jiucaihezi-v6

Use when converting character analysis results into Banana JSON prompts for text-to-image generation. This model benefits from explicit detail, reference-sheet layout, and strong negative constraints.

Use when converting shot-design results into Banana 3x3 storyboard grid JSON prompts for the current flashxiaolagu mainline. This skill is assembly-only and should write short natural-language cinematic beats, not rigid keyword chains.

Use when converting prop analysis results into Banana JSON prompts for the current Banana/Veo pipeline. This stage should preserve visible structure, layout blocks, multi-view detail, and generation-critical markings.

Use when converting scene analysis results into Banana JSON prompts for the current Banana/Veo pipeline. This stage should lead with one decisive narrative identity sentence, then give layered scene control rather than one giant brute-force room dump.

Use when one or more split storyboard panel images such as `storyboards/frames/.../panel_004.png` need Nano Banana Pro image editing instead of rerunning the whole Banana storyboard batch. This skill writes structured Chinese edit prompts for panel-level character, scene, prop, or fused repairs while explicitly preserving locked elements and continuity.

Use when analyzing script characters for the current Banana/Veo short-drama pipeline. Output a dual-layer character asset spec: a slim control_table for downstream automation and a lightweight production_bible for human review and reuse.

Use when converting raw script into a material engineering book before shot design. This stage translates audience-facing script into production-facing reusable material units such as dialogue coverage, action chain fragments, reveals, inserts, resets, and reactions for downstream shot design.

Use when analyzing script props for the current Banana/Veo short-drama pipeline. Output a dual-layer prop asset spec that is specific enough for detail-hungry downstream image models.

Use when turning script locations into a final empty-environment master-shot scene asset for the current Banana/Veo short-drama pipeline. This stage must inherit the selected type-analysis style and lighting, lock one reusable camera truth, and exhaustively enumerate everything visible in that master shot for downstream prompt assembly.

Use when converting script content and engineering-book material units into executable shot design for xiaolagumanju. This skill must inherit pacing, respect the material engineering book, and output only downstream-useful shot control data.

Use when starting a new film/drama project and need multiple style options for the user to choose from before all downstream work. This stage decides ratio, style design, and pacing design, and absorbs lighting design into the same output.

Use when converting shot-design results or storyboard first-frame beats into Grok-friendly prompts for `rhart-video-g/image-to-video`, `xai/grok-imagine/image-to-video`, or 全能视频G in the current flashxiaolagu mainline. This skill is assembly-only and enforces the tested Chinese segmented timeline format with `cut` and the fixed ending `无音乐，无音效，无字幕`.

Use when converting the new shot-design output into LTX 2.3 image-to-video prompts for xiaolagumanju. This skill should read only compact downstream-useful fields such as first frame, last frame, shot prompt, dialogue, and duration, and should calculate final video duration from dialogue length at execution time.

Use when converting script text, dialogue, or character information into Qwen TTS voice design prompts. This skill should infer suitable voice identity, emotional tone, speaking rhythm, and optional scene flavor for each speaker, then output concise natural-language voice design prompts that can be passed to Qwen3-TTS.

Generate images, videos, audio, and 3D models via RunningHub API (170+ endpoints) and run any RunningHub AI Application (custom ComfyUI workflow) by webappId. Covers text-to-image, image-to-video, text-to-speech, music generation, 3D modeling, image upscaling, AI apps, and more.

Use when converting shot-design results into Veo-friendly image-to-video or start-end-to-video prompts for the current flashxiaolagu mainline. This skill is assembly-only and should respect the actual endpoint constraints.

视频合成工具 — 拼接视频片段并添加字幕

Use when generating a single talking-head or dialogue shot from a first frame, a minimal motion tag, a clean voice audio file, and dialogue text. This skill is for voice-locked shot rendering in the xiaolagumanju pipeline.