Voice Video Action Assistant

Use when you need an AI assistant that takes action from voice and video input.

harishkotra Updated

File contents

Voice & Video Action Assistant

Take action from voice and video input: understand the user's intent and execute it.

When to use

  • A user speaks or shows something and wants an action taken.
  • You need multimodal understanding (voice, video, screen) driving real actions.

Procedure

  1. Capture and transcribe the voice/video input.
  2. Understand the intent and the action required.
  3. Map it to a concrete, safe action; confirm before consequential steps.
  4. Execute and report what was done.
  5. Handle ambiguity by asking one clarifying question.

Pitfalls

  • Voice/video intent can be ambiguous; confirm before irreversible actions.
  • Multimodal input needs good transcription/vision; verify the model handles it.

Verification

  • A voice/video request leads to the correct action being executed and confirmed.

harishkotra/yc-s26-skills/tree/main/voice-video-action-assistant commit dbb56a42ba

Frequently asked questions

npx skillmds@latest add harishkotra/voice-video-action-assistant