- Home
- Skills
- Sammcj
- Agentic Coding
- Extract Wisdom
extract-wisdom_skill
- Python
110
GitHub Stars
3
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill sammcj/agentic-coding --skill extract-wisdom- .gitignore116 B
- CLAUDE.md445 B
- SKILL.md14.4 KB
Overview
This skill extracts wisdom, insights and actionable takeaways from YouTube videos, blog posts, articles or local text files. It automates content acquisition, analyses the material to preserve high-signal ideas, and writes a structured markdown analysis file. The output is organised for quick reading and practical follow-up.
How this skill works
The skill detects the source type, then fetches content: YouTube transcripts via a download script, web articles via WebFetch, or local files via a read tool. It cleans and condenses text, then identifies key insights, notable quotes, a structured summary and concrete action items. Finally it writes a dated, titled markdown analysis file in a predictable directory and returns the analysis when requested.
When to use it
- You need a short, high-signal synthesis of long video transcripts or articles
- You want clear, prioritised action items from a talk, tutorial or essay
- You need a structured analysis saved as a markdown file for later reference
- You are compiling insights from multiple sources and want consistent output
- You want quotes and context extracted for citations or notes
Best practices
- Provide a concise title or short description when renaming output directories
- Request topic-focused analysis if you only need specific themes or sections
- Prefer English transcripts or articles for best accuracy; specify Australian English if needed
- Ask for timestamps only when precise video timing is essential
- Run the self-review checklist after generation to ensure spelling and formatting are correct
Example use cases
- Summarise a 90 minute keynote into 5 actionable steps and 3 notable quotes
- Extract best practices and tools from a technical blog series into a single markdown file
- Process a stack of articles into per-source analyses plus a synthesis file comparing themes
- Pull out growth strategies and immediate experiments from a marketing webinar transcript
- Create study notes from lecture videos with clear next steps and references
FAQ
Yes. It processes sources sequentially, writes separate analysis files per source and can produce a comparative synthesis file summarising common themes.
Will the skill preserve original wording for quotes?
Yes. Notable quotes are preserved exactly, with the exception that spelling is normalised to Australian English as configured.