.claude/skills/extract-wisdom/SKILL.md
Extract structured wisdom, insights, and actionable takeaways from any content — podcasts, articles, videos, transcripts, books, or conversations. Use this skill whenever the user asks to "extract wisdom", "summarize insights", "pull out key ideas", "what are the takeaways", "extract the best parts", "distill this content", "what did I learn from this", or provides a transcript/article and asks for a structured breakdown. Also trigger when the user pastes or references long-form content and wants the signal extracted from the noise — even if they don't use the word "wisdom" specifically. Inspired by Daniel Miessler's Fabric pattern.
npx skillsauth add theramjad/ray-os extract-wisdomInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You extract surprising, insightful, and interesting information from content. You care about ideas related to human flourishing, the meaning of life, technology's role in humanity's future, AI, learning, continuous improvement, and similar deep topics — but adapt to whatever domain the content covers.
Read the input content carefully. Then produce a structured breakdown across the sections below. The goal is to compress hours of content into minutes of reading while preserving the most valuable signal.
Produce each section in order. Use bulleted lists (not numbered). Each bullet should be exactly 16 words — this constraint forces precision and makes the output scannable.
A 25-word summary of who is presenting/writing and what the content covers.
Extract 20-50 of the most surprising, insightful, or interesting ideas. Aim for at least 25. These are the raw "aha" moments — things that made you stop and think.
Extract 10-20 refined insights. These are higher-level than IDEAS — more abstracted, more distilled. Think of them as the IDEAS that survived a second pass through a quality filter. Combine related ideas into deeper observations.
Extract 15-30 of the most memorable quotes, using the exact words from the source. Attribute each quote to its speaker at the end of the bullet.
Extract 15-30 practical personal habits mentioned by or about the speakers. Sleep schedules, reading routines, productivity systems, diet, exercise, things they always do or avoid.
Extract 15-30 surprising, verifiable facts about the world mentioned in the content. These should be things someone could look up — statistics, historical events, scientific findings.
Extract all mentions of books, articles, tools, projects, people, art, or other sources of inspiration. This is a completeness-oriented section — capture everything referenced.
The single most important takeaway from the entire piece, in exactly 15 words.
Extract 15-30 actionable recommendations — things the listener/reader could actually go do. Each should be specific enough to act on.
The user may provide content in various forms:
Fetch or read the content as needed, then apply the extraction process above.
content-media
Edit raw screen recording videos with synced audio. Removes repeated takes, false starts, silence, filler, and [MUSIC] tags to produce a clean final cut. Use when the user provides a raw/unedited MP4 video file and wants it edited down. Triggers on: "edit this video", "cut this video", providing a raw MP4 for editing, or any request to remove bad takes from a recording.
tools
Monitor Twitter/X for trending AI and developer tool discussions, score them, and deliver pre-digested content briefs. Use this skill whenever the user wants to find trending topics on Twitter, check what people are talking about in AI/tech, scout for video ideas from Twitter, or says things like "what's trending", "anything new on Twitter", "find me something to talk about", "scout Twitter", or "what are people saying about X". Also triggers on "monitor layer", "input layer", or "fountainhead" when Twitter is relevant.
development
# /triage — Inbox Triage ## Description Scan all connected communication channels, prioritize items by urgency, and draft responses in your voice. Clear your inbox in minutes. ## Arguments - `quick` — Tier 1 items only, no drafts (fastest) - `digest` — Full scan with summaries, drafts for Tier 1-2 - (no argument) — Full scan with drafts for everything actionable ## Instructions You are running inbox triage for {{YOUR_NAME}}. The goal is to process all incoming messages quickly and surface wh
tools
YouTube data utility — fetch transcripts, metadata, thumbnails, and search for videos. Wraps the Supadata API and yt-dlp into a single CLI tool. Use whenever you need YouTube data like transcripts, video metadata, thumbnail images, or need to search YouTube for videos matching a query. Triggers on any YouTube data fetching need from other skills or direct user requests.