KyrieCheungYep GitHub avatar

ky-markdown-rebuilder

KyrieCheungYep

A document-reconstruction skill for Codex, Claude Code, and Antigravity that converts visually complex PDFs, slide decks, scans, and reports into page-aligned, validated Markdown using text extraction, page rendering, visual inspection, and automated output checks.

Stars

120

7-day growth

No data

Forks

15

Open issues

0

License

No data

Last updated

2026-07-11

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It goes beyond plain text extraction by combining per-page visual inspection, structured reconstruction, and a quality contract that blocks delivery on format drift, broken links, or missing pages — a rare level of rigor in document-to-Markdown tools.

Who it is for

  • Developers who use AI coding agents (Codex, Claude Code) to process documents
  • Technical writers and content producers needing reliable Markdown from complex source files
  • Researchers or analysts dealing with scanned books, reports, or slide decks

Use cases

  • Rebuilding a dense PDF report into per-page Markdown with preserved tables and diagrams
  • Converting a visual-heavy sales deck into a deep-visual Markdown with original-resolution checks
  • Transcribing a scanned book or archival document into 1:1 Markdown tables without layout commentary

Strengths

  • Uses per-page original-resolution visual inspection rather than thumbnail guesses
  • Provides multiple output modes (fast, page-aligned, deep-visual, transcribe) for different document types
  • Includes a preflight script to verify required tools (pdftoppm, soffice, tesseract, etc.) before use
  • Enforces a quality contract with automated checks for page continuity, source lines, link validity, and table integrity

Considerations

  • Requires external dependencies like pdftoppm, soffice, tesseract, and Python libraries — not self-contained
  • Not designed for simple plain text or unstructured Markdown where direct conversion is faster
  • The tool is a skill for specific AI agents (Codex, Claude Code, Antigravity), not a standalone application

README quick start

安装

Description

A Codex / Claude Code skill for rebuilding visually complex documents into page-aligned Markdown.

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482