Problem Diagnosis logo

Problem Diagnosis

Community
dylantarre
problem-diagnosis

Use when animation "feels wrong" but you can't pinpoint why—debugging floaty movement, stiff characters, unclear action, or any motion that isn't working and needs systematic troubleshooting.

Overview

Publisherdylantarre
Repositoryanimation-principles
Skill nameproblem-diagnosis
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 Problem Diagnosis 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/problem-diagnosis .claude/skills/problem-diagnosis
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Problem Diagnosis 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 Problem Diagnosis 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 Problem Diagnosis 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.

Problem Diagnosis

Think like a doctor examining symptoms. Something feels wrong. Your job is to identify the specific principle being violated and prescribe the cure. Systematic diagnosis beats random fixes.

Core Mental Model

When animation feels off, ask: What principle is being violated, and how?

"It doesn't look right" isn't actionable. The 12 principles are your diagnostic checklist. Every animation problem is a principle problem—find which one, and the solution becomes clear.

Diagnostic Framework

Symptom: "Floaty" or "Weightless"

Likely Causes:

  • Missing slow-in/slow-out (objects should accelerate with gravity)
  • Insufficient anticipation before jumps
  • No squash on landing impacts
  • Timing too uniform (everything same speed)
  • Missing secondary weight (hair/clothing not responding to gravity)

Fixes:

  1. Add ease-in at motion start
  2. Add squash frames at impact points
  3. Include settling oscillations after stops
  4. Vary timing based on mass

Symptom: "Stiff" or "Robotic"

Likely Causes:

  • Missing arcs (linear interpolation instead of curves)
  • No overlapping action (all parts move together)
  • Twinning (left and right doing identical things)
  • No secondary action
  • Timing too uniform

Fixes:

  1. Add arc curves to all motion paths
  2. Offset timing of connected body parts
  3. Break symmetry in poses
  4. Add breathing and weight shifts
  5. Include micro-movements

Symptom: "Unclear" or "Hard to Read"

Likely Causes:

  • Poor staging (elements overlap confusingly)
  • Weak silhouettes
  • Insufficient anticipation (action comes from nowhere)
  • Not enough exaggeration
  • Competing attention points

Fixes:

  1. Simplify background during key action
  2. Push poses to clear silhouettes
  3. Extend anticipation timing
  4. Increase exaggeration 20%
  5. Reduce secondary action during primary beats

Symptom: "Boring" or "Lifeless"

Likely Causes:

  • No appeal in character posing
  • Timing lacks contrast (no fast vs. slow)
  • Missing anticipation-payoff structure
  • Insufficient exaggeration
  • No secondary action or texture

Fixes:

  1. Push personality in poses
  2. Create timing contrast (faster fasts, slower slows)
  3. Add clear anticipation beats
  4. Increase exaggeration of key poses
  5. Layer in secondary movement

Symptom: "Cartoony" (Unintentionally)

Likely Causes:

  • Excessive squash and stretch
  • Over-exaggerated timing
  • Physics violations too extreme
  • Follow-through too elastic

Fixes:

  1. Reduce squash/stretch to 10-20% range
  2. Add more frames to smooth extremes
  3. Ground with realistic settling time
  4. Pull back follow-through delay

Symptom: "Too Fast" / "Too Slow"

Likely Causes:

  • Frame count mismatch with intention
  • Missing ease-in or ease-out
  • Key poses not held long enough
  • Anticipation/payoff imbalance

Fixes:

  1. Adjust frame count (add/remove in-betweens)
  2. Check easing curves
  3. Hold key poses 2-4 more frames
  4. Rebalance anticipation vs. action timing

Diagnostic Process

  1. Identify the symptom — Name what's wrong in plain terms
  2. Isolate the problem — Is it the whole scene or specific moments?
  3. Check principles systematically:
    • Timing and spacing?
    • Squash and stretch?
    • Anticipation and follow-through?
    • Arcs?
    • Staging?
    • Exaggeration level?
    • Secondary action?
  4. Test hypothesis — Make one change, evaluate
  5. Iterate — If unfixed, try next most likely principle

The Golden Rule

One fix at a time. Animation problems often have multiple causes, but changing everything at once makes it impossible to learn what worked. Diagnose, treat one principle, evaluate, repeat.

Frequently asked questions

What does the Problem Diagnosis AI skill do?

Use when animation "feels wrong" but you can't pinpoint why—debugging floaty movement, stiff characters, unclear action, or any motion that isn't working and needs systematic troubleshooting.

Why use Problem Diagnosis on TypingMind?

Because you install it once and use it with any model. Problem Diagnosis 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 Problem Diagnosis 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/problem-diagnosis. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Problem Diagnosis?

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 Problem Diagnosis?

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

Is the Problem Diagnosis 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 👇