
ExtractWisdom
Pulls the sharpest ideas, quotes and contrarian takes from videos, podcasts and articles
- Repository
- danielmiessler/LifeOS
- Stars
- 19,682
- Licence
- MIT
- Files
- 5 files
What it does
Once installed, the agent reads a video transcript, podcast, interview, article or pasted text in full, then writes a summary built around what that specific content contains rather than a fixed template. It can also run an Alpha mode that returns a short ranked list of the most new ideas (24 by default, or a number you choose). Full-depth output adds a one-sentence takeaway, a two-minute highlights list and references worth following, and contrarian takes from the speaker are meant to be kept in their strongest form.
Great for
- People who regularly consume long interviews or podcasts and want the key points quickly
- Researchers or writers who want fast, source-grounded notes on articles
- Users already working in Claude Code who want a repeatable summarising workflow
Skip it if
- Fact-checking or high-stakes decisions: output is a model summary and can misstate or omit details, so verify against the source
- Multi-source web investigation, which the skill itself routes to a separate Research skill
- Users who need the fixed Fabric extract_wisdom prompt; the skill points them to Fabric for that
Try asking
- “extract wisdom from this Marcus Hutchins interview”
- “ea 8 on this podcast transcript”
- “Extract the key insights from this blog post”
- “What is new in this article? Give me the highest-alpha ideas”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 5 original files, the MIT licence and an attribution note.
ExtractWisdom.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip ExtractWisdom.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip ExtractWisdom.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Paste the transcript or give a direct URL so the agent works from the full source rather than a memory of it
- Ask for a depth level or an Alpha count (for example ea 8) if the default length is not right
- Run the optional Setup.md steps first if you want YouTube links to work
What's inside
- Intents/Alpha.md
- Intents/Extract.md
- References/VoiceCalibration.md
- Setup.md
- SKILL.md
Redistributed unmodified from danielmiessler/LifeOS under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.