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.
More from coding & agent
- Cloudflare open-sources security-audit-skill for coding agents with machine-readable findings — cloudflare · 2026-09-16
- Supabase keeps climbing: the open-source Postgres platform for AI apps hits 109k stars — supabase · 2026-09-16
- Cline: open-source autonomous coding agent ships as SDK, IDE extension, or CLI — cline · 2026-09-16
- Anthropic open-sources knowledge-work plugins built for Claude Cowork, hits 24k stars — anthropics · 2026-09-16
- Tencent's open-source WeKnora RAG knowledge platform tops 24.8k GitHub stars — Tencent · 2026-09-16
- Developers compare approaches for cross-device agent memory and context persistence — mundane--alternative · 2026-09-16