skills.rest
infantesromeroadrian
infantesromeroadrianCOMMUNITY
Explore all skills by this author →
Website𝕏@infantes_adrianGitHub

wiki-ingest

Extracts and formats text from diverse sources for wiki-style storage.

Updated Jun 21, 2026
Search Tags:#PDF#YouTube#arXiv#knowledge ingestion#LLM Wiki
One-click install
npx skills add https://github.com/infantesromeroadrian/arca-agent --skill wiki-ingest-infantesromeroadrian
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wiki-ingest
Source: https://github.com/infantesromeroadrian/arca-agent/tree/main/template/skills/wiki-ingest
Command: npx skills add https://github.com/infantesromeroadrian/arca-agent --skill wiki-ingest-infantesromeroadrian

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, curl, pdftotext, python3, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps users easily ingest external knowledge sources like YouTube videos, arXiv papers, and local PDFs into their LLM Wiki, making it easy to access and reference this information across sessions.

Core Features & Use Cases

  • Knowledge Ingestion: Automates the process of extracting text from various sources and preparing it for inclusion in an LLM Wiki.
  • Supports Multiple Sources: Works with YouTube videos, arXiv papers, local PDFs, and local text files.
  • Use Case: When you watch a talk or read a paper that you want to reference later, you can use this Skill to automatically extract the content and add it to your Wiki.

Quick Start

To ingest a YouTube video, say: /wiki-ingest <youtube-url>

Frequently Asked Questions about wiki-ingest

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

FAQPage Schema
How do I ingest external knowledge from a YouTube video into my LLM Wiki?▼

To ingest external knowledge from a YouTube video, you provide the video URL to trigger automated text extraction using yt-dlp, which prepares the structured content for inclusion in your LLM Wiki.

Can I extract text from arXiv papers and local PDFs for knowledge ingestion?▼

Yes, you can extract text from arXiv papers and local PDFs for knowledge ingestion. The process utilizes curl and pdftotext to pull and format the content, structuring it for your LLM Wiki.

Do I need to install python3 and yt-dlp before extracting text from multiple sources?▼

Yes, you need to install python3, yt-dlp, curl, and pdftotext before extracting text from multiple sources. These dependencies are required to process YouTube videos, arXiv papers, and local PDFs.

What is the best way to organize and reference external knowledge sources across sessions?▼

The best way to organize and reference external knowledge sources across sessions is to automate text extraction from videos and papers, preparing structured content that remains accessible within your LLM Wiki.

Does knowledge ingestion work with local text files as well as online sources?▼

Yes, knowledge ingestion works with local text files as well as online sources. It extracts text from local PDFs, local text files, YouTube videos, and arXiv papers, preparing all content for your LLM Wiki.

Related Skills

Explore More Education & Research Skills→
jholhewresjholhewres
3

summarize

Condenses web pages, articles, videos, podcasts, and files into concise summaries.

Community
Intermediate
techwolf-aitechwolf-ai
95

kb-import

Convert Markdown, PDF, DOCX, and text files into structured KB entries with YAML frontmatter.

Official
Advanced
Prat011Prat011
1.5k

notion-knowledge-capture

Extract key concepts and decisions from conversations into structured Notion pages.

Community
Advanced
hochoa13hochoa13

ocr-and-documents

Extracts text and tables from PDFs, images, and other document formats via OCR and parsing tools.

Community
Advanced