skills.rest
Kaleb-Rupe
Kaleb-RupeCOMMUNITY
Explore all skills by this author →
𝕏@MightieMagsGitHub

ExtractWisdom

Extracts content-adaptive insight sections from videos, podcasts, and articles.

Updated Jul 10, 2026
Search Tags:#summarization#content analysis#wisdom extraction#markdown report#key takeaways#youtube transcript#podcast insights
One-click install
npx skills add https://github.com/Kaleb-Rupe/aurora --skill extractwisdom-kaleb-rupe
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ExtractWisdom
Source: https://github.com/Kaleb-Rupe/aurora/tree/main/claude/skills/ContentAnalysis/ExtractWisdom
Command: npx skills add https://github.com/Kaleb-Rupe/aurora --skill extractwisdom-kaleb-rupe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Static summarization templates force every piece of content into the same fixed sections, missing the unique insights each source actually contains. This Skill reads content first, detects which wisdom domains are present, and builds custom sections around what it finds. ## Core Features & Use Cases - Dynamic Section Generation: Detects wisdom domains in the content (programming philosophy, contrarian takes, business insights) and creates tailored sections instead of static IDEAS/QUOTES headers. - Five Depth Levels: Choose Instant, Fast, Basic, Full, or Comprehensive extraction depending on how deep you need to go. - Multi-Source Input: Works with YouTube transcripts (via fabric), article URLs, local files, or pasted text. - Use Case: Paste a YouTube link to a two-hour podcast interview and receive a structured report with conversational, headline-worthy sections, a one-sentence takeaway, and a references list of people and projects worth following up on. ## Quick Start Extract wisdom from this YouTube video at full depth: https://youtube.com/watch?v=example

Frequently Asked Questions about ExtractWisdom

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

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

Provide the YouTube URL and the skill retrieves the transcript using fabric -y, then performs a deep read to detect wisdom domains. It outputs a Markdown report with custom sections, a one-sentence takeaway, and references worth exploring.

How to summarize a podcast or article without generic bullet points?▼

This skill reads the full content first and builds sections around the actual insight domains present, such as contrarian takes or first-time revelations. Bullets follow conversational tone rules with specific details and quotes rather than vague summaries.

What depth levels does wisdom extraction support?▼

Five levels are available: 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 synthesis). Specify the level in your request.

Can I customize the extraction style or voice?▼

Yes. The skill checks ~/.claude/Aurora/USER/SKILLCUSTOMIZATIONS/ExtractWisdom/ for PREFERENCES.md or configuration files before running. Any customizations found there override the default tone and behavior rules.

What input sources does content extraction support?▼

Four input types are supported: YouTube URLs (transcript via fabric), article URLs (fetched via WebFetch), local file paths, and directly pasted text. All sources go through the same deep-read and dynamic section workflow.

Related Skills

Explore More Content & Communication Skills→
karaage0703karaage0703
136

xs:podcast

Automate podcast episode download, transcription, and summarization from iTunes or RSS feeds.

Community
Intermediate
evolution-foundationevolution-foundation
520

social-content-repurposer

Extract insights from source content and draft platform-native social posts.

Official
Intermediate
dangelesdangeles
6

fact-checker

Cross-reference claims against trusted sources and generate structured verification reports.

Community
Advanced
arunodaarunoda
21

RAG Fact Search

Search extracted facts locally using Ollama embeddings and sqlite-vec.

Community
Intermediate