Update to Givon AI

{
  "description": "For generating narration from agreed words, use the exact spoken text and current model voice controls to separate speech content from delivery settings. Not needed for writing or editing the script itself.",
  "included_files": [],
  "name": "voiceover-for-video",
  "skill_md_contents": "---\nname: voiceover-for-video\ndescription: \"For generating narration from agreed words, use the exact spoken text and current model voice controls to separate speech content from delivery settings. Not needed for writing or editing the script itself.\"\nmetadata:\n  version: skill-render-ea6bd93365667f6d\n---\n\n# Voiceover for video\n\nFollow the confirmed contract of the chosen model. Keep the creative task separate from the\nexact text to be spoken, and use only the declared delivery parameters.\n\n## Text to be spoken\n\nPut the exact approved spoken words into `input.prompt`. Preserve wording, numbers,\nabbreviations, names and pauses. Use inline audio tags only when the model's current prompting\nguidance supports them and the user included or requested that delivery.\n\n## Delivery\n\nRead `givon_get_model_schema` for the chosen voiceover model. List voices through\n`givon_list_voices` (CLI: `givon voice list`) and pass the chosen id as `input.voice`.\nUse only delivery controls exposed as flat properties in that schema, with their declared\nvalues and defaults. Do not assume a project-default voice or copy fields from an internal\nchat contract. Keep delivery instructions separate from words that should actually be spoken.\nQuote this exact input and continue through `givon-ai-create` after approval.\n"
}