H3 Prompt Writing
Workflow
- If the input is only a rough idea, story, or image without an executable shot plan, read the sibling
video-director skill first. Use its selected directing plan as the source of truth; do not invent a second concept during prompt conversion.
- Identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA.
- For base text/keyframe modes, read
references/base-en.txt and follow its final prompt structure.
- For full-reference mode, read
references/ref-en.txt and follow its six-section rewrite format.
- Preserve the exact field names, section order, labels, timing, actions, transitions, and ending from the selected guide and directing plan.
Base Modes
- T2VA: build the full audiovisual timeline from text.
- I2VA: start from the first frame and develop forward from it.
- FL2VA: describe the continuous path between the first and last frames.
- L2VA: infer a plausible opening and converge to the supplied last frame.
Use integrated_multimodal_description, overall_soundscape, and non_diegetic_music in the order shown in references/base-en.txt.
Full-Reference Mode
Ref2VA rewrites use subject_definitions, summary, retention_analysis, detailed_description, overall_soundscape, and non_diegetic_music in that order. Reference labels stay consistent across all sections.
Read references/ref-en.txt for label rules, retention analysis, and complete examples.
Output Rules
- Write rewrite sections in English; preserve dialogue, lyrics, and visible scene text in their original language.
- Describe each shot by composition, subjects, environment, actions, camera, sound, and the exact point where referenced content appears.
- Avoid plot summaries, unresolved reference labels, and timing that does not match the requested duration.
Dsivio 内置版
对话使用本 Skill 的原始脚本和 MCP。查找、保存或修改模板时读 共享模板说明，直接读写共享文件夹；不创建页面任务或同步草稿。运行环境由应用提供，内置副本随应用更新。
视频配置在哪
视频页面和本插件共用一份 providers.json，页面保存后下次脚本调用直接生效，不需要重复配置。路径优先取 DSVIDEO_CONFIG_PATH；否则 Windows 为 %APPDATA%/dsvideo/providers.json，macOS/Linux 为 ${XDG_CONFIG_HOME:-~/.config}/dsvideo/providers.json。
用户问模型或配置时，运行 python <插件根目录>/scripts/dsvideo_config.py show（密钥脱敏），查看 providers.grok / providers.minimax / providers.comfy 的 model 和 base_url。MiniMax-H3 路线模型固定为 MiniMax-H3；ComfyUI 模型由工作流决定。旧环境变量显式覆盖时说明来源。生成仍使用插件自己的脚本和 MCP。
1---2name: h3-prompt-writing3description: Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio.4---56# H3 Prompt Writing78## Workflow9101. If the input is only a rough idea, story, or image without an executable shot plan, read the sibling `video-director` skill first. Use its selected directing plan as the source of truth; do not invent a second concept during prompt conversion.112. Identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA.123. For base text/keyframe modes, read `references/base-en.txt` and follow its final prompt structure.134. For full-reference mode, read `references/ref-en.txt` and follow its six-section rewrite format.145. Preserve the exact field names, section order, labels, timing, actions, transitions, and ending from the selected guide and directing plan.1516## Base Modes1718- T2VA: build the full audiovisual timeline from text.19- I2VA: start from the first frame and develop forward from it.20- FL2VA: describe the continuous path between the first and last frames.21- L2VA: infer a plausible opening and converge to the supplied last frame.2223Use `integrated_multimodal_description`, `overall_soundscape`, and `non_diegetic_music` in the order shown in `references/base-en.txt`.2425## Full-Reference Mode2627Ref2VA rewrites use `subject_definitions`, `summary`, `retention_analysis`, `detailed_description`, `overall_soundscape`, and `non_diegetic_music` in that order. Reference labels stay consistent across all sections.2829Read `references/ref-en.txt` for label rules, retention analysis, and complete examples.3031## Output Rules3233- Write rewrite sections in English; preserve dialogue, lyrics, and visible scene text in their original language.34- Describe each shot by composition, subjects, environment, actions, camera, sound, and the exact point where referenced content appears.35- Avoid plot summaries, unresolved reference labels, and timing that does not match the requested duration.3637## Dsivio 内置版3839对话使用本 Skill 的原始脚本和 MCP。查找、保存或修改模板时读 [共享模板说明](../../TEMPLATES.md)，直接读写共享文件夹；不创建页面任务或同步草稿。运行环境由应用提供，内置副本随应用更新。4041## 视频配置在哪4243视频页面和本插件共用一份 `providers.json`，页面保存后下次脚本调用直接生效，不需要重复配置。路径优先取 `DSVIDEO_CONFIG_PATH`；否则 Windows 为 `%APPDATA%/dsvideo/providers.json`，macOS/Linux 为 `${XDG_CONFIG_HOME:-~/.config}/dsvideo/providers.json`。44用户问模型或配置时，运行 `python <插件根目录>/scripts/dsvideo_config.py show`（密钥脱敏），查看 `providers.grok` / `providers.minimax` / `providers.comfy` 的 `model` 和 `base_url`。MiniMax-H3 路线模型固定为 MiniMax-H3；ComfyUI 模型由工作流决定。旧环境变量显式覆盖时说明来源。生成仍使用插件自己的脚本和 MCP。
zmgid