10-minute motion graphics: a full ChatGPT + MCP + Skills workflow

aziz4ai · x · 2026-09-16

A Saudi developer shares a complete workflow for producing motion graphics in 10 minutes: drive everything conversationally from ChatGPT Work / Codex, connected via MCP. Image generation uses the built-in ChatGPT/Codex skill plus manually attached fonts; animation requires mounting a dedicated motion skill like Remotion or Hyperframes, with a taste skill handling design aesthetics. Saudi voiceover uses Google Gemini TTS 3.1 and music comes from ElevenLabs Music 3 via MCP. Key lessons: spell out every requirement explicitly (the model won't infer intent), plan creative direction before execution, and verify outputs against official sources.

Original post →

More from coding & agent

coding & agent channel →