Agent skill

Production Art Prompt Designer

by Supreme-Ultimate in Supreme-Ultimate/novel-to-script-team

Turns the character and scene lists from a director analysis into detailed text-to-image prompts for character sheets, scenes and props, after confirming a visual style with you.

MITAuto-check passedMedia & Creative

SKILL.md written in Chinese; this summary is our English description.

Install Production Art Prompt Designer

skills CLI
$ npx skills add Supreme-Ultimate/novel-to-script-team --skill art-design-skill -a claude-code

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

GitHub CLI
$ gh skill install Supreme-Ultimate/novel-to-script-team art-design-skill --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/Supreme-Ultimate/novel-to-script-team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/art-design-skill .claude/skills/art-design-skill && 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
art-design-skill
GitHub stars
175
Token cost
~1.8k tokens
SKILL.md length
314 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

Turns the character and scene lists from a director analysis into detailed text-to-image prompts for character sheets, scenes and props, after confirming a visual style with you.

  • Works in 7 steps: ../../references/00-first-principles.md → ../../references/10a-action-dialogue-scen… → ../../references/10b-atmosphere-fantasy.md → …
  • Writing text-to-image prompts for characters in a screenplay adaptation
  • SKILL.md covers 必读, 进阶参考(按需查阅), 技能说明 and 输入, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

The SKILL.md is in Chinese and belongs to a novel-to-screenplay pipeline. It reads a set of required reference files on first principles, action scenes, atmosphere, image and motion prompts, genre techniques, a micro-drama storyboard visual dictionary and frame description elements, with color psychology and lighting guides on demand. Character prompts describe one image with a face close-up on the left and front, side and back full-body views on the right against white. Scene prompts are written per scene with the shot size and angle.

Output goes to three accumulating files per script, one each for characters, scenes and props, and scenes and props must stay separate. Step zero is mandatory: ask which visual style to use, such as hyper-realistic, realistic illustration, anime, 3D render or a custom one, and write it as a style statement at the top. Prompts are then designed only for items marked new or variant, with a dependency analysis so derived scenes reference a base scene. The excerpt is cut off in the props strategy.

When your agent uses it

  • Writing text-to-image prompts for characters in a screenplay adaptation
  • Creating consistent scene reference prompts from a scene list
  • Designing prop prompts on white backgrounds for a short drama project
  • Locking a visual style before generating any reference images

Example prompts

  • “Turn the character list from the director analysis into character sheet prompts.”
  • “Write scene prompts for the studio scenes, with the wide shot as the base and derived scenes referencing it.”
  • “Ask me which visual style to use and then write the prop prompts.”
  • “Add prompts only for the new and variant items in the updated scene list.”

Requirements

  • A character and scene list from a director analysis step

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

  1. ../../references/00-first-principles.md
  2. ../../references/10a-action-dialogue-scenes.md
  3. ../../references/10b-atmosphere-fantasy.md
  4. ../../references/11b-image-motion-prompt.md
  5. ../../references/12-genre-specific-techniques.md
  6. ../../references/19-micro-drama-storyboard-system.md — 微短剧分镜两阶段系统(第一阶段:视觉词典)
  7. ../../references/20-frame-description-elements.md(帧图描述完整元素表)

What it can do on your machine

Read from SKILL.md and the folder at commit 117dceb. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    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 no API keys, tokens, secrets or passwords.

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

Context cost

Production Art Prompt Designer loads about 1.8k tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 314 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~16
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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 passed

The automated check found no risky patterns in SKILL.md.

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from Supreme-Ultimate/novel-to-script-team at commit 117dceb, republished under its MIT licence (© Supreme-Ultimate). 314 words, ~1,798 tokens.

Download SKILL.mdSave it as .claude/skills/art-design-skill/SKILL.md (or your agent's skills folder).
name
art-design-skill
description
服化道设计技能。将导演分析产出的人物清单和场景清单转化为可直接用于文生图工具的详细提示词。

服化道设计技能

必读

  1. ../../references/00-first-principles.md
  2. ../../references/10a-action-dialogue-scenes.md
  3. ../../references/10b-atmosphere-fantasy.md
  4. ../../references/11b-image-motion-prompt.md
  5. ../../references/12-genre-specific-techniques.md
  6. ../../references/19-micro-drama-storyboard-system.md — 微短剧分镜两阶段系统(第一阶段:视觉词典)
    • 使用时机:AI微短剧项目,创建角色和场景提示词时
    • 核心价值:参考视觉词典的角色词条、场景词条、物件词条标准,确保描述精度和可复制性
    • 关键要求:外貌锁定(5个以上可视化细节)、服装档案(可直接复制的完整描述)、空间锁定(材质、色彩、氛围)
  7. ../../references/20-frame-description-elements.md(帧图描述完整元素表)

进阶参考(按需查阅)

  • ../../references/15-color-psychology.md — 色彩心理学(色彩情绪映射、色彩叙事、类型化色彩)
    • 使用时机:设计场景色调、角色服装色彩时
  • ../../references/17-lighting-narrative.md — 光影叙事(光影情绪映射、光线类型与情绪)
    • 使用时机:设计场景光照状态时

技能说明

美术设计技能,将导演提供的人物清单和场景清单转化为可直接用于文生图工具生成参考图的详细提示词。

人物提示词出图格式:一张图,左半边面部特写,右半边全身正面/侧面/背面设定图,白色背景。

场景提示词出图格式:每个场景独立出图。根据分镜需求标注对应的景别和视角(如全景/俯拍/仰拍/POV等),确保参考图匹配实际拍摄视角。

输入

  1. 导演分析产出中的人物清单和场景清单
  2. 已有的 outputs/{剧本名}/assets/character-prompts.md、outputs/{剧本名}/assets/scene-prompts.md 和 outputs/{剧本名}/assets/prop-prompts.md(如存在)

输出

  1. outputs/{剧本名}/assets/character-prompts.md — 人物提示词(跨集累积,追加式写入)
  2. outputs/{剧本名}/assets/scene-prompts.md — 场景提示词(跨集累积,追加式写入)
  3. outputs/{剧本名}/assets/prop-prompts.md — 物品/道具提示词(跨集累积,追加式写入)

重要:场景和物品必须分开两个文件,不得混在一起。

执行流程

第零步:确认视觉风格(必须与用户确认)

在生成任何提示词之前,必须先与用户确认视觉渲染风格。 这是最高优先级的决策,直接影响所有提示词的写法。

向用户提供以下选项(或用户自定义):

风格说明适用场景
超写实(Hyper-realistic)照片级真实感,皮肤毛孔、光影物理准确Seedance 写实视频、真人短剧
写实插画(Realistic Illustration)半写实绘画风格,保留手绘质感动态漫画、概念设定
动漫风(Anime/Manga)日系动漫风格动态漫画、二次元项目
3D 渲染(3D Render)Pixar/Blender 风格的 3D 角色3D 动画项目
其他用户自定义风格—

确认后,将风格写入提示词文件的头部作为「视觉风格声明」,所有后续提示词必须遵循此风格。

示例:

**视觉风格声明**:超写实风格(Hyper-realistic),照片级真实感,自然光影,皮肤质感细腻真实,电影摄影质感

重要:不得跳过此步骤。不得自行假设风格。必须等用户明确选择后再继续。

第一步:读取上游产物
  • 读取导演分析产出中的人物清单和场景清单
  • 读取已有的 outputs/{剧本名}/assets/character-prompts.md、outputs/{剧本名}/assets/scene-prompts.md 和 outputs/{剧本名}/assets/prop-prompts.md(如存在),了解已设计的人物、场景和物品
  • 根据人物清单和场景清单中的"素材状态"列,只为标注为"新增"或"变体"的项设计提示词
  • "复用"项跳过,不需要设计
第一点五步:依赖关系分析(必须在写提示词之前完成)

在开始写任何提示词之前,必须先完成依赖关系分析。 这是保证视觉一致性的关键步骤。

分析三类依赖关系:

① 场景 → 场景依赖(空间一致性)

  • 同一叙事空间的不同机位/状态必须共享空间基因(墙面材质、家具布局、色温体系)
  • 识别"基础场景"(第一次出现的全景)和"派生场景"(同空间的其他机位/时间变体)
  • 派生场景添加 **参考图**:场景 XX(XX 为基础场景编号)

示例:

工作室全景(场景01)→ 基础
工作室桌面俯拍(场景02)→ 参考图:场景 01
工作室黑暗(场景09)→ 参考图:场景 01

② 物品 → 白底独立策略(与人物一致)

  • 物品采用和人物相同的白底独立出图策略:白色干净背景,不引用场景
  • 不添加 **所在场景** 或 **参考图**:场景 XX
  • 物品提示词只描述物品本身的材质、颜色、尺寸、质感等视觉属性
  • 光线使用中性白色摄影棚光(非场景光),确保物品细节清晰可辨

③ 场景 → 人物引用(角色一致性)

  • 场景提示词中出现角色时,必须从 character-prompts.md 中复制对应角色的关键描述(服装、发型、标志性特征),不得凭记忆重写

④ 场景 → 物品引用(道具一致性)

  • 所有在场景提示词中有主体描述的物品,都必须添加 **参考图**:物品 XX 并用"(参见参考图 物品 XX)"替代内联描述
  • 不得在场景提示词中重新描述物品的外观(材质、尺寸、颜色等),这些信息已在 prop-prompts.md 中定义
  • 场景提示词中只描述物品在场景中的位置、状态(如"光束在弹跳"、"面朝下扣着")和与场景光线的交互
  • 即使物品只是桌面上的一个小元素,只要提示词中提到了它的名称,就必须加参考图
  • 禁止使用泛称代替具体物品编号:不得写"桌面回路装置发光"或"一个镜子回路装置",必须写明具体是哪个物品(如"三角形回路装置(参见参考图 物品 01)")。如果是多个物品,逐一列出编号
  • 唯一例外:完全模糊不可辨认的背景元素(如"远处置物架上的工具盒")

⑤ 物品 → 角色关联(标记式引用,不内联描述)

  • 物品如果与角色相关(如发卡是妻子的),添加 **关联角色**:人物 XX(角色名)
  • 物品提示词中不得内联描述人物外貌,如需角色出现在物品中(如照片里的人),使用 **参考角色**:人物 XX 标记,让生图脚本自动引用角色参考图
  • 物品提示词只描述物品本身,角色信息通过标记传递

⑥ 同族物品一致性(家族一致性)

  • 属于同一"家族"的物品(如多个回路装置)共享材料体系(框架材质、镜片规格、铰链类型)
  • 先定义家族共性,再描述个体差异
  • 后续同族物品添加 **参考图**:物品 XX(XX 为家族第一个物品编号)

输出:在开始写提示词前,先输出一张依赖关系表,格式:

## 依赖关系表

### 场景依赖
| 场景 | 类型 | 参考 | 原因 |
|------|------|------|------|
| 场景 01 | 基础 | — | 工作室首次出现 |
| 场景 02 | 派生 | 场景 01 | 同一工作室,俯拍机位 |
| ...

### 物品依赖(白底独立,仅标记同族和角色关联)
| 物品 | 家族 | 参考物品 | 关联角色 | 说明 |
|------|------|---------|---------|------|
| 物品 01 | 回路装置 | — | — | 家族基础物品 |
| 物品 02 | 回路装置 | 物品 01 | — | 同族变体 |
| 物品 04 | — | — | 人物 02 妻子 | 妻子的发卡 |
| ...

### 角色引用
| 场景/物品 | 引用角色 | 引用内容 |
|-----------|---------|---------|
| 场景 04 | 人物 02 妻子 | 服装+发型+标志特征 |
| ...
第二步:设计人物造型提示词

为每个人物编写设定提示词:

出图布局:

  • 一张图,左半边面部特写,右半边全身正面/侧面/背面三视图设定图
  • 白色干净背景
  • 渲染风格遵循「视觉风格声明」(第零步确认的风格)

提示词必须包含:

  • 角色整体定位(年龄、性别、国籍/民族特征)
  • 面部细节:脸型、五官、肤色、发型/发色、表情
  • 体型:身高、体态
  • 服装:款式、颜色、材质、细节
  • 配饰:手表、耳环、眼镜、包等
  • 鞋子
  • 整体气质

26 元素框架补充(参见 references/20-frame-description-elements.md):

  • 人物朝向:角色的默认呈现角度(正面 / 四分之三侧面)
  • 表情眼神:角色的默认/标志性表情
  • 典型位置:角色在画面中的典型位置
第三步:设计场景环境提示词

排列顺序:基础场景排在前面,派生场景排在后面(确保生图时基础场景先生成)。

一致性规则:

  • 派生场景的空间描述必须从基础场景复制核心元素(墙面、家具、地面),只修改差异部分(机位、光线、时间)
  • 场景中出现角色时,从 character-prompts.md 中复制该角色的外貌和服装描述,不得简化或重写
  • 派生场景必须添加 **参考图**:场景 XX

每个场景标注:

  • 对应分镜编号和出图视角
  • 参考图(如果是派生场景)

每个场景提示词必须包含:

  • 地点类型与空间布局
  • 时间(影响光照)
  • 光源类型与光线方向
  • 整体色调/色彩倾向
  • 关键道具/家具/物件
  • 空间纵深与层次
  • 氛围/情绪
  • 人物在场状态(必须显式声明):无人场景写"画面中无人";有人场景用"(参见参考图)"指定具体角色。不得省略——AI 生图模型会对未声明的画面自行脑补人物

26 元素框架补充(参见 references/20-frame-description-elements.md):

  • 默认机位角度:该场景的典型拍摄视角(平视 / 俯拍 / 仰拍)
  • 画面层次:前景 / 中景 / 背景的典型元素描述
  • 画幅比例:16:9(标准)
  • 空间布局与相对位置:人物与环境的典型距离和包围关系

所有场景提示词必须保持视觉风格统一(遵循整体风格声明),光影逻辑自洽。

第四步:设计物品/道具提示词

排列顺序:同族物品中,基础物品排在前面,后续物品排在后面。

一致性规则:

  • 物品采用白底独立策略,与人物出图策略一致:白色干净背景,中性摄影棚光
  • 不添加 **所在场景** 或 **参考图**:场景 XX
  • 同族物品共享材料体系描述,只写差异部分
  • 同族后续物品添加 **参考图**:物品 XX(家族第一个物品)
  • 与角色相关的物品添加 **关联角色**:人物 XX(角色名)
  • 物品中需要角色出现时(如照片),使用 **参考角色**:人物 XX 标记,不得在提示词中内联描述人物外貌

多角度布局:一张图,展示正面、侧面、俯视三个角度(或根据道具特点调整)

每个道具提示词必须包含:

  • 尺寸、形状、材质
  • 颜色、质感、磨损/使用痕迹
  • 关键细节特征
  • 整体质感描述
第五步:输出

按照标准格式,分别写入三个文件:

  • 人物提示词 → 追加到 outputs/{剧本名}/assets/character-prompts.md
  • 场景提示词 → 追加到 outputs/{剧本名}/assets/scene-prompts.md
  • 物品/道具提示词 → 追加到 outputs/{剧本名}/assets/prop-prompts.md

重要:场景和物品/道具必须分开两个文件,不得混在同一个文件中。

首集时创建文件,后续集数追加新增/变体条目到文件末尾。

条目标题格式规范(严格执行)

生图脚本通过标题格式识别可生图条目。不符合格式的段落会被跳过。

统一标题级别:所有条目使用 ##(二级标题),三个文件保持一致。

标题格式:

## {类型} {编号}:{名称}({集数} 新增/变体)

示例:

## 人物 01a:归档者(ep01 新增)
## 场景 03:镜子空间(ep01 新增)
## 物品 02:菱形镜子回路装置(ep01 新增)

规则:

  • 类型只能是 人物、场景、物品 三种
  • 编号紧跟类型,用空格分隔(如 01a、03、02)
  • 编号后必须跟中文冒号 : 或英文冒号 :
  • 非条目内容(如家族共性说明、依赖关系表)不得使用 ## 标题,改用加粗文本或引用块
  • 文件头部元数据(项目、版本、风格声明等)不使用 ## 标题

禁止:

## 回路装置家族共性说明    ← 错误:非条目不得用 ## 标题
### 场景 01:...           ← 错误:不得用 ### 标题
## 依赖关系表              ← 错误:非条目不得用 ## 标题

正确的非条目写法:

**回路装置家族共性说明**

以下三个回路装置共享同一材料体系:
- 框架:...
参考图标记格式

生图脚本通过以下标记自动识别依赖关系并传入参考图:

**参考图**:场景 01        ← 引用场景图
**参考图**:物品 01        ← 引用物品图
**参考角色**:人物 01a     ← 引用角色图(人物变体专用)

标记放在条目标题下方、提示词正文之前。生图脚本会自动查找对应的已生成图片作为 API 参考图输入。

提示词写法原则

参考 references/11b-image-motion-prompt.md,核心要点:

纯视觉描述:提示词中只包含视觉元素的描述,不得出现任何要求模型在图上添加文字、标注、水印、箭头、色板等非视觉内容的指令。如需图片无文字,在提示词中明确写"画面中没有任何文字、标签或标注"。

叙事描述式:用完整段落描述,不要关键词堆叠

  • ✗ "穿红色衣服"
  • ✓ "穿深红色修身棉袄外套,内搭碎花棉布衫"

具体化:所有描述必须具体到可视化的程度

  • ✗ "室内场景"
  • ✓ "现代都市写字楼的开放式办公区,大部分工位已空"

摄影术语融入自然语言:不要孤立列出术语,而是描述其效果

情绪通过视觉细节传达:不要抽象描述

注意事项

  • 人物提示词必须明确"左半边面部特写 + 右半边三视图"的布局要求
  • 场景提示词要包含足够的环境细节以确保场景可信度和一致性
  • 如果是为变体设计(如同一人物的冬装版),需在提示词中注明与原版的关联和差异
  • 所有提示词必须完整可用,用户可以直接复制到文生图工具生成图片
  • 每个条目标注创建集数(如 ep01 新增),便于追溯

成功标准

  1. 人物提示词包含所有必需元素(年龄、五官、体型、服装、配饰、气质)
  2. 场景提示词包含所有必需元素(地点、时间、光线、色调、道具、氛围)
  3. 提示词采用叙事描述式,不使用关键词堆叠
  4. 所有描述具体到可视化程度
  5. 场景宫格保持视觉风格统一
  6. 只为"新增"和"变体"项编写提示词,"复用"项跳过

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

Files

Just SKILL.md in skills/art-design-skill of Supreme-Ultimate/novel-to-script-team.

Open the folder on GitHubat commit 117dceb

Compare with similar skills

Production Art Prompt Designer 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.

Production Art Prompt Designer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Production Art Prompt Designer this skillSupreme-Ultimate/novel-to-script-team175—~1.8kAutomated safety check: PassMIT
Canghe Comicfreestylefly/canghe-skills4618 repos~3.2kAutomated safety check: PassNone
Seedance Storyboard Generatorliangdabiao/Seedance2-Storyboard-Generator2.6k—~2.2kAutomated safety check: PassNone
Xhs ImagenNimaChu/xhs-imagen120—~2.3kAutomated safety check: PassMIT
Hbg Life SimulationMr-funny/hbg-life-simulation141—~5.8kAutomated safety check: PassMIT
Whiteboard Videognipbao/codex-whiteboard-video-skill327—~7.2kAutomated safety check: NotesMIT

Similar skills

  • Canghe Comic

    freestylefly/canghe-skills

    Knowledge comic creator supporting multiple art styles and tones.

    461 GitHub starsUsed in 8 repos~3.2k tokens
    Media & CreativeAuto-check passed
  • Seedance Storyboard Generator

    liangdabiao/Seedance2-Storyboard-Generator

    专业的Seedance 2.0平台AI视频脚本和分镜生成器。当用户要求:(1) 将文章/故事转换为视频脚本,(2) 生成Seedance 2.0分镜提示词,(3) 规划多集AI视频系列,(4) 为GPT-Image-2、Seedream、Nano Banana…

    2.6k GitHub stars~2.2k tokensUpdated 19 days ago
    Media & CreativeAuto-check passed
  • Xhs Imagen

    NimaChu/xhs-imagen

    Create complete Xiaohongshu image-and-text posts from a topic, article, document, or rough idea, including research, fact checking, post copy, pagination, storyboards, a 3:4 cover, 9:16 content…

    120 GitHub stars~2.3k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Hbg Life Simulation

    Mr-funny/hbg-life-simulation

    Create Chinese HBG “模拟人生 / 人生副本” narrative videos with a consistent comic IP, a rapid multi-life opening, continuous natural-speed narration, synchronized short captions, dense static manga…

    141 GitHub stars~5.8k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed
  • Whiteboard Video

    gnipbao/codex-whiteboard-video-skill

    Generate smooth hand-drawn whiteboard and story videos directly inside Codex from text scripts, GPT Image 2 color storyboards, scene plans, SVGs, line art, or local images.

    327 GitHub stars~7.2k tokensUpdated 1 mo ago
    Media & CreativeAuto-check: notes
  • Knowledge Comic Creator

    JimLiu/baoyu-skills

    Writes original educational comics with detailed panel layouts in a chosen art style and tone, generating the images in batches through whichever backend is available.

    27k GitHub starsUsed in 2 repos~5.5k tokens
    Media & CreativeAuto-check passed

More from Supreme-Ultimate/novel-to-script-team

All 17 skills in this repo
  • Art Direction Review

    Supreme-Ultimate/novel-to-script-team

    Reviews costume, makeup and prop design prompts for characters and scenes in a novel-to-film pipeline, scoring each one and returning PASS or FAIL with a problem list.

    175 GitHub stars~918 tokensUpdated 5 mo ago
    Auto-check passed
  • Script Comparative Review Against Hits

    Supreme-Ultimate/novel-to-script-team

    Chinese-language skill that scores a generated short-drama script against a reference hit script on rhythm, dialogue style, emotional impact and structure, with PASS/FAIL thresholds.

    175 GitHub stars~1.8k tokensUpdated 5 mo ago
    Auto-check passed
  • Director Script Breakdown for Seedance

    Supreme-Ultimate/novel-to-script-team

    Breaks a script or outline into plot points and writes a director's walkthrough, character list and scene list sized for Seedance video generation.

    175 GitHub stars~1.3k tokensUpdated 5 mo ago
    Auto-check passed
  • Film Storyboard Prompt Builder

    Supreme-Ultimate/novel-to-script-team

    Turns a script, synopsis or scene outline into AI image prompts for storyboards, using a beat breakdown, a nine-panel Beat Board and four-panel Sequence Boards.

    175 GitHub stars~815 tokensUpdated 5 mo ago
    Auto-check passed
  • Hit Script Retrieval Skill

    Supreme-Ultimate/novel-to-script-team

    爆款剧本检索技能。使用混合搜索(语义+关键词)检索最相关的爆款剧本,为生成提供参考. An agent skill from Supreme-Ultimate/novel-to-script-team.

    175 GitHub stars~1.6k tokensUpdated 5 mo ago
    Auto-check passed
  • Image Generation Skill

    Supreme-Ultimate/novel-to-script-team

    调用 nano banana API(gemini-3.1-flash-image-preview)生成图片。支持纯文本生图和参考图生图。

    175 GitHub stars~640 tokensUpdated 5 mo ago
    Auto-check: notes

Questions about Production Art Prompt Designer

What does Production Art Prompt Designer do?

Turns the character and scene lists from a director analysis into detailed text-to-image prompts for character sheets, scenes and props, after confirming a visual style with you. md is in Chinese and belongs to a novel-to-screenplay pipeline. It reads a set of required reference files on first principles, action scenes, atmosphere, image and motion prompts, genre techniques, a micro-drama storyboard visual dictionary and frame description elements, with color psychology and lighting guides on demand.

When should I use Production Art Prompt Designer?

Production Art Prompt Designer fits situations like: writing text-to-image prompts for characters in a screenplay adaptation; creating consistent scene reference prompts from a scene list; designing prop prompts on white backgrounds for a short drama project; locking a visual style before generating any reference images.

How do I install Production Art Prompt Designer in Claude Code?

Run `npx skills add Supreme-Ultimate/novel-to-script-team --skill art-design-skill -a claude-code`. Or copy the skill folder (skills/art-design-skill in Supreme-Ultimate/novel-to-script-team) into .claude/skills/art-design-skill in your project. Claude Code loads it when a task matches its description.

How do I install Production Art Prompt Designer in Codex?

Run `npx skills add Supreme-Ultimate/novel-to-script-team --skill art-design-skill -a codex`. Or copy the skill folder (skills/art-design-skill in Supreme-Ultimate/novel-to-script-team) into .agents/skills/art-design-skill in your project. Codex loads it when a task matches its description.

Can I use Production Art Prompt Designer 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 Supreme-Ultimate/novel-to-script-team --skill art-design-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/art-design-skill, .gemini/skills/art-design-skill, .github/skills/art-design-skill and .opencode/skills/art-design-skill in your project.

What does Production Art Prompt Designer need to run?

SKILL.md names no scripts, command-line tools or credentials: Production Art Prompt Designer is instructions for the agent only. Our summary lists: A character and scene list from a director analysis step.

Does Production Art Prompt Designer 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 Production Art Prompt Designer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Production Art Prompt Designer use?

Production Art Prompt Designer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Production Art Prompt Designer use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Production Art Prompt Designer?

Skills that share tags, products or a category with Production Art Prompt Designer: Canghe Comic (freestylefly/canghe-skills, 461 stars), Seedance Storyboard Generator (liangdabiao/Seedance2-Storyboard-Generator, 2.6k stars), Xhs Imagen (NimaChu/xhs-imagen, 120 stars) and Hbg Life Simulation (Mr-funny/hbg-life-simulation, 141 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Production Art Prompt Designer?

Supreme-Ultimate (a GitHub organization) maintains it in Supreme-Ultimate/novel-to-script-team, which has 175 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on May 2, 2026.

Source: Supreme-Ultimate/novel-to-script-team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.