Claudemy
Turn any topic into a short audio course with cited sources
About
Say "teach me negotiation" and it researches 20 to 40 web pages, maps where sources agree and split, and builds about 12 two-host audio lessons of 2 minutes each. Every lesson comes with a card (the idea in three lines, source agreement, one small thing to try, links) and a rule for your playbook. A checker refuses lessons that cite pages it did not actually read. It can also build a class from one person's blog or Substack.
Install
Works with Claude Code
Access
HighWhat this skill's own files let it touch on your machine and accounts. Access isn't a verdict: check the publisher and the security audits too.
- Bundles scripts
- Runs shell commands
- Writes files in your project
- Uses the network
- Asks for credentials
Bundles Python scripts (beautifulsoup4) and uses ffmpeg to fetch pages and render audio. Researched pages and lessons are saved in a local ./claudemy/<topic>/ folder. An optional ElevenLabs API key (env var or OS keychain via the plugin prompt) sends lesson text to ElevenLabs for two-voice audio; without it, free macOS voices are used. No server and no analytics. Gen Agent Trust Hub marks it high risk: it reads arbitrary web pages (possible prompt injection) and pipes ElevenLabs MP3s into ffmpeg, which its own analysis says is media processing, not remote code. Review the scripts if that matters to you. Needs Claude Code with web search.
Reviewed from source on Oct 18, 2026. Read the files yourself before installing.
More Writing skills
All skillsRelated articles
All articlesBest Claude Code Marketing Skills (2026)
The Claude Code marketing skills I install first (SEO audit, copywriting, pricing) and three MCP tools that give them real SEO data.
Best Memory Tools for Claude Code (2026)
Five tools that give Claude Code memory across sessions, agents and machines, with install commands, honest caveats and when CLAUDE.md is enough.
7 Tools to Cut Your Coding Agent's Token Bill (2026)
Seven tools that cut Claude Code, Codex and Cursor token usage by compressing shell output, searching code and fetching current docs, with honest caveats.








