Short Drama Production H3 Prompt Writing

---
name: h3-prompt-writing
description: 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.
metadata:
  compatibility: Portable to any agent that can read local files — no external API calls, MiniMax Hub tools, or proprietary runtime required. The agents/openai.yaml file only adds optional ChatGPT/Codex UI metadata; it does not restrict the skill to OpenAI agents.
---

# H3 Prompt Writing

## Workflow

1. Identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA.
2. For base text/keyframe modes, read `references/base-en.txt` and follow its final prompt structure.
3. For full-reference mode, read `references/ref-en.txt` and follow its six-section rewrite format.
4. Preserve the exact field names, section order, labels, and timing notation from the selected guide.

## 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.
## Tips for Better Results
- Always match the total duration of the description to the requested video length (4–15 seconds).
- Keep reference labels consistent (e.g. `<Picture 1>`, `<Video 1>`, `<Audio 1>`) across every section.
- Prefer concrete visual and audio details over abstract words like "cinematic" or "beautiful".
- When using keyframes (I2VA / FL2VA / L2VA), clearly state how the first and/or last frame connects to the timeline.

## Production handoff

Consume the approved shot plan, reference roles and requested duration; do not redesign the story or approve source media. Draft rewrites may identify missing inputs explicitly, but final references and labels must refer to actual reviewed assets. Return prompts to the storyboard/production owner; prompt completion does not authorize generation or certify video quality. Keep the vendor reference documents unchanged. The bundled guides target 4–15 seconds; a provider advertising longer output does not itself extend this prompt contract. Route longer requests to the production adapter's compatibility workflow instead of silently stretching timestamps.