Factory MCP
warpdotdev/warp
Use the Warp Factory MCP to hand work to a software factory and collaborate with it — bundle local work and send it to the cloud, find factory tasks from a Slack thread / Linear ticket /…
AI短剧提示词工厂 - 端到端将小说/故事创意转化为结构化提示词包(角色立绘+场景+道具+分镜图片+视频+音频)的完整流水线。一个入口启动全流程,内部自动按阶段推进:策划→设计→剧本→诊断→提示词组装→API JSON输出。支持小说改编和原创短剧两条路径。触发词:AI短剧、短剧制作、小说转短剧、短剧提示词、提示词工厂、短剧全流程、小说改编短剧、生成短剧、AI视频剧本、短剧项目、分镜提示词、视频提…
$ npx skills add LeoYeAI/openclaw-master-skills --skill ai-drama-prompt-factory -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills ai-drama-prompt-factory --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-drama-prompt-factory .claude/skills/ai-drama-prompt-factory && rm -rf skills-srcUse ~/.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/
Install the "ai-drama-prompt-factory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-drama-prompt-factory into .claude/skills/ai-drama-prompt-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-drama-prompt-factory", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-drama-prompt-factoryType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add LeoYeAI/openclaw-master-skills --skill ai-drama-prompt-factory -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills ai-drama-prompt-factory --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ai-drama-prompt-factory .agents/skills/ai-drama-prompt-factory && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ai-drama-prompt-factory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-drama-prompt-factory into .agents/skills/ai-drama-prompt-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-drama-prompt-factory", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill ai-drama-prompt-factory -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills ai-drama-prompt-factory --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ai-drama-prompt-factory .cursor/skills/ai-drama-prompt-factory && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ai-drama-prompt-factory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-drama-prompt-factory into .cursor/skills/ai-drama-prompt-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-drama-prompt-factory", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/LeoYeAI/openclaw-master-skills.git --path skills/ai-drama-prompt-factory--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add LeoYeAI/openclaw-master-skills --skill ai-drama-prompt-factory -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills ai-drama-prompt-factory --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ai-drama-prompt-factory .gemini/skills/ai-drama-prompt-factory && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ai-drama-prompt-factory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-drama-prompt-factory into .gemini/skills/ai-drama-prompt-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-drama-prompt-factory", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install LeoYeAI/openclaw-master-skills ai-drama-prompt-factoryInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add LeoYeAI/openclaw-master-skills --skill ai-drama-prompt-factory -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ai-drama-prompt-factory .github/skills/ai-drama-prompt-factory && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ai-drama-prompt-factory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-drama-prompt-factory into .github/skills/ai-drama-prompt-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-drama-prompt-factory", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add LeoYeAI/openclaw-master-skills --skill ai-drama-prompt-factory -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install LeoYeAI/openclaw-master-skills ai-drama-prompt-factory --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/LeoYeAI/openclaw-master-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ai-drama-prompt-factory .opencode/skills/ai-drama-prompt-factory && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ai-drama-prompt-factory" agent skill from https://github.com/LeoYeAI/openclaw-master-skills/tree/main/skills/ai-drama-prompt-factory into .opencode/skills/ai-drama-prompt-factory/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-drama-prompt-factory", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
ai-drama-prompt-factoryAI短剧提示词工厂 - 端到端将小说/故事创意转化为结构化提示词包(角色立绘+场景+道具+分镜图片+视频+音频)的完整流水线。一个入口启动全流程,内部自动按阶段推进:策划→设计→剧本→诊断→提示词组装→API JSON输出。支持小说改编和原创短剧两条路径。触发词:AI短剧、短剧制作、小说转短剧、短剧提示词、提示词工厂、短剧全流程、小说改编短剧、生成短剧、AI视频剧本、短剧项目、分镜提示词、视频提…
AI Drama Prompt Factory is an agent skill from LeoYeAI/openclaw-master-skills. AI短剧提示词工厂 - 端到端将小说/故事创意转化为结构化提示词包(角色立绘+场景+道具+分镜图片+视频+音频)的完整流水线。一个入口启动全流程,内部自动按阶段推进:策划→设计→剧本→诊断→提示词组装→API JSON输出。支持小说改编和原创短剧两条路径。触发词:AI短剧、短剧制作、小说转短剧、短剧提示词、提示词工厂、短剧全流程、小说改编短剧、生成短剧、AI视频剧本、短剧项目、分镜提示词、视频提示词、prompt factory。
Its SKILL.md is about 4.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 21 other files, including scripts, reference files and assets (for example `_meta.json`, `assets/negative-prompts.json` and `assets/project-template.json`).
The repository describes itself as: 🧠 Curated collection of 1209+ best OpenClaw skills — weekly updated by MyClaw.ai. The licence is MIT.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit e5199b5. It shows what the files ask for, not the result of running them.
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.
Ships 3 files in scripts/ (Python, from the files we listed), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
AI Drama Prompt Factory loads about 4.3k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 444 words of instructions outside code blocks.
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.
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); the scripts in this folder are not scanned.
The full file from LeoYeAI/openclaw-master-skills at commit e5199b5, republished under its MIT licence (© LeoYeAI). 444 words, ~4,302 tokens.
.claude/skills/ai-drama-prompt-factory/SKILL.md (or your agent's skills folder). This skill also uses 18 other files; get the full folder from GitHub.端到端将小说或故事创意转化为结构化提示词包,输出标准JSON供外部AI生成工具消费。
系统边界:只生产提示词数据,不做图片/视频/音频的实际生成。
任何短剧相关任务触发后,在执行任何工作之前,必须先向用户确认以下信息:
向用户确认:
向用户确认交付方式:
向用户确认:
确认完成后,开始执行第一个Phase。
铁律一:分镜图片提示词中必须使用角色和道具的名字
✅ 张慧芬转身替病床上的陈易(觉醒前)整理输液管
❌ 48岁中年女性转身替24岁苍白男性整理输液管铁律二:视频提示词必须基于分镜图片提示词派生 视频是图片的动态延伸,不能独立生成。
铁律三:提示词使用中文自然语言描述 连贯的场景叙述句,不是英文标签堆叠。
启动协议 → Phase 1 策划 → Phase 2 设计 → Phase 3 剧本 → Phase 4 诊断 → Phase 5 组装
↑ │
└────────┘
(修改≤3轮)| 路径 | 流程 | 诊断 |
|---|---|---|
| A: 小说改编 | 全5阶段 | 必须 |
| B: 原创短剧 | Phase 1→2→3→5 | 可选 |
文件1:planning/story-outline.md
必须包含以下完整结构:
# 故事大纲:{作品名称}
## 1. 基础信息
- 作品名称:{名称}
- 来源:{原创/改编自《XX》}
- 写作视角:{第一人称/第三人称全知/等}
- 视觉风格:{电影写实/日系动漫/2.5D}
- 剧本风格:{标准叙事/爽文漫剧}
- 目标集数:{N}集
- 每集时长:{N}分钟
## 2. 时空背景
{年代、地点、社会环境、特殊设定,150-300字}
## 3. 叙事结构
- 结构类型:{三幕/五幕/单元剧}
- 递进模式:{描述}
- 情绪曲线概要:{描述}
## 4. 核心冲突
{主角+困境+对抗力量+逆袭路径,100-200字}
## 5. 角色清单
### 主要角色
| 角色名 | 性别 | 年龄 | 身份 | 核心特征 | 外观变体 |
|--------|------|------|------|---------|---------|
| 陈易 | 男 | 24 | 大学生/觉醒者 | 外表懦弱内心坚韧 | 觉醒前、觉醒后 |
| ... | | | | | |
### 次要角色
| 角色名 | 性别 | 身份 | 故事功能 |
|--------|------|------|---------|
| ... | | | |
## 6. 关键道具
| 道具名 | 外观概述 | 剧情功能 | 首次出现 |
|--------|---------|---------|---------|
| 天机古卷 | 泛黄线装古书 | 主角能力来源 | 第1集 |
## 7. 核心场景清单
| 场景名 | 类型 | 出现集数 |
|--------|------|---------|
| 医院普通病房 | 室内 | 第1-2集 |
| 世界杯决赛球场 | 室外 | 第5-6集 |文件2:planning/episodes-plan.md
# 分集规划
## 第1集「{标题}」
- 核心事件:{一句话概述}
- 涉及角色:{角色列表}
- 主要场景:{场景列表}
- 情绪走向:{如:压抑→微光}
- 集尾钩子:{悬念/反转描述}
- 预计镜头数:{N}
## 第2集「{标题}」
...输出以上2个文件后,告知用户:
Phase 1 策划完成。请查看故事大纲和分集规划,确认无误后我将进入 Phase 2 设计阶段。如需调整请告知。
文件1:characters/{角色名}.json(每个角色一个文件)
{
"name": "陈易",
"character_id": "char_chenyi",
"gender": "男",
"age": 24,
"identity": "被雷劈获得超能力的普通大学生",
"personality": {
"core_traits": "外表懦弱内心坚韧",
"speech_style": "初期怯懦,觉醒后沉稳有力",
"motivation": "证明自己的价值"
},
"voice_default": {
"gender": "male",
"age_desc": "青年男性",
"timbre": "初期虚弱低沉,觉醒后清亮有力"
},
"variants": {
"觉醒前": {
"description": "病号服状态,虚弱苍白",
"appearance": "短发凌乱/黑色、面色苍白",
"outfit": "蓝白条纹病号服、病号裤、无鞋、无配饰",
"prompt": "现代、24岁、男、短发凌乱/黑色、蓝白条纹病号服、病号裤、无、面色苍白,电影写实风格,高质量,真实光影,电影级打光,8K分辨率,超高清细节,全身,纯色背景,面向镜头"
},
"觉醒后": {
"description": "运动装状态,精神焕发",
"appearance": "短发利落/黑色、目光锐利",
"outfit": "灰色运动外套、深蓝色运动裤、白色运动鞋、无配饰",
"prompt": "现代、24岁、男、短发利落/黑色、灰色运动外套、深蓝色运动裤、白色运动鞋、无配饰,电影写实风格,高质量,真实光影,电影级打光,8K分辨率,超高清细节,全身,纯色背景,面向镜头"
}
}
}角色提示词公式:
{时代}、{年龄}岁、{性别}、{发型/发色}、{上装}、{下装}、{鞋/配饰}、{面部特征},
{风格标签},全身,纯色背景,面向镜头文件2:scenes/{场景名}.json(每个场景一个文件)
{
"name": "医院普通病房",
"scene_id": "scene_hospital_room",
"type": "室内",
"era": "中国现代",
"key_elements": ["白色墙面", "输液架", "病床", "窗户"],
"variants": {
"白天": {
"lighting": "窗户透入柔和自然光",
"prompt": "中国现代,电影写实风格,室内,白天,现代医院普通病房,白色墙面干净整洁,输液架立在病床旁,病床白色床单,窗户透入柔和自然光"
},
"夜晚": {
"lighting": "走廊灯光透过门缝微弱照入",
"prompt": "中国现代,电影写实风格,室内,深夜,现代医院普通病房,白色墙面,病床旁输液架,走廊灯光透过门缝微弱照入,氛围安静压抑"
}
}
}场景提示词公式: {时代},{风格},{室内/室外},{时间},{环境详描}
文件3:props/{道具名}.json(每个关键道具一个文件,普通道具不需要)
{
"name": "天机古卷",
"prop_id": "prop_ancient_book",
"type": "信物",
"story_function": "主角能力来源,被雷劈时的护身符",
"prompt": "中国古代,电影写实风格,信物,泛黄卷边的线装书,封面为深蓝色布面,边角磨损严重,书页间夹有干枯的银杏叶书签,纸质泛黄,封面深蓝色布面,书签枯黄色"
}道具提示词公式: {时代},{风格},{类型},{外观详描},{材质/颜色}
文件4:style/style-guide.json(全局唯一)
{
"style_type": "电影写实",
"era": "中国现代",
"character_prompt_suffix": "电影写实风格,高质量,真实光影,电影级打光,8K分辨率,超高清细节",
"scene_prompt_suffix": "电影写实风格",
"storyboard_prompt_suffix": "写实风格,电影级打光,8K分辨率,超细节刻画",
"storyboard_enhance_tags": ["高对比度光影", "动态模糊感", "电影级质感", "8K超高清"],
"target_ratio": "9:16"
}详细规范: references/design-guide.md
输出所有设计文件后,向用户展示:
Phase 2 设计完成。共生成 {N} 个角色(含 {M} 个状态变体)、{N} 个场景、{N} 个道具的设计卡和提示词。
角色一览:
- 陈易:觉醒前(病号服)/ 觉醒后(运动装)
- 张慧芬:默认(护士装)
- ...
请确认角色/场景/道具设计是否需要调整,确认后进入 Phase 3 剧本生成。
文件1:scripts/ep{NN}/script.json(核心交付物)
{
"episode": {
"number": 1,
"title": "天降奇才",
"duration_target": "90s",
"style": "标准叙事",
"emotion_arc": "压抑→微光"
},
"shots": [
{
"shot_id": "ep01_sh01",
"shot_number": 1,
"duration": "3s",
"characters": [
{ "name": "陈勇", "variant": "默认" },
{ "name": "张慧芬", "variant": "默认" },
{ "name": "陈易", "variant": "觉醒前" }
],
"scene": "医院普通病房",
"scene_variant": "白天",
"shot_type": "近景",
"camera_movement": "固定",
"action_desc": "画面右侧陈勇背影离去,张慧芬转身替病床上的陈易整理输液管,轻叹气,眼神略带无奈",
"dialogue": {
"speaker": "张慧芬",
"text": "唉,陈易,你的医药费已经拖欠三天了...",
"emotion": "无奈叹息"
},
"sfx": ["脚步声远去", "输液管碰撞"],
"bgm": "无",
"source_anchor": "P-003",
"emotion_level": 2,
"narration": null
},
{
"shot_id": "ep01_sh02",
"shot_number": 2,
"...": "..."
}
],
"episode_summary": {
"total_shots": 15,
"characters_used": ["陈易", "张慧芬", "陈勇"],
"scenes_used": ["医院普通病房"],
"hook": "陈易在病床上突然睁开双眼,瞳孔中闪过金色光芒"
}
}每个shot必须包含的字段:
| 字段 | 类型 | 必须 | 说明 |
|---|---|---|---|
| shot_id | string | ✅ | ep{NN}_sh{NN} 全局唯一 |
| shot_number | int | ✅ | 集内序号 |
| duration | string | ✅ | 目标时长(如"3s") |
| characters | array | ✅ | 出场角色,每个含name和variant |
| scene | string | ✅ | 场景名(对应scenes/下的文件) |
| scene_variant | string | ✅ | 场景变体(白天/夜晚等) |
| shot_type | string | ✅ | 特写/近景/中景/全景/远景 |
| camera_movement | string | ✅ | 固定/推/拉/摇/跟 |
| action_desc | string | ✅ | 动作+表情+位置的自然语言描述 |
| dialogue | object/null | ✅ | 有对白时:speaker+text+emotion;无对白时:null |
| sfx | array | ✅ | 音效列表(可为空数组) |
| bgm | string | ✅ | BGM描述或"无" |
| source_anchor | string | ✅ | 原文锚点(改编)或"原创" |
| emotion_level | int | ✅ | 情绪强度1-5 |
| narration | string/null | ✅ | 旁白文本(爽文风格时使用)或null |
文件2:continuity/ep{NN}-state.json(连贯性状态)
{
"episode": 1,
"character_states": {
"陈易": {
"variant": "觉醒前",
"location": "医院病房",
"emotion": "昏迷中",
"carrying": []
},
"张慧芬": {
"variant": "默认",
"location": "医院病房",
"emotion": "无奈疲惫",
"carrying": []
}
},
"planted_threads": [
{ "thread": "陈易的医药费问题", "planted_at": "ep01_sh01" }
],
"resolved_threads": [],
"props_status": {
"天机古卷": "在陈易枕头下"
},
"next_hook": "陈易在病床上突然睁开双眼,瞳孔中闪过金色光芒"
}详细规范: references/script-generation-guide.md 爽文风格: references/manga-drama-guide.md 连贯性管理: references/continuity-guide.md
文件3(可选):scripts/ep{NN}/script.md(Markdown分镜表格文档)
仅当用户在启动协议中选择"是"输出Markdown时才生成此文件。
# 第{N}集「{标题}」分镜剧本
> 情绪走向:{情绪弧线} | 目标时长:{时长} | 镜头总数:{N}
## 分镜表
| 镜头号 | 时长 | 角色 | 场景/变体 | 景别 | 运镜 | 动作描述 | 对白 | 音效 | BGM | 原文锚点 |
|--------|------|------|----------|------|------|---------|------|------|-----|---------|
| ep01_sh01 | 3s | 陈勇(默认)、张慧芬(默认)、陈易(觉醒前) | 医院普通病房/白天 | 近景 | 固定 | 画面右侧陈勇背影离去,张慧芬转身替病床上的陈易整理输液管,轻叹气,眼神略带无奈 | 张慧芬:"唉,陈易,你的医药费已经拖欠三天了..."(无奈叹息) | 脚步声远去、输液管碰撞 | 无 | P-003 |
| ep01_sh02 | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
## 集尾钩子
{钩子描述}
## 本集统计
- 总镜头数:{N}
- 涉及角色:{角色列表}
- 涉及场景:{场景列表}
- 含对白镜头:{N}个
- 情绪高点镜头:{镜头号列表}Markdown分镜表生成规则:
script.json 中的 shot 字段一一对应角色名(变体),无变体时只写角色名说话人:"台词"(情绪),无对白时填 ——每集剧本完成后,向用户展示:
Phase 3 第{N}集剧本完成。共 {M} 个镜头,涉及角色:{列表},涉及场景:{列表}。 集尾钩子:{钩子描述} [如已选择Markdown输出] 同时输出了 Markdown 分镜表格文档
scripts/ep{NN}/script.md。[如为改编项目] 即将进入 Phase 4 诊断,对照原著校验忠实度。 [如为原创项目] 是否需要调整?确认后可直接进入 Phase 5 组装提示词。
文件:continuity/diagnosis-ep{NN}.md
# 第{N}集诊断报告
## 总评
- **综合评分:{分数}/100**
- **结论:{✅ 通过 / ❌ 未通过}**
- 致命问题(🔴):{数量}个
- 严重问题(🟠):{数量}个
- 一般问题(🟡):{数量}个
## 各维度评分
| 维度 | 得分 | 权重 | 加权分 |
|------|------|------|--------|
| 情节忠实度 | {x}/100 | 35% | {y} |
| 对白还原度 | {x}/100 | 25% | {y} |
| 角色一致性 | {x}/100 | 20% | {y} |
| 情感曲线 | {x}/100 | 10% | {y} |
| 连贯性 | {x}/100 | 10% | {y} |
| **合计** | | **100%** | **{总分}** |
## 问题清单
### 🔴 致命问题
1. **[ep01_sh05]** {问题描述}
- 原著:{原文内容}
- 剧本:{剧本内容}
- 修改建议:{具体修改方案}
### 🟠 严重问题
...
### 🟡 一般问题
...
## 亮点
- {做得好的地方}
## 修改清单(按镜头号排序)
| 镜头 | 级别 | 修改内容 |
|------|------|---------|
| ep01_sh05 | 🔴 | {具体修改指导} |
| ep01_sh12 | 🟠 | {具体修改指导} |剧本 → 诊断 → ✅ 通过(≥75) → Phase 5
→ ❌ 未通过 → 按修改清单逐镜头修改 → 再诊断(最多3轮)
→ 仍未通过 → 提示用户人工介入详细规范: references/diagnosis-guide.md
诊断完成后,向用户展示:
Phase 4 诊断完成。第{N}集评分:{分数}/100,{✅通过/❌未通过}。 [通过] 即将进入 Phase 5 组装提示词包。 [未通过] 发现 {N} 个问题需要修改(致命{N}个/严重{N}个),是否立即修改?
文件1:output/project-manifest.json(全项目唯一,首次生成后增量更新)
{
"project": {
"title": "项目名",
"source_title": "原著名(如有)",
"genre": "都市逆袭",
"era": "中国现代",
"total_episodes": 20,
"target_ratio": "9:16"
},
"style": {
"style_type": "电影写实",
"character_prompt_suffix": "电影写实风格,高质量,真实光影,电影级打光,8K分辨率,超高清细节",
"storyboard_prompt_suffix": "写实风格,电影级打光,8K分辨率,超细节刻画"
},
"characters": {
"陈易": {
"gender": "男",
"age": 24,
"variants": {
"觉醒前": { "prompt": "完整角色提示词..." },
"觉醒后": { "prompt": "完整角色提示词..." }
}
}
},
"scenes": {
"医院普通病房": {
"variants": {
"白天": { "prompt": "完整场景提示词..." },
"夜晚": { "prompt": "完整场景提示词..." }
}
}
},
"props": {
"天机古卷": { "prompt": "完整道具提示词..." }
}
}文件2:output/ep{NN}-prompt-package.json(每集一个)
{
"episode": {
"number": 1,
"title": "天降奇才",
"shot_count": 15,
"characters_used": ["陈易", "张慧芬", "陈勇"],
"scenes_used": ["医院普通病房"]
},
"shots": [
{
"shot_id": "ep01_sh01",
"shot_number": 1,
"duration": "3s",
"script": {
"characters": [
{ "name": "陈勇", "variant": "默认" },
{ "name": "张慧芬", "variant": "默认" },
{ "name": "陈易", "variant": "觉醒前" }
],
"scene": "医院普通病房",
"scene_variant": "白天",
"shot_type": "近景",
"action_desc": "画面右侧陈勇背影离去,张慧芬转身替病床上的陈易整理输液管",
"dialogue": {
"speaker": "张慧芬",
"text": "唉,陈易,你的医药费已经拖欠三天了...",
"emotion": "无奈叹息"
},
"source_anchor": "P-003"
},
"storyboard_prompt": "中国现代,医院普通病房,白色墙面,输液架,病床,柔和冷光,近景镜头(胸部以上),画面右侧陈勇背影离去,张慧芬转身替病床上的陈易(觉醒前)整理输液管,轻叹气,眼神略带无奈,写实风格,电影级打光,8K分辨率,超细节刻画",
"video_prompt": "场景为中国现代医院普通病房,白色墙面干净整洁,输液架立在病床旁,柔和冷光洒满房间。镜头从张慧芬(女)的近景开始,她站在病床边,目光望向画面右侧,陈勇(男)的背影正缓缓走出病房门口,写实风格,电影级打光。切镜到张慧芬(女)的近景(胸部以上),她收回目光转身面向病床上的陈易,双手轻柔整理输液管,轻叹气,嘴唇微动说着:\"唉,陈易,你的医药费已经拖欠三天了...\",眼神略带无奈,超细节刻画手部动作,8K分辨率。最后切镜到两人同框的中景,张慧芬(女)整理好输液管后低头看着陈易,病房里安静无声,氛围忧虑而沉重,无背景音乐。陈勇是男性,张慧芬是女性",
"audio_spec": {
"dialogue": {
"text": "唉,陈易,你的医药费已经拖欠三天了...",
"speaker": "张慧芬",
"speaker_gender": "female",
"voice_desc": "中年女性,声音疲惫温和,带叹息感,语速缓慢",
"emotion": "无奈叹息"
},
"sfx": [
{ "type": "脚步声远去", "timing": "陈勇离开时", "volume": "低" },
{ "type": "输液管碰撞", "timing": "张慧芬整理时", "volume": "轻微" }
],
"bgm": {
"mood": "无",
"note": "无背景音乐,保持安静压抑氛围"
}
}
}
],
"continuity": {
"character_states": {
"陈易": { "variant": "觉醒前", "location": "医院病房" },
"张慧芬": { "variant": "默认", "location": "医院病房" }
},
"next_hook": "陈易在病床上突然睁开双眼,瞳孔中闪过金色光芒"
}
}每个shot必须包含的3个提示词字段:
| 字段 | 类型 | 说明 |
|---|---|---|
| storyboard_prompt | string | 分镜图片提示词。中文自然语言。角色用名字引用。 |
| video_prompt | string | 视频提示词。基于storyboard_prompt派生。含切镜/对白/性别声明。 |
| audio_spec | object | 音频描述。含dialogue(对白+voice_desc)、sfx(音效)、bgm(BGM)。 |
{时代},{场景描述},{光影},{景别},
{角色名(状态)} + {位置} + {动作} + {表情},
{风格},{画质标签}场景为{场景描述扩写}。
镜头从{角色名(性别)}的{景别}开始,{动作},{风格}。
切镜到{角色名(性别)}的{景别},{动作},{对白:"台词"},{表情}。
最后切镜到{景别},{氛围收束}。
{角色A}是{性别},{角色B}是{性别}详细组装规则: references/assembly-rules.md 提示词示例: references/prompt-examples.md 平台适配: references/platform-adapters.md 完整Schema: references/api-schema.md
每集提示词包完成后,向用户展示:
Phase 5 第{N}集提示词包组装完成。
- 共 {M} 个镜头
- 分镜图片提示词:{M} 条
- 视频提示词:{M} 条
- 含对白镜头:{M} 个
- 输出文件:output/ep{NN}-prompt-package.json
是否继续生成下一集?或需要调整某个镜头的提示词?
{project-name}/
├── planning/
│ ├── story-outline.md ← Phase 1
│ └── episodes-plan.md ← Phase 1
│
├── characters/
│ ├── 陈易.json ← Phase 2
│ ├── 张慧芬.json ← Phase 2
│ └── ...
│
├── scenes/
│ ├── 医院普通病房.json ← Phase 2
│ └── ...
│
├── props/
│ └── 天机古卷.json ← Phase 2
│
├── style/
│ └── style-guide.json ← Phase 2
│
├── scripts/
│ ├── ep01/script.json ← Phase 3
│ ├── ep01/script.md ← Phase 3(可选,Markdown分镜表)
│ ├── ep02/script.json ← Phase 3
│ ├── ep02/script.md ← Phase 3(可选)
│ └── ...
│
├── continuity/
│ ├── ep01-state.json ← Phase 3
│ ├── ep02-state.json ← Phase 3
│ ├── diagnosis-ep01.md ← Phase 4
│ └── diagnosis-ep02.md ← Phase 4
│
└── output/
├── project-manifest.json ← Phase 5(首次生成后增量更新)
├── ep01-prompt-package.json ← Phase 5
├── ep02-prompt-package.json ← Phase 5
└── ...| Phase | 交付物 | 文件格式 | 数量 |
|---|---|---|---|
| Phase 1 策划 | story-outline.md + episodes-plan.md | Markdown | 2个 |
| Phase 2 设计 | {角色}.json + {场景}.json + {道具}.json + style-guide.json | JSON | 按角色/场景/道具数量 |
| Phase 3 剧本 | script.json + ep{NN}-state.json + script.md(可选) | JSON + Markdown | 每集2-3个 |
| Phase 4 诊断 | diagnosis-ep{NN}.md | Markdown | 每集1个 |
| Phase 5 组装 | project-manifest.json + ep{NN}-prompt-package.json | JSON | 1 + 每集1个 |
用户:"预览第1集镜头3的提示词"
→ 输出该镜头的完整链路:
1. 涉及角色的立绘提示词
2. 涉及场景的场景提示词
3. 分镜图片提示词
4. 视频提示词
5. 音频描述用户:"继续生成下一集"
→ 读取最近一集的 ep{NN}-state.json
→ 从 Phase 3 开始(→4→5)用户已有剧本,只需要提示词
→ 跳过Phase 1/3,先确认Phase 2设计件是否齐全
→ 如缺少设计件,从剧本描述中自动提取生成(降级模式)
→ 进入Phase 5组装© LeoYeAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 18 other files (scripts, references, assets) in skills/ai-drama-prompt-factory of LeoYeAI/openclaw-master-skills.
Open the folder on GitHubat commit e5199b5
AI Drama Prompt Factory 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| AI Drama Prompt Factory this skillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.3k | Automated safety check: Pass | MIT | |
| Factory MCPwarpdotdev/warp | 65k | 1 repos | ~237 | Automated safety check: Pass | AGPL-3.0 | |
| Warp Factory Fileswarpdotdev/warp | 65k | 1 repos | ~2.5k | Automated safety check: Pass | AGPL-3.0 | |
| Factorial AutomationComposioHQ/awesome-claude-skills | 77k | 3 repos | ~738 | Automated safety check: Pass | None | |
| FactoryBuilderIO/skills | 4.6k | — | ~1k | Automated safety check: Pass | MIT | |
| Theme Factoryanthropics/skills | 180k | 47 repos | ~781 | Automated safety check: Pass | Apache-2.0 |
warpdotdev/warp
Use the Warp Factory MCP to hand work to a software factory and collaborate with it — bundle local work and send it to the cloud, find factory tasks from a Slack thread / Linear ticket /…
warpdotdev/warp
Authors and edits file-based Warp software factory definitions rooted at factory.yaml, covering agents, automations, scorers and webhooks, and validates them before a pull request.
ComposioHQ/awesome-claude-skills
Automate Factorial tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills.
BuilderIO/skills
Experimental workflow for configuring an autonomous software delivery factory.
anthropics/skills
Applies one of ten preset color and font themes to slide decks, documents or HTML pages, or creates a new theme on the fly after you choose from a showcase.
mastra-ai/mastra
Produce a phased implementation plan for a Factory work item, then advance it to execute
LeoYeAI/openclaw-master-skills
Manages pipelines on a DevOps quality and efficiency platform through its OpenAPI: list workspaces and templates, create, update, run and cancel pipelines, and read run records.
LeoYeAI/openclaw-master-skills
Patches OpenClaw's Feishu extension so an edited document triggers an isolated agent session that reads the doc and replies inline, turning it into a live chat space.
LeoYeAI/openclaw-master-skills
Multi-context memory management system for OpenClaw agents with group-isolated storage, global shared memory, workspace organization, and group-specific skills isolation.
LeoYeAI/openclaw-master-skills
Runs a brand's AI-search visibility work end to end: diagnosing how AI platforms represent it, repositioning it, producing AI-optimized content and monitoring ongoing mentions.
LeoYeAI/openclaw-master-skills
Installs and authenticates the gws CLI, then automates Gmail, Drive, Sheets, Calendar, Docs, Chat and Tasks with ready-made recipes, persona bundles and security audits.
LeoYeAI/openclaw-master-skills
Runs four advisor roles, a fitness coach, nutritionist, data analyst and TCM practitioner, to build a health profile and track workouts, diet and wellness over time.
AI短剧提示词工厂 - 端到端将小说/故事创意转化为结构化提示词包(角色立绘+场景+道具+分镜图片+视频+音频)的完整流水线。一个入口启动全流程,内部自动按阶段推进:策划→设计→剧本→诊断→提示词组装→API JSON输出。支持小说改编和原创短剧两条路径。触发词:AI短剧、短剧制作、小说转短剧、短剧提示词、提示词工厂、短剧全流程、小说改编短剧、生成短剧、AI视频剧本、短剧项目、分镜提示词、视频提…. AI Drama Prompt Factory is an agent skill from LeoYeAI/openclaw-master-skills.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill ai-drama-prompt-factory -a claude-code`. Or copy the skill folder (skills/ai-drama-prompt-factory in LeoYeAI/openclaw-master-skills) into .claude/skills/ai-drama-prompt-factory in your project. Claude Code loads it when a task matches its description.
Run `npx skills add LeoYeAI/openclaw-master-skills --skill ai-drama-prompt-factory -a codex`. Or copy the skill folder (skills/ai-drama-prompt-factory in LeoYeAI/openclaw-master-skills) into .agents/skills/ai-drama-prompt-factory in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LeoYeAI/openclaw-master-skills --skill ai-drama-prompt-factory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-drama-prompt-factory, .gemini/skills/ai-drama-prompt-factory, .github/skills/ai-drama-prompt-factory and .opencode/skills/ai-drama-prompt-factory in your project.
Going by SKILL.md and its folder, AI Drama Prompt Factory needs Python for the scripts in its folder. Our summary lists: Python 3.
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.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
AI Drama Prompt Factory is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.3k tokens (SKILL.md is roughly 17k 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 12k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with AI Drama Prompt Factory: Factory MCP (warpdotdev/warp, 65k stars), Warp Factory Files (warpdotdev/warp, 65k stars), Factorial Automation (ComposioHQ/awesome-claude-skills, 77k stars) and Factory (BuilderIO/skills, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
LeoYeAI (a GitHub user) maintains it in LeoYeAI/openclaw-master-skills, which has 2,161 GitHub stars. The repository holds 1,235 skills in this directory. The repository was last updated on July 20, 2026.
Source: LeoYeAI/openclaw-master-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.