ExtractWisdom

Extracts content-adaptive wisdom sections from videos, podcasts, and articles at five depth levels.

Updated Sep 3, 2026
One-click install
npx skills add https://github.com/ruban-s/DevOS --skill extractwisdom-ruban-s
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ExtractWisdom
Source: https://github.com/ruban-s/DevOS/tree/main/skills/ExtractWisdom
Command: npx skills add https://github.com/ruban-s/DevOS --skill extractwisdom-ruban-s

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Fixed extraction templates force every video, podcast, or article into the same generic sections, flattening contrarian takes and unique insights into bland summaries. This Skill reads the content first, detects which wisdom domains are actually present, and builds custom sections around them. ## Core Features & Use Cases - Content-Adaptive Sections: Section names are invented for each piece of content — a security talk gets "Threat Model Insights" while a business podcast gets "Money Philosophy" — never a fixed template. - Five Depth Levels: Choose from Instant (1 section), Fast, Basic, Full (default, 5-12 sections), or Comprehensive (10-15 sections plus Themes & Connections). - Multi-Source Input: Pulls YouTube transcripts via fabric -y URL, fetches articles via WebFetch, or reads local files and pasted text. - Use Case: Paste a YouTube interview link and say "extract wisdom" to receive a conversational, quote-rich breakdown with a one-sentence takeaway, a 2-minute must-know list, and references worth following up. ## Quick Start Extract wisdom from this YouTube interview at full depth and give me the key takeaways.

Frequently Asked Questions about ExtractWisdom

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

FAQPage Schema
How do I extract key insights from a YouTube video?▼

Provide the YouTube URL and ask to extract wisdom. The skill runs `fabric -y URL` to pull the transcript, then builds content-specific sections with conversational bullets, a one-sentence takeaway, and follow-up references.

How do I summarize a podcast or interview transcript?▼

Paste the transcript or file path and request extraction at a depth level — Instant, Fast, Basic, Full, or Comprehensive. Full is the default and produces 5-12 adaptive sections plus closing takeaways.

Can I extract wisdom from articles and blog posts?▼

Yes, article URLs are fetched via WebFetch and local files are read directly. The extraction adapts its section names and structure to the article's actual content rather than applying a fixed template.

What are the depth levels for content extraction?▼

Five levels exist: Instant (1 section), Fast (3 sections), Basic (3 sections plus takeaway), Full (5-12 sections, the default), and Comprehensive (10-15 sections plus a Themes & Connections analysis).

What are the limitations when processing long content?▼

Very long content like 3-hour podcast transcripts should not be extracted in one pass. Save the transcript to a working file and chunk it before extraction to avoid losing insights.