Agent skill

Novel Storyboard

by suihe1 in suihe1/short-drama-production

将剧本与导演意图转成生成段、逐镜时间、参考素材计划和可校验分镜报告;使用官方 h3-prompt-writing 编写 H3 提示词,可导出投产包。用于技术分镜、镜头表和分镜修订;生成视频须另有明确任务与成本授权,不负责最终选片或剪辑。

Apache-2.0Auto-check: notesMedia & Creative

Install Novel Storyboard

skills CLI
$ npx skills add suihe1/short-drama-production --skill novel-storyboard -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install suihe1/short-drama-production novel-storyboard --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/suihe1/short-drama-production.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/novel-storyboard .claude/skills/novel-storyboard && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
novel-storyboard
GitHub stars
181
Token cost
~2.1k tokens
SKILL.md length
374 words
Files
15 (incl. scripts, references, assets)
Skills in repo
7
Repo updated
First seen
Licence
Apache-2.0

At a glance

将剧本与导演意图转成生成段、逐镜时间、参考素材计划和可校验分镜报告;使用官方 h3-prompt-writing 编写 H3 提示词,可导出投产包。用于技术分镜、镜头表和分镜修订;生成视频须另有明确任务与成本授权,不负责最终选片或剪辑。

  • Works in 9 steps: 定输入与范围 → seed 工作底稿 → 逐集分段切镜 → …
  • Tasks that involve Comics and storyboards
  • SKILL.md covers 输入与创作权限, novel-storyboard, 创作到生产的交接 and 边界, plus 3 more sections
  • Runs JavaScript, Python and PowerShell scripts from its folder; calls node; needs COMPSHARE_H3_API_KEY

What it does

Novel Storyboard is an agent skill from suihe1/short-drama-production. 将剧本与导演意图转成生成段、逐镜时间、参考素材计划和可校验分镜报告;使用官方 h3-prompt-writing 编写 H3 提示词,可导出投产包。用于技术分镜、镜头表和分镜修订;生成视频须另有明确任务与成本授权,不负责最终选片或剪辑。

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 18 other files, including scripts, reference files and assets (for example `README.en.md`, `README.md` and `examples/渡口-storyboard.json`).

It sits in Media & Creative, covering Comics and storyboards and Creative writing and fiction. It works with MiniMax. The repository describes itself as: AI 短剧生产总控 / 短剧skill:专业导演与分镜、MiniMax H3、CompShare、声音资产、粗剪与 QC,默认 16:9。 The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Comics and storyboards
  • Tasks that involve Creative writing and fiction

Example prompts

  • “/novel-storyboard”

Requirements

  • Python 3
  • Node.js
  • PowerShell
  • Pre-approved tools (allowed-tools): Read, Write, Bash, Task, Glob

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. 定输入与范围
  2. seed 工作底稿
  3. 逐集分段切镜
  4. 方案检查(最终校验在素材与提示词完成后)
  5. 出分镜图(可选)
  6. 5 — 素材验收后写最终 H3 提示词
  7. 6 — 完整校验与投产前复核
  8. 输出与汇报
  9. CompShare H3 API 投产(可选、需明确授权)

What it can do on your machine

Read from SKILL.md and the folder at commit dbd3310. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Read
    • Write
    • Bash
    • Task
    • Glob

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (JavaScript, Python and PowerShell), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • COMPSHARE_H3_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Novel Storyboard loads about 2.1k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 34 tokens; SKILL.md has 374 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~34
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Read, Write, Bash, Task, Glob

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from suihe1/short-drama-production at commit dbd3310, republished under its Apache-2.0 licence (© suihe1). 374 words, ~2,118 tokens.

Download SKILL.mdSave it as .claude/skills/novel-storyboard/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.
name
novel-storyboard
description
将剧本与导演意图转成生成段、逐镜时间、参考素材计划和可校验分镜报告;使用官方 h3-prompt-writing 编写 H3 提示词,可导出投产包。用于技术分镜、镜头表和分镜修订;生成视频须另有明确任务与成本授权,不负责最终选片或剪辑。
allowed-tools
Read, Write, Bash, Task, Glob
metadata.license
Apache-2.0
metadata.runtimes
claude-code, codex
metadata.version
1.3.0
metadata.triggers
novel-storyboard, 分镜, 出分镜, 镜头表, 切镜, 首帧, storyboard, shot list

输入与创作权限

先读用户实际材料与目标,复用已确定的事实和规格;已有剧本、资产或分镜直接进入相关工作,不为流程完整重写上游。未授权的删线、合人、改变人物身份、主题、结局或重要表演意图,先展示原位置、具体方案与得失,再由用户选择;已授权的局部修正直接完成。

下面的类型经验、批次和创作预算是适配起点,不是用户接受过的创作要求。旧校验器可能仍将部分经验规则报为失败:区分实际数据/引用/模型接口错误与创作建议,说明不适用项,保留原稿;不伪造字段、不静默改戏或降低技术投产要求。总控可用时参考其 references/creative-agreement.md;独立任务按本段处理,不强制依赖总控。

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。每个新增镜头都会增加参考准备、生成筛选、连续性与后期工作。先保持导演的观看逻辑与可剪性,再适配当前工具的单段上限(默认 15 秒),不为凑切点增加无意义镜头。

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,长对话在生成层按模型能力分段,是否切镜服从导演意图(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
首帧 + 运动双提示词首帧给图像模型(配合参考图),运动是模型无关的过程描述;景别、运镜是枚举,英文短语必须写进对应提示词
H3 视频提示词(每段一条)分镜结构和候选素材先定稿;素材验收后,再由官方 h3-prompt-writing 按生成模式改写。Ref2VA 为六段式;I2VA/FL2VA/L2VA 才使用对应关键帧指令。认领节拍的原生台词逐字进 <d>[Chinese] …</d> 块
生成批次单同场景 + 同光照的镜头归一批,共用同一张环境参考图——AI 版的顺场表,脚本自动汇总
配音对齐单每句台词对到镜号——TTS 音频贴到哪一段视频,脚本自动汇总
H3 API 投产(可选)用户明确授权后,把单段提示词与分镜图提交给 CompShare;本地图以内嵌数据发送,避免临时图床缓存串图

{baseDir} = 本文件所在目录。脚本 {baseDir}/scripts/novel-storyboard.mjs,零依赖,node 直接跑。

边界(不做的事):不写戏不改台词(novel-script 的活)、不出场景/角色/道具设定图(novel-art / novel-characters 的活)、不自行发明或内化 H3 官方格式、不做剪辑合成。视频生成是可选投产步骤,只有用户明确要求并授权 API 成本后才执行。口型/唇形同步暂不管。


Step 0 — 定输入与范围

已有剧本可先做导演与分镜讨论,不要求先改写大纲。使用本工具 validate/render/export 时需要结构化 script.json 和 --script;先忠实映射原稿,保留对白、事件与已有拍法,无法承载的意图另附交接说明。其余上游按有则用:

  • --outline / --cast:提示词禁人名检查 + 报告里 C01 显示成人名
  • --art:报告里 S01 显示成场景名 + 批次单嵌场景设定图

已有导演包时,先继承其镜头目的、顺序、画幅、节拍与连续性;技术调整保留来源和偏差。总控选择导演桥接路线时不再重复本流程。

一次切几集:跟剧本的批次走(剧本写到哪就分到哪),默认一批 ≤ 3 集。

Step 1 — seed 工作底稿
bash
node {baseDir}/scripts/novel-storyboard.mjs seed <script.json> --eps 1-3 > <workdir>/storyboard.json

确定性展开:每场的节拍清单(编号、动作/台词、每拍秒数、说话人)进 seedScenes,这就是切镜时的工作底稿。每拍秒数是上游估时基线;导演可依据围读、表演和镜头可读性调整,记录变化并复核总时长。 shots 留空,切镜才是模型的活。

Step 2 — 逐集分段切镜

每集一份任务,能并发就并发。每份任务拿到:

  • {baseDir}/references/storyboard-pass.md 和 {baseDir}/references/schema.md(读它们,照着做)
  • 该集的 seedScenes 底稿 + 场景卡(art.json 的锚点与光照提示词)+ 角色卡(cast.json 的形象要点)

流程:先按剧情单元分段(每段 9–15 秒、不跨场),普通叙事切 2–5 秒;一眼可读、无精确文字的 insert/full-frame-content 可短至 minInformationCutSeconds(默认 1.2 秒)。每切写一条分镜图提示词。一个源节拍只由一个 cut 的 beats 主要认领;补充信息、主观内容或反应覆盖使用 coverageOf,不能为了多一个镜头而重复认领同一节拍。

此阶段只固定镜头事实、frame、姿态连续性、关键信息展示策略和参考素材需求;不要冻结最终 h3Prompt。可以临时留空,直到候选素材完成验收。

先写明 generationMode:h3-t2va、h3-i2va、h3-fl2va、h3-l2va 或 h3-ref2va。Ref2VA 必须同时写 referenceMode: "multi-reference" 和显式 references;提示词采用 subject_definitions → summary → retention_analysis → detailed_description → overall_soundscape → non_diegetic_music 六段式。参考图按职责选择身份、场景拓扑、关键道具、内容素材,动作/构图图仅在无法靠文字稳定说明且自身完全正确时使用。若候选构图图存在多手、手别、支撑点、姿势或轴线错误,设置 referenceControlMode: "semantic-assets",只喂干净人物/环境/道具/内容资产,由提示词负责姿态、方位和镜头调度。I2VA/FL2VA/L2VA 才能声明首帧/尾帧并使用官方关键帧对齐句。[Shot k] 切点仍由分镜秒数推导并逐字核对;每切的运镜、动作、光线、表演和声音落在自己的时间窗。

切完把 seedScenes 删掉。

提速不等于成片倍速。技术分镜继承导演 pacingPlan:优先压缩已读懂的建立、重复信息和动作尾巴,保护关键内容最低可读时间与转折后的反应。总时长变化超过 15% 必须记录并审批导演偏差;分镜不得静默改变节奏意图。

Step 3 — 方案检查(最终校验在素材与提示词完成后)

素材未生成、h3Prompt 仍为空时,先人工对账节拍覆盖、台词承载、轴线、时长与资产需求。可用 checkup 列诊断,但提示词/参考验收缺失属于未完成项,不能声称最终校验通过,也不能伪填 approved 或假提示词只为过门。现有 validate 是完整交付校验,没有草稿放行模式。

Step 4 — 出分镜图(可选)

按项目画幅逐切准备构图规划图;只有选用关键帧模式时才称首/尾帧,走 codex 内置 $imagegen,读 {baseDir}/references/frame.md 照契约做。要点:

  • 没有 codex 就整步跳过,只交提示词,报告显示占位不装有
  • 参考图按职责而不是按数量选择:默认优先干净的人物身份、场景全局方位/拓扑、关键道具和内容资产。动作/构图参考是高风险可选项,只有肢体、支撑点、持物手、屏幕方向和空间轴线全部正确才可使用。相近的人脸特写、同角度重复图和互相冲突的手别/服装不得进入 Ref2VA;必要时改用 semantic-assets,让提示词调度镜头
  • 一格一次调用绝不批量;输出 ./<段号>/f<切序>.png(f1 = 主分镜图,每段一个文件夹)
  • 默认先出第一段的整套分镜图给用户看效果(3–5 张),确认画风和正反打构图再往后补——一集约 30–40 格,错了浪费的是整批
  • 候选图先做资产 QC:人物身份、场景拓扑、躺/坐/站、身体支撑点、持物手、屏幕方向和关键信息占比逐项检查。画面裁掉了证明姿态所需的接触点,就不能因为“看起来好看”而通过
  • 手机/电脑/文件承载剧情关键信息时,按 information.displayStrategy 生成插入镜头、全屏内容素材或可跟踪屏幕;精确文字走后期合成
  • 单个失败跳过不阻断,最后汇总说明
Step 4.5 — 素材验收后写最终 H3 提示词

只有候选素材的真实文件、顺序、职责与 QC 状态已确定,才写每段最终 h3Prompt。必须同时使用 MiniMax 官方 h3-prompt-writing skill,并完整读取当前模式参考。{baseDir}/references/h3-prompt.md 只负责输入映射和质量门衔接。

Ref2VA 把审核通过的参考写入显式 references;设置 referenceQcRequired: true 时,每项还要列出 requiredChecks、checks 和 reviewStatus: approved。最终提示词必须描述真实图片里存在的姿态和构图,不能用文字强行纠正一张已经错误的参考图。

Show full SKILL.md (156 more words)Show less
Step 4.6 — 完整校验与投产前复核

素材、参考顺序与最终提示词完成后运行:

bash
node {baseDir}/scripts/novel-storyboard.mjs validate <storyboard.json> --script <script.json> --outline <outline.json> --cast <cast.json> --art <art.json>

修复结构、节拍、切点、声音与模式错误后再 export。只有 T2VA 可没有输入图片;需要参考的模式缺图时交付未完成清单。不要把每切规划图全部塞入 Ref2VA。官方结构以 h3-prompt-writing 为准,本地 references/h3-prompt.md 仅管字段映射与工具约束。

Step 5 — 输出与汇报
bash
cd <输出目录>
node {baseDir}/scripts/novel-storyboard.mjs render <剧名>-storyboard.json --md \
  --script <script.json> --outline <outline.json> --art <art.json> > <剧名>-storyboard.md
node {baseDir}/scripts/novel-storyboard.mjs render <剧名>-storyboard.json --html \
  --script <script.json> --outline <outline.json> --art <art.json> > storyboard-report.html

报告界面语言用 --lang zh|en 指定(优先级 --lang > JSON 顶层 lang 字段 > 默认中文)——只切界面标签,与 promptLang(H3 提示词语言)互相独立。render 自动去 images/<镜号>-frame.png 找首帧(批次单还会找场景设定图),先出图再 render。报告含:KPI 带、分镜节奏带(粗分隔 = 段边界、片宽 = 分镜时长占比、颜色深浅 = 景别远近、点击跳段卡)、分集分镜表(主分镜图 + 子分镜条 + 逐切分镜行 + 分镜图/H3 提示词复制按钮)、生成批次单、配音对齐单、质量门、导出 JSON。Markdown 版每段附完整 H3 提示词,直接复制可用。

汇报一句话说清:几集几镜、总时长 vs 目标、几个生成批次、出了几张首帧、报告路径;没过的门和没出的图明说。

最终落地:

<输出目录>/
├── <剧名>-storyboard.json
├── <剧名>-storyboard.md
├── storyboard-report.html         ← 双击就能开
├── manifest.json                  ← export 生成
└── E01-01/                        ← 一段一个文件夹 = 一次 H3 生成的全部材料
    ├── ref-*.png                  ← Ref2VA 按职责命名的参考图;不代表切点关键帧
    ├── f1.png / f2.png …          ← 仅在关键帧模式或评审需要时保留
    └── prompt.md                  ← H3 提示词(export 生成)
Step 6 — CompShare H3 API 投产(可选、需明确授权)

用户要求“生成视频、调用 API、提交 H3”时,先读 {baseDir}/references/h3-api.md,使用 {baseDir}/scripts/h3-api.py。API 调用会上传参考图并消耗积分,不能从“出分镜”自动推断授权。

固定风控:

  • 默认只提交一个 4–15 秒段做测试;用户看过成片并明确同意后才批量。
  • 优先在 job 中用本地 path;脚本把图片编码成 Data URL 并校验 SHA-256,发现重复图直接拒绝。
  • 公网 url 仅用于稳定直链;多个链接的末级文件名相同(例如都叫 /download)时拒绝提交,避免平台缓存串图。
  • API key 只从 COMPSHARE_H3_API_KEY、COMPSHARE_H3_KEY_FILE 或 ~/.codex/secrets/compshare-h3.key 读取;不得写进 job、提示词、日志或交付物。
  • 提交前运行 preflight 和 submit --dry-run;核对参考图数量、不同哈希、画幅、分辨率、时长和输出路径。
  • 用户要求干净画面时,在 promptSuffix 明写禁止字幕、标题、Logo、水印;生成后仍需看成片验证,不能只凭提示词宣称成功。
  • API 返回 failed/cancelled 就停止,不自动重试付费任务。只有连接失败且确认服务端未创建任务时,才可在用户授权范围内重试。

创作到生产的交接

novel-characters → cast.json       (谁:角色设定图)
novel-outline    → outline.json    (什么:结构与分集)
novel-art        → art.json        (哪里:场景/道具设定图)
novel-script     → script.json     (戏:场次、节拍、台词)
novel-storyboard → storyboard.json (怎么拍:镜头、首帧、批次)

分镜消费剧本和已批准导演意图;采用总控导演桥接路线时不再重复执行本 skill 重切。标准分镜路线则保留导演来源与偏差说明。投产包交总控完成成本授权、任务执行、选片、剪辑和 QC;技术分镜交付不等于整剧闭环,台词清单也不默认触发全剧 TTS。

边界

  • 报告界面内置中英(--lang,默认中文);H3 执行提示词 promptLang 固定为 en,中文只保留对白、歌词和可见文字。中文自由 brief 可在独立 Context-IR 实验中使用,但不是正式六段式输出
  • 秒数是下给视频模型的生成时长不是估算——段上限按你的模型改 params.maxSegmentSeconds,切的节奏区间改 min/maxCutSeconds
  • 口型/唇形同步暂不管——那是生成管线的事
  • 分镜图按用途验收:审阅图可带明确缺口,模型参考图必须满足当前镜头的身份、姿态与信息要求;不能把未解决问题默认推给付费重生成
  • API 调用不是分镜交付的默认步骤;任何提交、重试、批量生成都受用户当次授权和成本边界约束

自测

bash
node {baseDir}/scripts/selftest.mjs

自测不调模型、不花额度。19 道质量门每一道都有击穿用例。改完脚本先跑这个。

自带样例

{baseDir}/examples/渡口-storyboard.json:《渡口》第 1 集完整分镜——10 段 34 切认领剧本全部 35 拍,平均 3.5 秒一切,共 119 秒 / 目标 120 秒,2 个生成批次,每段带完整的 H3 视频提示词(多图对齐 + 切点时刻全部对账通过)。当质量基准,也是自测夹具。

制作交接

独立使用时,自检后主动打开当前报告并给绝对路径链接,说明本轮范围、检查重点和下一步;需要锁定内容时在对话中收取通过或修改结论。已有确认覆盖当前版本就不重复询问,打开页面或下载 JSON 不算批准。总控已接管时,由总控统一收取这次结论,不另开重复审批。当前内容、依赖或源图改变后,不因旧文件仍存在就跳过复核;输出新版本并保留原审阅笔记。

本项目的阶段职责、变更记录和交付顺序由 short-drama-production 的 references/company-workflow.md 统一维护;未安装总控时按本 skill 的输入和交付范围独立完成,不将总控变成硬依赖。

涉及尚未授权的创作取舍时,给用户 2–3 个有具体差异的选项,说明收益、损失与推荐,允许保留原稿或自定义。模型先完成阅读、诊断和短样段,不把准备工作推给用户;已经明确授权的范围直接执行。未经用户选择,不把暂定片长预算升级成删词、删情绪段落的理由。

© suihe1, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 14 other files (scripts, references, assets) in skills/novel-storyboard of suihe1/short-drama-production.

  • SKILL.md
  • README.en.md
  • README.md
  • assets/report.webp
  • examples/渡口-storyboard.json
  • references/frame.md
  • references/h3-api.md
  • references/h3-prompt.md
  • references/report-style.md
  • references/schema.md
  • references/storyboard-pass.md
  • scripts/h3-api.py
  • scripts/novel-storyboard.mjs
  • scripts/save-h3-key.ps1
  • scripts/selftest.mjs

Open the folder on GitHubat commit dbd3310

Compare with similar skills

Novel Storyboard next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Novel Storyboard compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Novel Storyboard this skillsuihe1/short-drama-production181—~2.1kAutomated safety check: NotesApache-2.0
Novel Storyboardeternityspring/shuohao-skills4.3k—~1.8kAutomated safety check: NotesApache-2.0
H3 Cinematic Directorjtydhr88/ComfyTV1.1k—~2.7kAutomated safety check: PassMIT
Storyboard Managerailabs-393/ai-labs-claude-skills4551 repos~4.6kAutomated safety check: PassMIT
Minimax H3 Reference Video Promptunknowlei/minimax-h3-opencode-skills122—~3kAutomated safety check: PassMIT
Minimax H3 Text Video Promptunknowlei/minimax-h3-opencode-skills122—~2.3kAutomated safety check: PassMIT

Similar skills

  • Novel Storyboard

    eternityspring/shuohao-skills

    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)。

    4.3k GitHub stars~1.8k tokensUpdated 3 days ago
    Media & CreativeAuto-check: notes
  • H3 Cinematic Director

    jtydhr88/ComfyTV

    Convert approved scripts, shot briefs, storyboards, keyframes, character sheets, scene assets, prop sheets, and sound briefs into director-level storyboards and production-ready MiniMax H3 prompts.

    1.1k GitHub stars~2.7k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed
  • Storyboard Manager

    ailabs-393/ai-labs-claude-skills

    Assist writers with story planning, character development, plot structuring, chapter writing, timeline tracking, and consistency checking.

    455 GitHub starsUsed in 1 repo~4.6k tokens
    Media & CreativeAuto-check passed
  • Minimax H3 Reference Video Prompt

    unknowlei/minimax-h3-opencode-skills

    Default downstream MiniMax H3 specialist for every image-based request unless the user explicitly declares boundary-only first/last frames with no reusable reference role.

    122 GitHub stars~3k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Minimax H3 Text Video Prompt

    unknowlei/minimax-h3-opencode-skills

    Downstream MiniMax H3 specialist for professional text-to-video (T2VA) prompts using the official three-field format.

    122 GitHub stars~2.3k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Papercraft Stop Motion Explainer

    tl2012tl/comfyUI-llama-TE

    For creators explaining science, education, or general knowledge through tactile handmade papercraft visuals.

    241 GitHub starsUsed in 4 repos~5.7k tokens
    Media & CreativeAuto-check passed

More from suihe1/short-drama-production

  • Novel Art

    suihe1/short-drama-production

    为 AI 短剧设计场景和叙事道具母本、光照与状态变体,产出 art.json、Markdown、评审报告和可选设定图。用于美术设定、场景与道具一致性;不代替导演调度或成片人流设计。

    181 GitHub stars~1.3k tokensUpdated 25 days ago
    Auto-check: notes
  • Novel Characters

    suihe1/short-drama-production

    从故事中整理人物身份、关系、外观和声线设计,产出角色卡、图像提示词与评审报告,可按需生成设定图。用于角色分析、人物画像和角色母本;短剧制作中按已批准大纲与当前批次选角。

    181 GitHub stars~1.8k tokensUpdated 25 days ago
    Auto-check: notes
  • Novel Outline

    suihe1/short-drama-production

    把小说或故事改编为短剧大纲,确定人物去留、分集因果、剧情重点与资产预算,产出可校验 JSON、Markdown 和评审报告。用于短剧大纲、改编方案和现有大纲诊断;不写完整剧本或镜头方案。

    181 GitHub stars~1.3k tokensUpdated 25 days ago
    Auto-check: notes
  • Novel Script

    suihe1/short-drama-production

    将分集大纲写成结构化场次、动作节拍和逐句台词,核对人物与美术引用、估算时长并交付剧本评审报告。用于写剧本、对白和场次修订;不分镜、不直接执行配音或视频生成。

    181 GitHub stars~658 tokensUpdated 25 days ago
    Auto-check: notes
  • Short Drama Production

    suihe1/short-drama-production

    统筹 AI 短剧的阶段、依赖、审批、H3 任务、声音资产、粗剪和 QC,并用 production.json 追踪返工;默认支持 16:9。用于整部短剧生产、继续项目、状态检查或上游变更影响分析;单独创作大纲、角色、美术、剧本或分镜时使用对应专业 skill。

    181 GitHub stars~1.1k tokensUpdated 25 days ago
    Auto-check passed
  • Short Drama Director

    suihe1/short-drama-production

    把剧本转成表演、场面调度、镜头覆盖、景别、机位、运镜与剪辑意图,产出可校验导演镜头包。用于导演方案、拍法、镜头诊断和分镜重构;只要求大纲、剧本或资产设定时不触发。

    181 GitHub stars~1.2k tokensUpdated 25 days ago
    Auto-check passed

Works with

Questions about Novel Storyboard

What does Novel Storyboard do?

将剧本与导演意图转成生成段、逐镜时间、参考素材计划和可校验分镜报告;使用官方 h3-prompt-writing 编写 H3 提示词,可导出投产包。用于技术分镜、镜头表和分镜修订;生成视频须另有明确任务与成本授权,不负责最终选片或剪辑。. Novel Storyboard is an agent skill from suihe1/short-drama-production.

When should I use Novel Storyboard?

Novel Storyboard fits situations like: tasks that involve Comics and storyboards; tasks that involve Creative writing and fiction.

How do I install Novel Storyboard in Claude Code?

Run `npx skills add suihe1/short-drama-production --skill novel-storyboard -a claude-code`. Or copy the skill folder (skills/novel-storyboard in suihe1/short-drama-production) into .claude/skills/novel-storyboard in your project. Claude Code loads it when a task matches its description.

How do I install Novel Storyboard in Codex?

Run `npx skills add suihe1/short-drama-production --skill novel-storyboard -a codex`. Or copy the skill folder (skills/novel-storyboard in suihe1/short-drama-production) into .agents/skills/novel-storyboard in your project. Codex loads it when a task matches its description.

Can I use Novel Storyboard in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add suihe1/short-drama-production --skill novel-storyboard -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/novel-storyboard, .gemini/skills/novel-storyboard, .github/skills/novel-storyboard and .opencode/skills/novel-storyboard in your project.

What does Novel Storyboard need to run?

Going by SKILL.md and its folder, Novel Storyboard needs JavaScript, Python and PowerShell for the scripts in its folder, the command-line tools its instructions call (node) and credentials named COMPSHARE_H3_API_KEY. Our summary lists: Python 3; Node.js; PowerShell. Its frontmatter pre-approves these tools: Read, Write, Bash, Task, Glob.

Does Novel Storyboard access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Novel Storyboard safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Novel Storyboard use?

Novel Storyboard is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Novel Storyboard use?

About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.5k tokens, read only when the agent opens those files.

What are the alternatives to Novel Storyboard?

Skills that share tags, products or a category with Novel Storyboard: Novel Storyboard (eternityspring/shuohao-skills, 4.3k stars), H3 Cinematic Director (jtydhr88/ComfyTV, 1.1k stars), Storyboard Manager (ailabs-393/ai-labs-claude-skills, 455 stars) and Minimax H3 Reference Video Prompt (unknowlei/minimax-h3-opencode-skills, 122 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Novel Storyboard?

suihe1 (a GitHub user) maintains it in suihe1/short-drama-production, which has 181 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on September 16, 2026.

Source: suihe1/short-drama-production on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.