skills.rest
dbbaskette
dbbasketteCOMMUNITY
Explore all skills by this author →
GitHub

pdf-extract

Extract structured Markdown from PDFs using the pdf-extract CLI.

Updated Mar 9, 2026
Search Tags:#ocr#pdf#markdown#tables#data-extraction#ingest
One-click install
npx skills add https://github.com/dbbaskette/herald --skill pdf-extract-dbbaskette
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pdf-extract
Source: https://github.com/dbbaskette/herald/tree/main/skills/pdf-extract
Command: npx skills add https://github.com/dbbaskette/herald --skill pdf-extract-dbbaskette

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract clean, structurally faithful Markdown from PDFs by preserving heading hierarchy, tables, lists, and reading order, enabling reliable AI processing and downstream memory or wiki workflows.

Core Features & Use Cases

  • Preserves document structure (headings, tables, lists) and outputs Markdown that maintains readability for AI reasoning and ingestion.
  • Supports common workflows: extract for summaries, ingest into memory, or surface for wiki pages, including scanned PDFs via hybrid OCR.
  • Facilitates downstream analysis by providing structured, surface-ready content that can be fed into wiki-ingest or memory systems.

Quick Start

Extract a PDF into structured Markdown using the pdf-extract workflow.

Frequently Asked Questions about pdf-extract

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

FAQPage Schema
How do I convert a PDF to Markdown while preserving tables and headings?▼

You can convert PDF to Markdown with preserved tables and headings using the opendataloader-pdf CLI, which outputs structurally faithful Markdown maintaining document hierarchy, lists, and reading order for reliable AI ingestion.

Can I extract text from scanned PDFs using OCR for AI ingestion?▼

Yes, scanned PDFs can be processed for AI ingestion using the pdf-extract workflow's hybrid OCR capabilities, which outputs clean, structured Markdown suitable for downstream memory or wiki-ingest systems.

What do I need to run the pdf-extract workflow for data extraction?▼

To run the pdf-extract workflow for PDF data extraction, you need the opendataloader-pdf CLI installed and a compatible Python environment to execute the extraction and generate Markdown output.

Does PDF data extraction support JSON or HTML output for complex table layouts?▼

Yes, PDF data extraction may offer JSON or HTML outputs for advanced table and layout data, though Markdown is the default output format for maintaining AI readability and structural faithfulness.

What is the best way to ingest PDF content into a memory or wiki system?▼

The best way to ingest PDF content into memory or wiki systems is extracting it into clean Markdown first, which preserves reading order and document structure for reliable downstream analysis and ingestion workflows.

Related Skills

Explore More Data & Analytics Skills→
webdevtodayjasonwebdevtodayjason

ocr-and-documents

Extract text from PDFs, scanned documents, and images using OCR.

Community
Advanced
Simon-Copilot-StudioSimon-Copilot-Studio

llm-wiki

Ingest sources into an interlinked markdown knowledge base with cross-links.

Community
Advanced
guccangguccang
3

llm-wiki

Create and maintain interlinked markdown knowledge bases with YAML metadata.

Community
Advanced
ntaksh42ntaksh42
1

data-visualization

Generate interactive HTML charts from CSV, JSON, or table data using Chart.js.

Community
Intermediate