Update to Givon AI

{
  "description": "Create or transform product visuals through Givon AI using a product brief, live model guidance and schema-supported inputs.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 390
    },
    {
      "relative_path": "references/mode-selection.md",
      "size_in_bytes": 1312
    },
    {
      "relative_path": "references/prompt-structures.md",
      "size_in_bytes": 1751
    }
  ],
  "name": "givon-ai-product-photoshoot",
  "skill_md_contents": "---\nname: givon-ai-product-photoshoot\ndescription: \"Create or transform product visuals through Givon AI using a product brief, live model guidance and schema-supported inputs.\"\nmetadata:\n  version: skill-render-ea6bd93365667f6d\n---\n\n# Givon AI Product Photoshoot\n\nTurn the user's product brief into one or more schema-valid image generations. The brief\ndescribes the desired visual; the live catalog and selected model schema own executable modes,\ninputs, settings and defaults.\n\n## Workflow\n\n1. Capture the requested deliverable, product identity, reference roles and intended use.\n2. Ask only for information required to make the next action executable when it cannot be\n   inferred from the brief, attached media, current context or live schema defaults. Collect all\n   such missing inputs together.\n3. Use `givon-ai-create` to inspect active models and the selected model's detailed schema.\n4. Build a compact prompt from the user's creative facts and the relevant structure in\n   [references/prompt-structures.md](references/prompt-structures.md).\n5. Pass product/reference media only through schema-supported asset fields.\n6. Generate the requested number of results and return labeled ready assets.\n\nRead [references/mode-selection.md](references/mode-selection.md) when the brief is incomplete\nand you need to resolve blocking creative inputs. Apply the selected model family guidance\nexposed by `givon-ai-create` after model selection.\n\n## Product brief\n\nUse only relevant dimensions:\n\n- product identity and details to preserve;\n- source/reference role;\n- intended use and output container;\n- scene, composition, crop, pose or interaction;\n- light, material and visual direction;\n- exact visible text;\n- count and aspect when explicitly chosen or required.\n\nFor a series, keep a coherent visual system while giving each image a distinct purpose. Default\ndelivery contains short labels and ready asset URLs or handles; include implementation detail\nwhen the user asks for it.\n"
}