A funnel feeding a tower of four graded sieve trays full of crystals, cut open to show an indigo channel carrying one crystal out the side into a ring.
Research

ExtractWisdom

Content-adaptive wisdom extraction (sections built around what the content holds, five depth levels, mandatory contrarian takes) and extract alpha (the N highest-alpha, net-new ideas as short ranked bullets) from videos, podcasts, articles, files or text, from the full source

02
Workflows
00
Tools
01
Reference
12
Triggers

The Problem

Most content summarization tools apply the same template to everything. A security conference talk gets the same headers as a philosophy podcast: IDEAS, QUOTES, HABITS, FACTS. The sections don't match the content, so the output feels like a form that got partially filled in. You also lose the texture — the contrarian take, the moment of genuine surprise, the human story behind the technical point. What comes back is an inventory, not insight. And because the sections are fixed, the thing worth knowing most is often buried or missing entirely.

How This Skill Approaches It

ExtractWisdom reads the content first and figures out what wisdom domains are actually present before deciding on sections. A programming interview gets 'Developer Workflow' and 'Architecture Philosophy'. A business podcast gets 'Contrarian Business Takes' and 'Money Philosophy'. The section names are headlines, not categories — designed to make you curious, not to file things away. Five depth levels let you choose the right tradeoff: Instant gives one killer section, Comprehensive goes 10-15 sections with a Themes and Connections synthesis at the end. All bullets follow strict voice rules — written like you'd say it to a friend over coffee, not like a compressed tweet. YouTube content gets pulled via fabric -y for the transcript; articles come in via WebFetch. The Extract workflow applies the content-scan, section-selection, and extraction phases in sequence, then closes with a One-Sentence Takeaway, a 2-minute summary, and a references list.

Not for static Fabric extract_wisdom pattern (use Fabric), or multi-source web investigation (Research)

In Action

What you say to your DA, and what the ExtractWisdom skill actually does.

  • You say "extract wisdom from this andrej karpathy interview"
    Runs Extract: fetches the YouTube transcript via fabric -y, scans for wisdom domains present in the conversation, builds custom sections like 'How He Thinks About Learning' and 'What AI Actually Changes', applies Level 3 conversational voice rules throughout, and closes with a One-Sentence Takeaway and 2-minute summary.
  • You say "extract wisdom from this article at comprehensive depth"
    Runs Extract at Comprehensive level: fetches the article via WebFetch, identifies 10-15 wisdom domains, generates full sections with 8-15 bullets each, and adds a Themes and Connections section that surfaces the deeper patterns connecting everything — the throughlines the author may not have realized they were revealing.

Inside the Skill

The thinking, frameworks, and architecture that distinguish this skill from a generic version of the same task.

Ideal State

  • A reader who has two minutes gets the specific ideas, quotes and contrarian takes that make this piece worth their time, in sections named for this content rather than a fixed template.
  • Every bullet sounds like the principal telling a friend about it, and every detail comes from this content, never from the calibration samples.
  • Contrarian takes are mandatory: a genuinely hot take from the speaker appears undiluted, because spicy takes are the most memorable and shareable material.
  • An Alpha run returns exactly the N ideas asked for (24 by default), ranked by how new they are, each short and faithful to the source, or fewer with a note when the content has fewer.
  • The structure matches the requested depth level (Full by default) and passes the Quality Check in Intents/Extract.md § Output format; the extractwisdom-contract eval separately checks that insights come from the source and that a contrarian take appears.

Intent Routing

Intent Trigger File
Extract "extract wisdom from", ew, "analyze this", YouTube URL Intents/Extract.md
Alpha "extract alpha", ea or ea 8, "highest-alpha ideas", "what is new in this" Intents/Alpha.md
File Read when
References/VoiceCalibration.md writing any bullet: the three-level voice ladder with sample bullets (calibration only)
EvalState.md checking the extractwisdom-contract eval results (machine-written by Assay, never hand-edited)
Setup.md first-time setup: the optional fabric and yt-dlp install for YouTube links

Data & Config

User customizations live at <configRoot>/LIFEOS/USER/CUSTOMIZATIONS/SKILLS/ExtractWisdom/ (configRoot is $CLAUDE_CONFIG_DIR when set, else ~/.claude). When it exists, its PREFERENCES.md, configurations and resources override the defaults here; when absent, the defaults stand.

First-time setup: Setup.md.

Gotchas

  • Source fetching (fabric -y URL for YouTube, raw HTML for articles) and chunking long transcripts are in Intents/Extract.md § Inputs and § Gotchas.

Examples

Example 1: YouTube interview extraction

User: "extract wisdom from this Marcus Hutchins interview"
→ Extract intent; transcript from `fabric -y URL`
→ Sections named for this interview, then the closing sections for Full

Example 2: Article extraction

User: "extract the key insights from this blog post"
→ Raw HTML fetched and its body extracted in full (never WebFetch, which returns a summary)
→ Sections adapted to the article, with source attribution

Workflows & Routing · 2

Each workflow is one job the skill runs. The trigger phrases route your request to the right one — this is the skill's routing table.

  1. 01
    Extract Intents/Extract.md

    extract wisdom from, ew, analyze this, YouTube URL

  2. 02
    Alpha Intents/Alpha.md

    extract alpha, ea or ea 8, highest-alpha ideas, what is new in this

How to Invoke

Say any of these to your DA and LifeOS activates the ExtractWisdom skill automatically:

  • "extract wisdom"
  • "ew"
  • "extract alpha"
  • "ea"
  • "highest-alpha ideas"
  • "what is new in this"
  • "analyze video"
  • "analyze podcast"
  • "extract insights"
  • "key takeaways"
  • "summarize interview"
  • "distill content"

Or invoke explicitly:

Skill("ExtractWisdom")

References · 1

Auxiliary files the skill loads at runtime — frameworks, guides, configs.

  • Setup

References & Credits

The thinkers, books, frameworks, and research this skill is built on. The ideas belong to them — the integration belongs to LifeOS.

Want LifeOS to do this for you?

Install LifeOS on your machine — your DA gets the ExtractWisdom skill plus 96 others, all hooked into one Life OS.