跳到主内容
智客 ZICQ

技能库 智客分类:媒体内容 h3-prompt-writing

H3 Prompt Writing

写入迷你Max H3视频生成提示 T2VA, I2VA, FL2VA, L2VA, 和Ref2VA. 将多式请求重写为 H3 即时结构时使用, 组合集成_ 多式_ description, 总体_ soundscape, 以及非_ diegetic_ music, 校正密钥框架, 或定义图像、 视频和音频的参考标签 .

8881 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

写入迷你Max H3 视频生成提示 T2VA, I2VA, FL2VA, L2VA, 和 Ref2VA

何时用

将多模式请求重写为 H3 即时结构, 编组集成_ 多式联运_ 描述, 整体_ 声音scape, 以及非_ diegetic_ music, 校正密钥框架, 或定义图像、 视频和音频的参考标签

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:H3 Prompt Writing、Workflow、Base Modes、Full-Reference Mode、Output Rules、Tips for Better Results。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/base-en.txt、references/ref-en.txt,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

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 WritingWorkflowBase ModesFull-Reference ModeOutput RulesTips for Better Results

兼容: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.

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
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.
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.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 2
  • references/base-en.txt
  • references/ref-en.txt

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「h3-prompt-writing」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-5239027479db12d7-H3-%E5%BF%AB%E9%80%9F%E5%86%99%E5%85%A5.html
请存为 .cursor/skills/h3-prompt-writing/SKILL.md 或 .claude/skills/h3-prompt-writing/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/minimax-ai/minimax-h3 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/minimax-ai/minimax-h3' --list

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

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- 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. 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. ``, ``, ``) 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.

相关技能

媒体内容

Nano Banana Pro

以纳米·香蕉Pro(Gemini 3 Pro Image)来生成/编辑图像. 用于创建/修改请求,包括编辑。 支持文本到图像+图像到图像; 1K/2K/4K; 使用 -- input-image.

媒体内容

Youtube Watcher

从YouTube视频中获取并读取文字记录. 需要汇总视频时使用,回答有关视频内容的问题,或者从中提取信息.

媒体内容

Atxp

Access ATXP支付API工具用于网页搜索,AI图像生成,音乐创建,视频生成,X/Twitter搜索,电子邮件,代理账户管理. 当用户需要实时网络搜索时使用,AI生成的媒体(图像,音乐,视频),X/Twitter搜索,发送/接收电子邮件,或创建和资助代理账户. 需要通过“ …

媒体内容

Youtube

YouTube Data API与管理的OAuth的集成. 搜索视频,管理播放列表,访问频道数据,并与评论互动. 用户想与YouTube互动时使用此技能. 对于其他第三方应用,使用api-gateway技能(https://clawhub.ai/byungkyu/api-gate…