TypingMindTypingMindThe best frontend for AI
Sound Design Expectation logo

Sound Design Expectation

Community
geegl
sound-design-expectation

Sound's emotional power comes from building and violating expectations. Surprise requires prior setup; too-accurate prediction causes boredom.

Overview

Publishergeegl
Repositorydirectorskills
Skill namesound-design-expectation
Stars
68
Forks
7
Bundled files
1
LicenseMIT
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by geegl on GitHub. Read the source before you install it.

Installation

Install the Sound Design Expectation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/geegl/directorskills/tree/main/output/books/sound-design/sound-design-expectation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/geegl/directorskills.git /tmp/directorskills
mkdir -p .claude/skills
cp -r /tmp/directorskills/output/books/sound-design/sound-design-expectation .claude/skills/sound-design-expectation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Sound Design Expectation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Sound Design Expectation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Sound Design Expectation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

RIA++ Skill: 预期违背原则 (Expectation Violation)

R — 原文 (Reading)

"当期望不准确的时候，情绪会在音乐和故事当中爆发。通过某一时刻与预期的背离，下一个应验的预期时刻能够被强化。" — 声音设计 — David Sonnenschein, p.g_0023

I — 方法论骨架 (Interpretation)

音乐和叙事的力量来自预期的建立和违背：

  • 预期被满足→愉悦、安心
  • 预期被违背→情绪爆发（惊喜/恐惧/幽默/感动）
  • 预期总是满足→厌烦、机械
  • 预期总是违背→不连贯、困惑

最优策略：在满足和违背之间找到节奏。一次违背强化下一次满足的效果。恐怖片经典：先用蝙蝠声引起虚惊（建立预期），然后用怪物吼声打破预期（真正的惊吓）。

A1 — 书中的应用 (Past Application)

案例 1: 恐怖片的虚惊-实惊交替

  • 问题: 如何让观众在整部恐怖片中保持紧张感？
  • 方法论的使用: 经典恐怖片结构：先用蝙蝠声/树枝声引起2-3次"虚惊"（建立预期=突然声响=惊吓），然后在观众习惯这个模式后，用完全不同的声音（如低沉的呼吸声）打破预期——这次是"实惊"
  • 结论: 预期的建立是违背的前提。没有足够的铺垫，违背毫无效果
  • 结果: 这成为恐怖片声音设计的基础公式

案例 2: 喜剧的声音预期违背

  • 问题: 如何用声音增强喜剧效果？
  • 方法论的使用: 角色严肃地走向舞台中央，观众预期庄重的音乐——结果放出了滑稽的音效。预期越"正经"，违背越搞笑。关键：先建立严肃的预期，再用声音打破它
  • 结论: 喜剧和恐怖在声音设计上是同构的——都依赖预期的建立和违背，只是情绪方向不同

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

  1. 用户在设计恐怖/惊悚场景的"惊吓点"——需要铺垫和预期管理
  2. 用户在设计喜剧场景的"笑点"——需要用声音打破严肃预期
  3. 用户觉得场景"可预测"——需要用声音制造意外
  4. 用户在设计反转/揭示场景——需要声音配合叙事转折

语言信号

  • "这个吓人点应该怎么铺"
  • "这个笑点的声音应该怎么处理"
  • "观众都知道接下来会发生什么"
  • "怎么让观众感到意外"
  • "声音太平淡了没有惊喜"

与相邻 skill 的区分

  • 与 sound-design-contrast-drama 的区别: contrast-drama 处理物理层面的音量对比，expectation 处理认知层面的预期管理。前者用"大声vs小声"，后者用"预期A vs 实际B"
  • 与 sound-design-sonata-drama 的区别: sonata-drama 处理宏观叙事结构，expectation 处理微观声音事件的预期管理

E — 可执行步骤 (Execution)

  1. 预期建立：先用2-3次类似的声音/节奏建立观众的预期模式

  2. 违背设计：在观众最预期某种声音时，给一个不同的声音

  3. 节奏平衡：检查满足/违背的比例——大约70%满足、30%违背是常见最优

    • 🔴 判停条件: 若预期建立阶段2-3次相似声音后观众仍未形成可预测的模式，回到步骤1增加声音相似度或减少建立次数间的间隔；若违背设计后测试观众的反应是困惑而非预期情绪，回到步骤2调整违背幅度——违背需在"出乎意料"和"可以理解"之间找到平衡

B — 边界 (Boundary) ★

反场景：纪录片（预期基于现实，不应人为操控）、功能性音效（需要可预测性）。

失败模式：

  • 违背太小——观众没注意到
  • 违背太大——观众困惑"这是什么？"
  • 建立不足——没有足够的预期铺垫就违背，效果为零

反模式与常见错误

  • 不要在没有充分建立预期的情况下直接违背——违背的力量完全取决于预期的强度，没有铺垫的"意外"对观众来说只是"莫名其妙"，而非"震撼"
  • 不要让违背模式变得可预测——如果每次"虚惊"后面都是"实惊"，观众会预期这个二阶模式，需要在更高层面打破预期（如连续两次虚惊后再实惊）
  • 不要混淆"意外"和"随意"——违背必须在叙事逻辑内，观众需要事后能理解"为什么是这个声音"，否则效果是困惑而非情绪爆发

作者的盲点 / 时代局限

David Sonnenschein 的声音设计理论源自传统电影声音制作，对数字时代的新声音形态（如 ASMR、空间音频、AI 生成音效）覆盖不足。他假设声音设计师有专业录音棚和拟音资源，独立创作者的低成本声音解决方案讨论较少。书中理论框架偏重感知心理学，对文化差异导致的声音审美差异（如东西方对沉默的不同理解）涉及有限。

此外，声音期望的讨论偏重叙事层面的期望管理，对技术层面的期望（如不同播放设备的声音质量预期）讨论不足。此外，Sonnenschein 未充分讨论跨文化语境中声音期望的差异——同一声音符号在不同文化中可能引发不同期望。

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Sound Design Expectation AI skill do?

Sound's emotional power comes from building and violating expectations. Surprise requires prior setup; too-accurate prediction causes boredom.

Why use Sound Design Expectation on TypingMind?

Because you install it once and use it with any model. Sound Design Expectation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Sound Design Expectation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/geegl/directorskills/tree/main/output/books/sound-design/sound-design-expectation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Sound Design Expectation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Sound Design Expectation?

As many as you like. As long as a model supports skills, you can use Sound Design Expectation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Sound Design Expectation AI skill free?

Yes. It is published on GitHub by geegl under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
NousResearch logo

Mono Color

NousResearch
OrganizationPopular

Generate one- or two-ink editorial print poster images.

53.5K
250.4K
9 files
View
NousResearch logo

Pretext

NousResearch
OrganizationPopular

Build creative browser demos with DOM-free text layout.

53.5K
250.4K
3 files
View
NousResearch logo

Sketch

NousResearch
OrganizationPopular

Throwaway HTML mockups: 2-3 design variants to compare.

53.5K
250.4K
Instructions
View
NousResearch logo

Tldraw Offline

NousResearch
OrganizationPopular

Drive and script tldraw offline canvases with an agent.

53.5K
250.4K
3 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇