cinema-studio-produce
End-to-end production orchestrator: user provides a script (raw text, treatment, or screenplay paragraph); skill parses it, classifies genre, generates character/scene reference assets, estimates and confirms budget, decomposes each scene into 2-4 content-diverse shots following R1-R20 rules, generates clips via Seedance 2.0 (or Kling), runs dual-judgment QA (Claude vision + Gemini 3.1 Pro), auto-fixes up to 3 iterations per failing clip, and finally concatenates into a single deliverable mp4 with full manifest and iteration log.
This is the production-ready pipeline built on top of the existing lower-level skills (script-to-video-seedance, script-to-video-kling, cinema-studio-qa, cinema-studio-ops). Use this when the user wants a complete short film (≥30s) from a script with minimal intervention. For one-off 15s clip tests, invoke the provider skill directly instead.
Use when:
- "把这个剧本拍成一部短片" / "produce this script" / "出片"
- User drops a multi-scene script (treatment, screenplay, log line)
- User reque
Repository SourceNeeds Review
script-to-video-seedance
Seedance 2.0 Fast pipeline for motion-heavy video production via Phoenix Cinema Studio API. Specializes in: real-world physics, action / martial arts / sports / chase scenes, joint audio-video generation with phoneme-level lip-sync, multimodal reference (≤9 images + ≤3 videos + ≤3 audio), native Chinese prompts, long single takes (≤15s). Default: `seedance-2.0-fast` @ 480p for cost efficiency.
Parses a screenplay into characters, locations, and scenes. Generates character reference images and location establishing shots, registers them via Ark compliance (single-step, no review modal), produces video clips where motion and physics carry the scene. Each clip is one `/generate-video` call, but Seedance can **render multiple internal shots within a single generation** when the prompt describes the cuts — so a single 15s clip can contain 2-3 shot-level beats (WS → MS → CU) that the model stitches together natively. Cross-clip consistency comes from reusing the SAME registered `reference_image_urls` across eve
Repository SourceNeeds Review
fire-smoke-detection-analysis
Detects fire and smoke in video scenes. Supports both video stream and image analysis. Suitable for fire early warning scenarios such as security surveillance, forest fire prevention, and industrial parks. | 烟火检测技能，对视频场景中火情和烟雾进行检测，支持视频流和图片检测，适用于安防监控、森林防火、工业园区等火灾预警场景
Archived SourceRecently Updated
basic-object-detection-analysis
Detects people, vehicles, non-motorized vehicles, pets, and parcels appearing in the target area. Supports video stream and image detection, suitable for general security surveillance scenarios. | 基础目标检测技能，检测出目标区域内出现的人、车、非机动车、宠物、包裹，支持视频流和图片检测，适用于通用安防监控场景
Archived SourceRecently Updated