Podcaster Turns 15 Manual Steps into 8 AI Skills, Saving 5 Hours a Week
petergyang · x · 2026-09-17
Podcaster Peter Yang shares his system of 8 AI skills that produces his entire show, compressing 15 manual steps and saving at least 5 hours a week while keeping his own taste in the loop.
- /podcast-prep: researches guests and builds interview guides
- /podcast-edit: reviews raw transcripts, picks highlight quotes for intro reels, marks cut points
- /podcast-production: orchestrates 5 skills to turn one episode into 6 distribution assets
He also outlines a 3-step system to automate any manual workflow, and pushes back on the idea that better models make skills obsolete — skills are what make AI reliably follow his specific editing and browser-use instructions. A companion video demos all 8 skills.
Related event: Three-step AI workflow turns 15 podcast steps into 8 skills(2 posts)→
More from coding & agent
- Android Use debuts: a scheduled, memory-equipped Android agent with permission controls — emeka_boris · 2026-09-17
- Matt Pocock proposes /pr skill: every model creates garbage PR bodies today — mattpocockuk · 2026-09-17
- Codex Agents Pile Up 76GB of Debug Files, Burning Through 5x Quota Overnight — craigbalding · 2026-09-17
- Build the agent setup first, pick the model second: a Linux + Tailscale + llama.cpp stack guide — max_paperclips · 2026-09-17
- Dev claims LLM memory is basically solved using LLM plus Jev for recall — JoshuaJBouw · 2026-09-17
- AI agents can now control Google Home as MCP server opens to third-party assistants — emmanuelvivier · 2026-09-17