Restart Claude Code after copying so it picks up the new skill.
Use it in TypingMind
Enable Animations 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.
SkillsLoad skill"animations"
GPT-6 Astra
The model loads Animations 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 Animations 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.
Animations
Software Mansion's production animation patterns for React Native on Reanimated 4 and the New Architecture.
Load at most one reference file per question. For API signatures and config options, webfetch the documentation pages linked in each reference file.
Version Check
Read the installed Reanimated version before writing animation code: node_modules/react-native-reanimated/package.json or the lockfile, not the package.json range. Reanimated 3.x has no CSS transitions or animations; use shared values there. On 4.x, a feature used below the version that added it (table in animations.md) is silently ignored or throws: do not emit it, and if the user asked for that feature, say which version adds it.
Critical Rules
NEVER use runOnJS. It is removed in Reanimated 4. Use scheduleOnRN(fn, ...args) from react-native-worklets instead. This applies everywhere: scroll handlers, gesture callbacks, useAnimatedReaction, useFrameCallback, and any other worklet context.
References
File
When to read
animations.md
Choosing between CSS transitions, CSS animations, and shared value animations; CSS feature availability by Reanimated version; CSS transition and CSS animation patterns and rules; CSS callbacks (onCSS*, 4.6.0+); animating text; infinite animation cleanup; scheduleOnRN
css-pseudo-selectors.md
Interaction state without React state: :hover, :active, :active-deepest, :focus, :focus-within (4.5.0+), selector precedence, the property lock, per-platform press traps
animation-functions.md
Gotchas and rules for core hooks (useSharedValue, useAnimatedStyle, useAnimatedProps, useDerivedValue); withSpring config modes; withRepeat and withClamp caveats; composing animations
layout-animations.md
Entering/exiting animation gotchas (nativeID conflict, view flattening); layout transitions; keyframe animation rules; list item animations (itemLayoutAnimation); shared element transitions
Canvas animations with @shopify/react-native-skia; Reanimated integration (shared values as direct props); interpolateColors; retained vs immediate mode (Picture API); path animations (usePathInterpolation, usePathValue); useClock; gesture integration and element tracking; SKSL runtime shaders and image filters; textures
canvas-atlas.md
Atlas for batched sprite/tile animation; useTexture, useRSXformBuffer; RSXform matrix format ([scos, ssin, tx, ty])
gpu-animations.md
GPU shader animations; react-native-wgpu Canvas and device setup; TypeGPU typed pipelines; Reanimated + WebGPU worklet integration; compute pipelines for particle systems, physics, and simulations; @typegpu/noise (Perlin noise, PRNG); @typegpu/sdf (signed distance shapes); Three.js / React Three Fiber for 3D
svg-animations.md
Animating SVG elements and paths with Reanimated; createAnimatedComponent for SVG; progress arcs; pulsing circles
Production animation patterns for React Native using Reanimated 4, Skia, WebGPU, and TypeGPU. Covers CSS transitions, CSS animations, CSS pseudo-selectors, CSS callbacks, shared value animations, canvas animations with react-native-skia, GPU shader animations, layout animations, scroll-driven animations, particle systems, procedural noise, SDF rendering, performance tuning, and accessibility. Trigger on: Reanimated, useSharedValue, useAnimatedStyle, withSpring, withTiming, withDecay, withRepeat, withSequence, CSS transition, CSS animation, layout animation, FadeIn, SlideIn, ZoomIn, LinearTr...
Why use Animations on TypingMind?
Because you install it once and use it with any model. Animations 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 Animations in TypingMind?
Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/software-mansion-labs/skills/tree/main/skills/react-native-best-practices/references/animations. 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 Animations?
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 Animations?
As many as you like. As long as a model supports skills, you can use Animations with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.
Is the Animations AI skill free?
It is published on GitHub by software-mansion-labs. Check the repository for licensing terms. 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.
