H3 Prompt Writing
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. dsh-short-video-studio 适配版:还负责把画布上的镜头表/分镜/参考绑定重写为 H3 结构化 prompt(见文末「插件对接」适配节)。
Install
npx skills add fengyungithub/dsh-short-video-studio --skill h3-prompt-writinggit clone --depth 1 https://github.com/fengyungithub/dsh-short-video-studio.git /tmp/dsh-short-video-studio
mkdir -p ~/.claude/skills
cp -r /tmp/dsh-short-video-studio/skills/h3-prompt-writing ~/.claude/skills/h3-prompt-writingPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# H3 Prompt Writing > 以下正文为 MiniMax 官方 SKILL.md 原文(Source: github.com/MiniMax-AI/MiniMax-H3, skills/h3-prompt-writing/SKILL.md, License: MiniMax H3 Community License), > 只读引用;dsh-short-video-studio 的插件适配内容见文末「插件对接(dsh-short-video-studio 适配)」节。 ## 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
Details
- Skill name
h3-prompt-writing- Repository
- fengyungithub/dsh-short-video-studio
- Path
skills/h3-prompt-writing/SKILL.md- License
- Apache-2.0
- Repo updated
- 9 November 2026
FAQ
What does the H3 Prompt Writing skill do?
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. dsh-short-video-studio 适配版:还负责把画布上的镜头表/分镜/参考绑定重写为 H3 结构化 prompt(见文末「插件对接」适配节)。
How do I install the H3 Prompt Writing skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add fengyungithub/dsh-short-video-studio --skill h3-prompt-writing. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is H3 Prompt Writing popular?
It lives in fengyungithub/dsh-short-video-studio, which has 44 GitHub stars and 7 forks.
Related skills
Brand Promo Video Generator
44fengyungithub/dsh-short-video-studio
把可核验的品牌素材与推广目标转化为一条完整的品牌宣传短片生产流程,依次完成素材收集、品牌事实表、来源清单、品牌资产上画布、创意方向、六列标准镜头表、镜头表自检门、生成前硬确认、逐镜视频生成(视频原生音频 + 画面内原生文案)、拼接成片与最终交付复查。全程走本地 ComfyUI 能力注册表(图片文生图 + 视频 AV 模型);带身份识别素材(LOGO / 产品界面 / 包装 / 吉祥物)绝不重绘或近似——画布原件可用时首帧锁定,否则降级为精确描述锚点。适用于品牌 / 产品 / 网站 / App / 小店 / 个人项目的新品发布、官网展示与社媒推广短片。不适用于 KOC 口播带货广告、缺少授权素材时仿造真实品牌标识、虚构产品功能或长篇剧情影片。
Image Generate
44fengyungithub/dsh-short-video-studio
把「提示词 + 尺寸/档位/张数 + 可选单张参考图」生成为一张或数张图片,支持文生图(t2i)与参考图生图(i2i 改绘)。适用于「输入框手动生成」这条轻量链路:用户在输入框用 `/image-generate` 斜杠命令加载本 skill、在工具条选参数、写 prompt,发送后由本 skill 解析命令行参数并调度图片生成工具出图并落画布。不适用于完整片型流程(简报/大纲/镜头表/分镜/逐镜交付),那些请用 story-short-generator 或 brand-promo-video-generator。
Qwen Image Prompt Writing
44fengyungithub/dsh-short-video-studio
把一句简短或含糊的出图需求重写为 Qwen-Image 2.1 能稳定吃下的长描述(官方 PE-T2I 八步骨架),或把含糊的改图需求重写为精确的编辑指令(官方 PE-I2I 属性解耦规范),并裁定画幅、RGBA 透明句柄、图内文字写法与「负向约束的正向改写」。触发词:提示词增强、提示词优化、扩写 prompt、一句话出图、改图指令、prompt 怎么写、qwen 提示词。
Omni AI Eval
46exploreomni/omni-agent-skills
Evaluate Omni AI accuracy using Omni's built-in eval system — define a prompt set, run a judged eval against a model (or branch), and read the accuracy-judge verdicts. Use this skill whenever someone wants to evaluate Omni AI, benchmark Blobby, run regression tests, compare AI output across branches or model-context changes, measure AI quality, run A/B tests on model changes, assess the impact of an ai_context or modeling change, or any variant of "run evals", "test Blobby", "benchmark query generation", "compare AI results", "regression test", "how accurate is the AI", or "measure the impact
Claude Agent SDK
35liangdabiao/claudesdk-skill
Claude Agent SDK framework guide for building AI-powered applications. Provides comprehensive API knowledge, architecture patterns, and code examples for both TypeScript and Python. Use when: (1) building projects with @anthropic-ai/claude-agent-sdk, (2) creating AI agents with tool use, hooks, subagents, or MCP servers, (3) implementing multi-turn conversations, streaming responses, or session management, (4) configuring permission modes, custom tools, or agent orchestration, (5) debugging or extending existing Claude Agent SDK code, (6) user mentions "agent sdk", "claude agent", "claude-agen
Omni AI Optimizer
46exploreomni/omni-agent-skills
Optimize an Omni Analytics model for Blobby, the Omni Agent — configure ai_context, ai_fields, synonyms, sample_queries, and ai_settings. Use this skill whenever someone wants to improve AI accuracy in Omni, make Blobby smarter, add AI context or example questions, curate which fields the AI sees, personalize AI context by user attribute, diagnose context-window pruning or truncation, raise a topic's AI context budget, control which topics AI can reach, troubleshoot why Blobby gives wrong answers, or any variant of "make the AI better", "Blobby isn't answering correctly", "optimize for AI", or
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.