ContentAnalysis

Extract adaptive insight reports from videos, podcasts, articles, and YouTube transcripts.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/Kaleb-Rupe/aurora --skill contentanalysis-kaleb-rupe
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ContentAnalysis
Source: https://github.com/Kaleb-Rupe/aurora/tree/main/claude/skills/ContentAnalysis
Command: npx skills add https://github.com/Kaleb-Rupe/aurora --skill contentanalysis-kaleb-rupe

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long-form content like podcasts, interviews, and YouTube videos contains valuable insights, but manually watching and note-taking is time-consuming, and static summary templates miss the content's actual themes. ## Core Features & Use Cases - Dynamic Section Generation: Detects which wisdom domains exist in the content and builds custom sections around them instead of using fixed categories like IDEAS or QUOTES. - Adjustable Depth Levels: Supports Instant, Fast, Basic, Full, and Comprehensive extraction depths with matching section counts and closing summaries. - Multi-Source Input: Accepts YouTube URLs via transcript extraction, article URLs, local files, or pasted text. - Use Case: Paste a YouTube interview link and receive a tailored insight report with conversational bullets, a one-sentence takeaway, a 2-minute summary, and follow-up references. ## Quick Start Extract wisdom from this YouTube video at full depth and give me the key takeaways.

Frequently Asked Questions about ContentAnalysis

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 request a wisdom extraction. The workflow uses fabric -y to pull the transcript, then performs a deep read and builds custom sections around the insight domains actually present in the content.

What content sources does wisdom extraction support?

It accepts YouTube URLs via transcript extraction, article URLs fetched with WebFetch, local file paths read directly, and pasted plain text. All sources go through the same deep-read and dynamic section workflow.

How is this different from a standard content summary?

Instead of static sections like IDEAS or QUOTES, it detects which wisdom domains exist in the content and names sections specifically for that material. It also enforces conversational tone rules so bullets read like spoken observations rather than documentation.

Can I control the depth of the content extraction?

Yes, five depth levels are available: Instant, Fast, Basic, Full, and Comprehensive. Full is the default with 5-12 sections, while Comprehensive adds a Themes and Connections synthesis section with up to 15 sections.

Can I customize the extraction output style?

Yes, the skill checks for user customizations in ~/.claude/Aurora/USER/SKILLCUSTOMIZATIONS/ExtractWisdom/ before running. Any PREFERENCES.md or configuration files found there override the default behavior.