunked reading. This approach supports paging through very large files in manageable text sections while skipping embedded base64 image lines.

Why does standard reading fail on markdown files with single-line image payloads?▼

Standard reading fails on markdown files with single-line image payloads because embedded base64 images bloat the file size massively. This causes the document to exceed standard tool limits and requires line filtering to bypass binary image data.

How do I jump to a specific section in a huge markdown file without loading the entire document?▼

To jump to a specific section in a huge markdown file without loading the entire document, you use targeted section lookup. This technique navigates straight to headers or keywords, extracting only the needed readable text while skipping base64 image lines.