Individual skill
novel-storyboard
给 AI 短剧出分镜:三层结构——段(一次视频生成,≤15 秒)→ 分镜(段内 2–5 秒的剪切,认领剧本节拍) → 分镜图(每切一张关键帧:主分镜图钉 0.00 秒,子分镜图钉各自切点)。 每段自带一条 MiniMax H3 视频提示词(官方口径默认英文、逐镜换行,promptLang 可切中文):对齐指令和 [Shot k] 切点时刻由分镜结构推导、逐字对账,台词逐字进 <d> 块(写法规范已内化为 references/h3-prompt.md,不依赖外部 skill)。 产出 storyboard.json + Markdown + 单页评审报告(分镜节奏带 / 分集分镜表 / 生成批次单 / 配音对齐单,含导出 JSON)。不出图——交付的是每格的画面提示词和它该挂哪些参考图。 18 道质量门全部由脚本确定性检查(第 18 道 shot-recipe 可选:挂上 shot-recipes 卡库才查,不挂就明说跳过); export 一键导出 H3 投产包(每段提示词 + 按 Picture 序的分镜图清单)。零依赖、零 API key,用当前会话额度。 Use when asked to 分镜、出分镜、镜头表、切镜、storyboard for AI short drama。
skills/novel-storyboard/SKILL.md
Source commit 5612d2a0bd5f19d978c3ee19d1e42840335e3b4b
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 6,390
- Repository last updated
- Nov 9, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
README.en.mddoc · 12,148 bytesREADME.mddoc · 12,545 bytesSKILL.mdcore · 14,449 bytesSKILL.mdcore · 14,449 bytesSKILL.mdcore · 14,449 bytesSKILL.mdcore · 14,449 bytesSKILL.mdcore · 14,449 bytesSKILL.mdcore · 14,449 bytesSKILL.mdcore · 14,449 bytesSKILL.mdcore · 14,449 bytesSKILL.mdcore · 14,449 bytesassets/report.webpasset · 190,454 bytesexamples/渡口-storyboard.jsonasset · 51,772 bytesreferences/frame.mddoc · 3,729 bytesreferences/h3-prompt.mddoc · 4,094 bytesreferences/report-style.mddoc · 3,619 bytesreferences/schema.mddoc · 8,189 bytesreferences/seedance-prompt.mddoc · 7,466 bytesreferences/shot-writing.mddoc · 6,188 bytesreferences/storyboard-pass.mddoc · 6,557 bytesreferences/test-fixtures/shot-recipes/hands-tell.mddoc · 180 bytesreferences/test-fixtures/shot-recipes/insert-beat.mddoc · 185 bytesreferences/test-fixtures/shot-recipes/ots-shot-reverse.mddoc · 217 bytesreferences/test-fixtures/upstream/README.mddoc · 612 bytesreferences/test-fixtures/upstream/渡口-art.jsonasset · 16,839 bytesreferences/test-fixtures/upstream/渡口-cast.jsonasset · 42,544 bytesreferences/test-fixtures/upstream/渡口-outline.jsonasset · 9,659 bytesreferences/test-fixtures/upstream/渡口-script.jsonasset · 38,592 bytesscripts/novel-storyboard.mjsruns · 110,165 bytesscripts/selftest.mjsruns · 48,739 bytes
Read excerpt
## novel-storyboard
给 AI 短剧出**分镜**——管线里第一个直接面对视频模型的层。**前提刻在骨子里:镜头是生成出来的,多切一镜的成本几乎为零**,所以这里不心疼镜头数量,上限只有一个:视频模型单段生成的时长(默认 15 秒)。
**核心机制:镜头认领节拍。** 每个镜头声明它覆盖剧本某场的哪几个连续节拍(`sceneIndex` + `beats: [起, 止]`),镜头不许跨场次——换景必换镜。这让分镜和剧本的关系变成可机械对账的:
| 交付 | 解决什么 |
| --- | --- |
| 节拍认领 | 每个节拍被恰好一个镜头认领、顺序不乱——剧本改了重跑 validate,失效的镜头当场点名 |
| 单镜头 ≤ 15 秒 | AI 视频单段生成上限,长对话在这里被强制拆镜(`params.maxShotSeconds` 按模型改) |
| 台词装得下 | 认领节拍的台词秒数 ≤ 镜头秒数——逐镜检查,不是拍脑袋 |
| 分镜图提示词 + 镜头正文 | 分镜图提示词(`frame`,中文,直呼角色名)给图像模型配合设定图出图;镜头正文(`shot`,中文,通用身份)写这几秒发生什么。景别是枚举,中文景别词必须写进分镜图提示词 |
| **H3 视频提示词(每段一条)** | MiniMax H3 的 I2VA 结构:固定对齐指令 + integrated_multimodal_description + overall_soundscape + non_diegetic_music。**认领节拍的台词逐字进 `<d>[Chinese] …</d>` 块**——对白、声景、配乐一段提示词全带上 |
| **Seedance 视频提示词(每段一条,程序拼)** | 跟 H3 并列。由脚本按官方结构拼:参考图声明、段级走位、逐镜量化字段、台词 `{}`、音效 `<>`、配乐 `()`、编号约束。模型只写每切的 `shot`,不写秒数、编号和图片引用 |