obsidian-wiki-ingest

Classify raw materials and generate wiki pages from PDFs, notes, and URLs.

2|Updated Jun 7, 2022

Search Tags:#obsidian #classification #knowledge-management #entity-extraction #wiki-ingest #source-ingest

Ready to run

npx skills add https://github.com/SebasAren/SebbaFlow --skill obsidian-wiki-ingest

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: obsidian-wiki-ingest
Source: https://github.com/SebasAren/SebbaFlow/tree/main/pi/.pi/agent/skills/obsidian-wiki-ingest
Command: npx skills add https://github.com/SebasAren/SebbaFlow --skill obsidian-wiki-ingest

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Keeps your personal wiki current by turning raw materials into structured wiki content without manual page-by-page entry, linking sources, and organizing notes, articles, and media.

Core Features & Use Cases

Automatic ingestion workflow: moves files from raw/inbox into appropriate folders (raw/papers, raw/notes, raw/articles, raw/videos) and creates corresponding wiki pages in wiki/sources, wiki/entities, wiki/concepts.
Cross-link generation and attribution: ensures wiki pages reference related concepts and entities with [[wiki links]] and preserves source credibility notes as part of the synthesis.
Supports diverse content types: PDFs, Markdown notes, HTML articles, URLs, YouTube transcripts, and video files, enabling scalable knowledge capture.

Quick Start

Ingest new sources from raw/inbox into the wiki by classifying, moving, and creating corresponding wiki pages.

Frequently Asked Questions about obsidian-wiki-ingest

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

FAQPage Schema

How do I automatically ingest PDFs and URLs into my Obsidian wiki?▼

To ingest PDFs and URLs into your Obsidian wiki, drop raw materials into the raw/inbox folder. The Skill automatically classifies items by type, moves files into appropriate raw/ subfolders, and generates corresponding wiki pages with cross-linked sources and concepts.

What is the best way to organize raw markdown notes and video transcripts in a personal wiki?▼

Organizing raw markdown notes and video transcripts requires an automated ingestion workflow that classifies raw materials, routes them into dedicated folders for notes and videos, and populates wiki pages with extracted entities and concepts.

Can I extract entities and concepts from HTML articles and link them in Obsidian?▼

Yes, you can extract entities and concepts from HTML articles. The ingestion process automatically generates [[wiki links]] referencing related concepts and entities, populating wiki/entities and wiki/concepts pages while preserving source attribution.

Does Obsidian wiki ingestion require a specific folder structure to function?▼

Yes, Obsidian wiki ingestion requires a specific folder structure to function. It enforces a wiki architecture comprising raw/, wiki/, and SCHEMA.md, routing files from raw/inbox into categorized subfolders and generating pages across wiki/sources and wiki/concepts.

How does source classification handle diverse content types like YouTube transcripts and papers?▼

Source classification handles diverse content types like YouTube transcripts and papers by identifying the format dropped in raw/inbox, moving the file into the matching raw/videos or raw/papers folder, and creating a structured wiki page with cross-links and synthesis entries.