agentleFS
full-aigc-skillsfull-aigc-skills/minimax-skills/skills/h3-prompt-writing/SKILL.md

h3-prompt-writing

Skill4 starsChanged 58 days agoApache-2.0View on GitHub

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.

11 other projects use a version of this, 8 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 2 are common, 3 are distinctive, and 3 are very specific to this project.

  • 2

    Common

    Most of the 10 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use integrated_multimodal_description, overall_soundscape, and non_diegetic_music in the order shown in references/base-en.txt.

    line 23
  2. Very specific:

    Read references/ref-en.txt for label rules, retention analysis, and complete examples.

    line 29
  3. Common:

    Write rewrite sections in English.

    line 33
  4. Common:

    Avoid plot summaries, unresolved reference labels, and timing that does not match the requested duration.

    line 35
  5. Distinctive:

    Always match the total duration of the description to the requested video length (4–15 seconds).

    line 37
  6. Very specific:

    Keep reference labels consistent (e.g.

    line 38
  7. Distinctive:

    Prefer concrete visual and audio details over abstract words like "cinematic" or "beautiful".

    line 39
  8. Distinctive:

    When using keyframes (I2VA / FL2VA / L2VA), clearly state how the first and/or last frame connects to the timeline.

    line 40

“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.
<!-- QUALITY_BASELINE_V1 -->

When to use(什么时候使用)

当用户需要 为当前请求选择并执行可验证、可恢复的专业工作流 时加载本技能。先从请求中提取目标、输入、约束、交付格式和验收标准;描述摘要为: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.。

Rules

  • 先读后写:先确认当前状态与真实能力,再执行会改变外部状态的动作。
  • 权限最小化:只使用完成当前步骤所需的文件、工具、账户与网络范围。
  • 证据优先:运行结果、资源 ID、版本、哈希或测试输出缺失时,明确标记为 NOT_VERIFIED。
  • 幂等优先:保留请求标识与阶段状态;结果不明确时先查询,不进行盲目重试。
  • 隐私安全:日志、示例、回执和错误信息不得包含 token、cookie、密钥或个人敏感数据。

Workflow

Step 1:澄清意图

确认本技能是否匹配目标;若只是相邻需求,交给更精确的技能。

Step 2:执行预检

确认目标、输入、约束、可用工具、成功标准和失败边界;任一关键条件未知时停止在只读阶段。

Step 3:形成计划

列出将调用的工具、会改变的对象、成功标准以及失败后的安全退出方式。

Step 4:执行动作

按最小充分步骤执行,并在关键状态变化处记录证据;每个外部调用均保留可关联的状态或回执。

Step 5:验证交付

输出结果、验证证据、未完成项、风险和明确的下一步,并把事实、推断和未验证项分开陈述。

Validation checklist

  • 技能触发条件与用户意图一致,没有把相邻任务误路由到本技能。
  • 输入、目标对象、版本和输出位置均已明确,且没有使用猜测值替代必填值。
  • 所有写入、付费、发布或不可逆动作都在用户授权范围内。
  • 结果已用独立检查验证;仅有“命令成功”或“文件存在”不算完整验收。
  • 输出包含实际证据、失败/跳过项、剩余风险和可执行的下一步。

Gotchas

  1. 把计划当结果:文档或提示词不等于真实执行;必须标明实际运行层级。
  2. 错误重试:超时或响应丢失可能已经产生远端状态,先查询再决定是否重试。
  3. 隐式扩大范围:批量、全量、发布、覆盖和付费不是普通读写的自然延伸。
  4. 版本漂移:引用外部资源时记录版本、tag 或提交;不要把可变分支当发布证据。
  5. 证据过期:缓存、旧截图和历史测试不能证明当前环境;在交付前刷新关键证据。

不适用与边界

不超出用户给定范围;写入、付费、发布和不可逆动作需要明确授权。 如果请求需要别的技能,不复制其正文;按技能名称进行交接,并保留当前任务上下文。

Progressive disclosure

  • 需要确定输入/输出、状态和授权点时,读取 references/workflow-contract.md。
  • 需要交付前自检时,读取 references/validation-checklist.md。
  • 遇到超时、部分成功或恢复场景时,读取 references/error-recovery.md。
  • 首次运行、拒绝越权和失败恢复分别参考 examples/happy-path.md、examples/boundary-refusal.md、examples/failure-recovery.md。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.