Back to Details

storyteller

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Storyteller Skill

Storyteller Skill

Overview

概述

This skill transforms metaphorical/theatrical narrative content into concrete, filmable visual stories. It serves as the critical translation layer between poetic writing and production-ready screenplay format.
The Problem It Solves:
INPUT:  "Aku menjadi laut yang membeku, menunggu pelaut yang tidak kembali"
PROBLEM: What does this LOOK LIKE on screen?
OUTPUT: Woman stands at frozen beach at dawn, staring at horizon where ship 
        disappeared. She places his jacket on the ice. Days pass (montage). 
        She returns. Always returns.
Core Principle: Preserve emotional truth while making content filmable.
本技能可将隐喻性/戏剧化叙事内容转换为具体、可拍摄的视觉故事。它是诗意写作与可用于制作的剧本格式之间的关键转换层。
解决的问题：
输入："Aku menjadi laut yang membeku, menunggu pelaut yang tidak kembali"（印尼语：我变成冰封的海洋，等待未归的水手）
问题：这在屏幕上呈现出来是什么样子？
输出：女人站在黎明时分的冰封海滩上，凝视着船只消失的地平线。她把他的夹克放在冰面上。日子一天天过去（蒙太奇镜头）。她总会回来。一直都会回来。
核心原则： 在让内容具备可拍摄性的同时，保留情感真实性。

Core Transformation Workflow

核心转换流程

Step 1: Extract Emotional Core

步骤1：提取情感核心

What does the metaphor FEEL like?
Read the metaphorical content and identify:
  • Primary Emotion: The dominant feeling (longing, grief, obsession, hope)
  • Emotional Intensity: Scale 1-10, how extreme is this feeling?
  • Relationship Dynamic: Who feels what toward whom?
  • Temporal Context: Is this present pain, past memory, future fear?
Example:
Metaphor: "Aku menjadikanmu altar pribadi"
Primary Emotion: Worship/devotion bordering on obsession
Intensity: 9/10 (extreme, unhealthy level)
Dynamic: Speaker → Beloved (one-directional adoration)
Temporal: Present state, ongoing condition
这个隐喻给人的感受是什么？
阅读隐喻内容并明确：
  • 核心情感： 主导情绪（思念、悲伤、痴迷、希望）
  • 情感强度： 1-10分制，情绪的强烈程度
  • 关系动态： 谁对谁抱有怎样的情绪？
  • 时间背景： 这是当下的痛苦、过去的回忆还是未来的恐惧？
示例：
隐喻："Aku menjadikanmu altar pribadi"（印尼语：我将你视作私人祭坛）
核心情感：近乎痴迷的崇拜/虔诚
强度：9/10（极端、不健康的程度）
关系动态：说话者→所爱之人（单向爱慕）
时间背景：当前状态，持续进行中

Step 2: Find Visual Equivalent

步骤2：寻找视觉等价物

What ACTIONS show this emotion?
Translate abstract emotion into visible behavior using this framework:
Emotion TypeVisual Translation Strategy
Longing/WaitingCharacter returns to same location repeatedly; keeps object belonging to absent person; checks phone/window/door obsessively
Worship/DevotionRitualistic behaviors (daily routines, shrine-like arrangements); serving without being asked; positioning self lower than object of worship
Loss/GriefEmpty spaces where person used to be; untouched belongings; inability to change/move on from environment
ObsessionCollection of items; repetitive actions; deteriorating self-care while maintaining focus on other
Fear of AbandonmentChecking behaviors; keeping lights on; sleeping in wrong positions; startling at sounds
Visual Vocabulary Reference: references/visual-vocabulary.md
哪些动作可以展现这种情绪？
通过以下框架将抽象情绪转化为可见行为：
情绪类型视觉转换策略
思念/等待角色重复回到同一地点；保留离去之人的物品；频繁查看手机/窗户/门
崇拜/虔诚仪式化行为（日常惯例、神龛式布置）；主动付出不求回报；身体姿态展现对所爱之人的仰视
失去/悲伤离去之人曾使用的空荡空间；原封不动的物品；无法改变/脱离当前环境
痴迷收集相关物品；重复性行为；专注于对方而忽视自我照料
被抛弃恐惧反复确认行为；保持灯光常亮；反常的睡姿；对声响过度敏感
视觉词汇参考： references/visual-vocabulary.md

Step 3: Generate Scene Breakdown

步骤3：生成场景拆解

Build filmable scenes around visual actions
For each emotional beat in the source material:
  1. Identify Location: Where would this emotion naturally occur?
  2. Define Action: What does the character DO to show this emotion?
  3. Select Props/Objects: What physical items carry symbolic weight?
  4. Establish Time: When does this happen? (time progression matters)
  5. Document Story Logic: Why does this visual choice work?
Scene Template:
SCENE [NUMBER]: [Brief Description]
Location: [Specific place]
Time: [Time of day/progression]
Action: [What character physically does]
Key Visuals: [Important visual elements]
Emotional Beat: [What audience should feel]
Story Logic: [Why this visual choice represents the metaphor]
围绕视觉动作构建可拍摄场景
针对源素材中的每个情感节点：
  1. 确定地点： 这种情绪最自然的发生场景是哪里？
  2. 定义动作： 角色会做什么来展现这种情绪？
  3. 选择道具/物品： 哪些实物具备象征意义？
  4. 设定时间： 事件发生在何时？（时间推进很重要）
  5. 记录故事逻辑： 为什么这个视觉选择是合理的？
场景模板：
SCENE [编号]: [简要描述]
Location: [具体地点]
Time: [时间/时间推进]
Action: [角色的具体行为]
Key Visuals: [重要视觉元素]
Emotional Beat: [观众应感受到的情绪]
Story Logic: [该视觉选择如何对应隐喻]

Step 4: Create Story Logic Map

步骤4：创建故事逻辑图

Document the metaphor→visual transformation
For transparency and creative consistency, document:
STORY LOGIC MAP
===============
Original Metaphor: "..."
Emotional Core: [extracted emotion]
Visual Translation: [chosen visual representation]
Why It Works: [explanation of connection]
Alternative Considered: [what else could work]
记录隐喻→视觉的转换过程
为保证透明度和创作一致性，请记录：
STORY LOGIC MAP
===============
Original Metaphor: "..."
Emotional Core: [提取的情绪]
Visual Translation: [选定的视觉表现]
Why It Works: [关联说明]
Alternative Considered: [其他可行方案]

Output Format

输出格式

Scene Breakdown Structure

场景拆解结构

markdown
undefined
markdown
undefined

Visual Story Breakdown: [Title]

视觉故事拆解: [标题]

Source Material Summary

源素材摘要

  • Original Concept: [From diverse-content-gen]
  • Emotional Core: [Primary emotion identified]
  • Tone: [Preserved from source]
  • Target Duration: [5-10 minutes]
  • 原始概念: [来自diverse-content-gen]
  • 情感核心: [识别出的核心情绪]
  • 基调: [保留自源素材]
  • 目标时长: [5-10分钟]

Character(s)

角色

  • [Name]: [Brief visual description, emotional state]
  • [姓名]: [简要视觉描述、情绪状态]

Scene-by-Scene Breakdown

逐场景拆解

Scene 1: [Title]

场景1: [标题]

Location: [Specific, filmable location] Time: [Time of day] Duration: [30-60 seconds estimate]
Visual Action: [Detailed description of what character does - FILMABLE actions only]
Key Visuals:
  • [Visual element 1]
  • [Visual element 2]
  • [Visual element 3]
Emotional Beat: [What audience feels]
Story Logic: [How this scene translates the original metaphor]
Location: [具体可拍摄地点] Time: [一天中的时段] Duration: [预估30-60秒]
Visual Action: [角色具体行为的详细描述 - 仅包含可拍摄动作]
Key Visuals:
  • [视觉元素1]
  • [视觉元素2]
  • [视觉元素3]
Emotional Beat: [观众的感受]
Story Logic: [该场景如何转换原始隐喻]

Scene 2: [Title]

场景2: [标题]

[Continue same format...]
[遵循相同格式...]

Story Logic Map

故事逻辑图

Original MetaphorEmotional CoreVisual TranslationWhy It Works
"...".........
原始隐喻情感核心视觉转换合理性说明
"...".........

Technical Notes for Screenwriter

给编剧的技术说明

  • [Any specific notes about pacing, transitions, or visual consistency]

---
  • [关于节奏、转场或视觉一致性的特定说明]

---

Transformation Guidelines

转换指南

What Makes a Scene "Filmable"

什么是“可拍摄”场景

✅ FILMABLE:
  • Physical actions (walking, touching, looking, moving objects)
  • Observable emotions (tears, shaking, stillness, posture)
  • Environmental details (weather, lighting, objects in space)
  • Time progression (morning→night, seasons changing)
❌ NOT FILMABLE:
  • Internal thoughts ("She thinks about him")
  • Abstract concepts ("Love fills the room")
  • Unvisualizable metaphors ("Her heart is a frozen sea")
  • Telling instead of showing ("She is sad")
✅ 可拍摄：
  • 物理动作（行走、触摸、注视、移动物品）
  • 可观察的情绪（流泪、颤抖、静止、姿态）
  • 环境细节（天气、光线、空间内的物品）
  • 时间推进（从早到晚、季节变化）
❌ 不可拍摄：
  • 内心想法（“她想念他”）
  • 抽象概念（“爱填满了房间”）
  • 无法视觉化的隐喻（“她的心是一片冰封的海洋”）
  • 直接陈述而非展现（“她很悲伤”）

Converting Common Metaphorical Patterns

常见隐喻模式的转换

Metaphor TypeVisual Approach
"I am [element]" (sea, fire, ice)Show character interacting with that element; use element as setting backdrop; character's behavior mirrors element properties
"You are my [sacred thing]" (altar, god, sun)Show ritualistic worship-like behaviors; lighting/composition that elevates the beloved; character positioning that shows devotion
"I am waiting for..."Show passage of time; same location revisited; objects accumulated or deteriorating; physical signs of waiting
"When you left..."Empty spaces; untouched belongings; paused activities; contrast with "before" flashbacks
隐喻类型视觉处理方式
“我是[元素]”（海洋、火焰、冰雪）展现角色与该元素的互动；将元素作为场景背景；角色行为呼应元素特性
“你是我的[神圣事物]”（祭坛、神明、太阳）展现仪式化的崇拜行为；用光线/构图突出所爱之人；角色姿态展现虔诚
“我在等待...”展现时间流逝；重复回到同一地点；物品的积累或损坏；等待的物理迹象
“当你离开时...”空荡的空间；原封不动的物品；停滞的活动；与“之前”的闪回形成对比

Detailed Methodology

详细方法论

For step-by-step transformation process with worked examples:
  • references/transformation-methodology.md
包含分步转换流程及实例：
  • references/transformation-methodology.md

Integration with Pipeline

与流程管道的集成

Input: diverse-content-gen Output

输入：diverse-content-gen的输出

Expect structured narrative ideas with:
  • POV, Setting, Tone, Structure already defined
  • "Why This Wins" analysis (emotional hooks identified)
  • Metaphorical/theatrical language
  • NOT scene-by-scene yet
接收已结构化的叙事创意，包含：
  • 已定义的视角、场景、基调和结构
  • “亮点分析”（已识别的情感钩子）
  • 隐喻性/戏剧化语言
  • 尚未进行逐场景拆解

Output: Ready for Screenwriter

输出：供编剧使用的内容

Provide scene breakdowns with:
  • Concrete locations and times
  • Physical, filmable actions
  • Key visuals for each scene
  • Emotional progression documented
  • Story logic preserved
Screenwriter will then:
  • Add proper screenplay formatting (sluglines, etc.)
  • Wrap in XML tags for pipeline
  • Add technical metadata (duration, characters list)
提供的场景拆解包含：
  • 具体地点和时间
  • 物理可拍摄动作
  • 每个场景的关键视觉元素
  • 记录的情感推进
  • 保留的故事逻辑
后续编剧将：
  • 添加标准剧本格式（场景标题等）
  • 用XML标签包裹以适配流程管道
  • 添加技术元数据（时长、角色列表）

Quality Checklist

质量检查清单

Before outputting scene breakdown, verify:
  • Every scene describes VISIBLE action (not internal thought)
  • Emotional core from source material is preserved
  • Story logic map explains all metaphor→visual translations
  • Scenes follow logical time/space progression
  • Total scene count appropriate for target duration (8-15 for 5-10 min)
  • Key visuals are specific enough for image generation
  • No unexplained jumps in emotion or location
  • Tone consistency maintained throughout
输出场景拆解前，请验证：
  • 每个场景仅描述可见动作（非内心想法）
  • 源素材的情感核心已保留
  • 故事逻辑图说明了所有隐喻→视觉的转换
  • 场景遵循合理的时间/空间推进
  • 总场景数与目标时长匹配（5-10分钟对应8-15个场景）
  • 关键视觉元素足够具体以支持图像生成
  • 情绪或地点无突兀跳转
  • 全程保持基调一致

Additional Resources

额外资源

Detailed Transformation Process

详细转换流程

references/transformation-methodology.md
references/transformation-methodology.md

Visual Vocabulary Reference

视觉词汇参考

references/visual-vocabulary.md
references/visual-vocabulary.md