Update to fal

{
  "name": "cinematography",
  "description": "Design cinematic image and video prompts for fal.ai. Use for shot language, camera movement, lighting, lens choices, color grade, scene blocking, film texture, and production-ready visual direction.\n",
  "included_files": [],
  "skill_md_contents": "---\nname: cinematography\ndescription: >\n  Design cinematic image and video prompts for fal.ai. Use for shot language,\n  camera movement, lighting, lens choices, color grade, scene blocking,\n  film texture, and production-ready visual direction.\n---\n\n# Cinematography\n\nUse when the user needs concrete visual direction, not generic \"cinematic\"\nprompting. Execution runs through fal.ai MCP tools.\n\n## Inputs To Collect\n\n- Subject and action.\n- Medium: still, video, image-to-video, edit, storyboard frame.\n- Genre and mood.\n- Framing: close-up, medium, wide, overhead, POV, profile, locked-off.\n- Camera motion: push-in, dolly, tracking, handheld, crane, drone.\n- Lens feel: wide, normal, telephoto, macro, shallow/deep focus.\n- Lighting: natural, practical, studio, noir, high key, low key, backlit.\n- Output: aspect ratio, duration, first frame, last frame.\n\n## Prompt Build\n\n1. Subject/action.\n2. Shot size and camera position.\n3. Camera motion over time if video.\n4. Lens/depth behavior.\n5. Lighting source and direction.\n6. Color palette and grade.\n7. Texture: clean digital, film grain, archival, phone, broadcast.\n8. Constraints: no identity/product drift, no fake text, no extra logos.\n\n## Model Choices\n\n- Premium still: `openai/gpt-image-2`, `fal-ai/nano-banana-pro`.\n- Final video: Seedance 2.0 text/image video.\n- Fast video draft: Grok Imagine Video.\n- Multi-prompt/control-heavy shot: Kling v3.\n\n## Quality Bar\n\n- Prompt describes an actual camera setup.\n- Motion is physically plausible.\n- Lighting direction matches the setting.\n- Video prompt has a beginning and ending state.\n- Any referenced first frame is treated as an anchor, not redesigned.\n"
}