mcpField
H
h3-prompt-writing

h3-prompt-writing

github.com/minimax-aiCreative & media10.8k11.8k installsUpdated today
Repository

About h3-prompt-writing

h3-prompt-writing is a skill for producing English prompts for video-generation workflows from text, keyframes, or full references. It specifies mode-specific structures, timing, and reference-label consistency.

Key features

  1. 01Supports five video input modes
  2. 02Applies mode-specific prompt structures
  3. 03Preserves section labels and ordering
  4. 04Describes shot, camera, and sound
  5. 05Matches descriptions to video duration

Use cases

  1. 01Write a timeline from a text idea
  2. 02Develop video from a first frame
  3. 03Describe motion between two keyframes
  4. 04Rewrite a video prompt using references

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/minimax-ai/minimax-h3 --skill h3-prompt-writing

After installing, type/h3-prompt-writingin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

agents/
openai.yaml
references/
base-en.txt
ref-en.txt

Details

From the project README

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.

Comments

Markdown supported