Exaggerated Clarity logo

Exaggerated Clarity

Community
dylantarre
exaggerated-clarity

Use when motion needs to read clearly and powerfully—broad comedy, action highlights, important story beats, or any moment that must unmistakably communicate to the audience.

Overview

Publisherdylantarre
Repositoryanimation-principles
Skill nameexaggerated-clarity
Stars
84
Forks
12
Bundled files
Instructions only
LicenseMIT
Links
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Exaggerated Clarity 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.
  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/dylantarre/animation-principles.git /tmp/animation-principles
mkdir -p .claude/skills
cp -r /tmp/animation-principles/skills/02-by-thinking-style/exaggerated-clarity .claude/skills/exaggerated-clarity
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Exaggerated Clarity 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 Exaggerated Clarity 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 Exaggerated Clarity 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.

Exaggerated Clarity

Think like a stage actor projecting to the back row. Subtlety is lost at speed. Your job is to make every intention unmistakable—amplify truth until it can't be missed.

Core Mental Model

Before animating any key moment, ask: Would this read from 50 feet away?

Animation isn't reality—it's reality turned up to 11. Exaggeration isn't lying; it's telling the truth louder. Real life is too subtle for the screen.

The 12 Principles Through Amplification

Exaggeration — The principle itself. Push every quality further than reality. Happy becomes ecstatic. Sad becomes devastated. Fast becomes blurred with speed.

Staging — Exaggeration needs clear framing. Silhouette tests: does the pose read as a black shape? If the attitude is unclear in silhouette, push the pose further.

Squash & Stretch — The most visible tool of exaggeration. Compress more than physics allows. Stretch beyond anatomy. The impossibility creates impact.

Anticipation — Exaggerated windup demands exaggerated payoff. Big anticipation sets up audience expectations—then exceed them.

Timing — Contrast creates clarity. Super-fast action against held poses. The extremes are what register. Middle speeds blur together.

Solid Drawing — Exaggerated proportions must still feel solid. A character stretched to absurdity should still have convincing mass. Volume creates believability within impossibility.

Appeal — Bold choices are appealing. Audiences respond to confidence. Timid exaggeration reads as mistake; committed exaggeration reads as style.

Follow Through & Overlapping Action — Exaggerate the delay. Let secondary elements trail dramatically. Hair that whips, clothes that swirl—push the physics of follow-through.

Secondary Action — Amplify supporting details. If a character is nervous, make their foot tap comically fast. Secondary action underscore primary emotion.

Arcs — Exaggerated motion follows exaggerated arcs. Wide sweeping curves for broad gestures. The bigger the arc, the more readable the motion.

Slow In & Slow Out — Extreme easing creates snap. Very slow buildup, instant action, extended settle. Contrast in timing is exaggeration in the time domain.

Straight Ahead & Pose to Pose — Exaggeration usually works better pose-to-pose. Plan your extreme poses, then push them 30% further before connecting them.

Practical Application

Exaggeration Scales:

  • Realistic: 100% (reference)
  • Feature animation: 120-150%
  • Broad comedy: 150-200%
  • Squash-stretch animation: 200-300%
  • Rubber hose: 300%+

What to Exaggerate:

  • Poses: Push silhouettes further
  • Timing: More contrast between fast and slow
  • Expressions: Bigger facial range
  • Physics: More squash, more stretch
  • Reactions: Delay and amplify

What NOT to Exaggerate:

  • Internal logic (rules you've established)
  • Character consistency
  • Emotional truth (exaggerate expression, not falseness)

When motion feels "mushy" or "unclear":

  1. Strengthen silhouettes
  2. Hold extreme poses longer
  3. Reduce busy secondary action
  4. Increase contrast in timing
  5. Push poses 20% further

When motion feels "cartoony" (unintentionally):

  1. Reduce squash/stretch percentage
  2. Ground physics with more settle time
  3. Add subtle secondary naturalistic motion
  4. Pull back exaggeration to 120% instead of 200%

The Golden Rule

Exaggeration is clarity, not parody. You're not making fun of movement—you're making it visible. The goal is for the audience to feel more, not to notice technique. When exaggeration serves story, it's invisible. When it serves itself, it's showboating.

Frequently asked questions

What does the Exaggerated Clarity AI skill do?

Use when motion needs to read clearly and powerfully—broad comedy, action highlights, important story beats, or any moment that must unmistakably communicate to the audience.

Why use Exaggerated Clarity on TypingMind?

Because you install it once and use it with any model. Exaggerated Clarity 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 Exaggerated Clarity in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dylantarre/animation-principles/tree/main/skills/02-by-thinking-style/exaggerated-clarity. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Exaggerated Clarity?

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 Exaggerated Clarity?

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

Is the Exaggerated Clarity AI skill free?

Yes. It is published on GitHub by dylantarre 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.

View all

Set up your own AI workspace now

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