wiki-ingest

Convert Markdown, PDFs, transcripts, and images into structured Obsidian wiki pages.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/sanchitnis/SanjaySecondBrain --skill wiki-ingest-sanchitnis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: wiki-ingest
Source: https://github.com/sanchitnis/SanjaySecondBrain/tree/main/obsidian-wiki/.skills/wiki-ingest
Command: npx skills add https://github.com/sanchitnis/SanjaySecondBrain --skill wiki-ingest-sanchitnis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires markdown, pdf, image processing, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill streamlines the process of converting raw documents like Markdown, PDFs, and transcripts into organized and structured Obsidian wiki pages, enhancing your note-taking and knowledge management experience.

Core Features & Use Cases

  • Document Ingestion: Accepts Markdown, PDFs, transcripts, and images for processing.
  • PDF Handling: Prioritizes Markdown transcriptions for content extraction, with fallbacks to PDF text and image recovery.
  • Entity Recognition: Identifies and links entities, concepts, and projects within the document.
  • Content Summarization: Creates a concise summary for each page in the wiki.
  • Wiki Integration: Seamlessly integrates new knowledge into existing pages with appropriate links.

Quick Start

Use the wiki-ingest skill to ingest the document 'presentation_slides.pdf' into your Obsidian wiki.

Frequently Asked Questions about wiki-ingest

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

FAQPage Schema
How do I convert PDFs and transcripts into structured Obsidian wiki pages?

You can convert PDFs and transcripts into structured Obsidian wiki pages by ingesting raw documents to automatically extract key entities, generate summaries, and link related concepts for knowledge management.

What is the best way to extract Markdown transcriptions from PDF files for a wiki?

Extracting Markdown transcriptions from PDFs is handled by prioritizing Markdown content within the document, falling back to direct PDF text and image recovery when Markdown is unavailable.

Can I ingest images alongside Markdown documents into my Obsidian knowledge base?

Yes, you can ingest images alongside Markdown documents and PDFs into your Obsidian knowledge base, requiring image processing libraries to handle visual content and integrate it into structured wiki pages.

How does entity recognition work when building a wiki from unstructured documents?

Entity recognition for wiki building works by scanning ingested documents to identify and link entities, concepts, and projects, then integrating this new knowledge into existing pages with appropriate links.

Do I need specific libraries to process PDFs and images for Obsidian note-taking?

Yes, you need Markdown, PDF, and image processing libraries to process documents and images for Obsidian note-taking, enabling the extraction of text and creation of structured wiki pages.

What are the limitations of using Markdown transcription for PDF text recovery?

Limitations of Markdown transcription for PDF text recovery include relying on fallback mechanisms like direct PDF text extraction and image recovery when prioritized Markdown transcriptions are not present in the source document.