Agent Skills › vllm-project/vllm-omni › h3-prompt-writing

h3-prompt-writing

GitHub

用于编写 MiniMax H3 视频生成提示词，支持 T2VA、I2VA 等多种模式。将多模态请求转换为结构化提示，定义视听时间线、场景描述及参考标签，确保符合格式规范与时长要求。

.agents/skills/h3-prompt-writing/SKILL.md vllm-project/vllm-omni

触发场景

编写视频生成提示词多模态请求重写为 H3 结构定义视听时间线和参考标签

安装

npx skills add vllm-project/vllm-omni --skill h3-prompt-writing -g -y

更多选项

非标准路径

npx skills add https://github.com/vllm-project/vllm-omni/tree/main/.agents/skills/h3-prompt-writing -g -y

不安装直接使用

npx skills use vllm-project/vllm-omni@h3-prompt-writing

指定 Agent (Claude Code)

npx skills add vllm-project/vllm-omni --skill h3-prompt-writing -a claude-code -g -y

安装 repo 全部 skill

npx skills add vllm-project/vllm-omni --all -g -y

预览 repo 内 skill

npx skills add vllm-project/vllm-omni --list

SKILL.md

Frontmatter

{
    "name": "h3-prompt-writing",
    "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."
    },
    "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."
}

H3 Prompt Writing

Workflow

Read portable-workflow.md for scope, available tools, durable artifacts, and generation handoff. For prompt-only work, no generation tools are required.
Identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA.
For base text/keyframe modes, read references/base-format.md and follow its final prompt structure.
For full-reference mode, read references/ref-format.md and follow its six-section rewrite format.
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-format.md.

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-format.md for label rules and retention analysis.

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

Match the description to the effective duration of the current clip or generation window. The upstream guides describe 4–15-second clips; longer work requires a verified backend extension or an explicit assembly plan, as described in the portable workflow.
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.