Dev.Cds Mobile logo

Dev.Cds Mobile

Organization
coinbase
dev.cds-mobile

USE THIS when asked to work on a new or existing (MOBILE) CDS React component in packages/mobile

Overview

Publishercoinbase
Repositorycds
Skill namedev.cds-mobile
Stars
506
Forks
114
Bundled files
Instructions only
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 coinbase on GitHub. Read the source before you install it.

Installation

Install the Dev.Cds Mobile 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/coinbase/cds/tree/master/.claude/skills/dev.cds-mobile
  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/coinbase/cds.git /tmp/cds
mkdir -p .claude/skills
cp -r /tmp/cds/.claude/skills/dev.cds-mobile .claude/skills/dev.cds-mobile
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dev.Cds Mobile 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 Dev.Cds Mobile 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 Dev.Cds Mobile 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.

CDS Mobile Package Guidelines

Mobile-specific patterns for @coinbase/cds-mobile.

Component Config Adoption (Mobile)

Use this guidance when adding ComponentConfigProvider defaults for the specific component you are editing.

Required implementation pattern

  1. Register the component in packages/mobile/src/core/componentConfig.ts using its *BaseProps:
ts
import type { MyComponentBaseProps } from '../category/MyComponent';

export type ComponentConfig = {
  MyComponent?: ConfigResolver<MyComponentBaseProps>;
};
  1. Adopt useComponentConfig in the component and destructure from merged props:
tsx
import { useComponentConfig } from '../hooks/useComponentConfig';

export const MyComponent = memo((_props: MyComponentProps) => {
  const mergedProps = useComponentConfig('MyComponent', _props);
  const { style, ...props } = mergedProps;

  return <Pressable style={style} {...props} />;
});

Rules to preserve behavior

  • Provider config supplies defaults only; local props must continue to win.
  • Use _props as the input variable and mergedProps as the configured output.
  • Type resolver entries with *BaseProps (not full *Props).
  • Keep scope to prop-level theming defaults; do not alter component behavior or control flow.
  • When practical during the same change, prefer arrow-function component declarations.

Styling with StyleSheet

Use StyleSheet.create for static styles and useTheme() for dynamic values:

tsx
import { StyleSheet, type StyleProp, type ViewStyle } from 'react-native';

const styles = StyleSheet.create({
  container: { position: 'relative', width: '100%' },
});

// Dynamic styles via theme hook
const theme = useTheme();
const dynamicStyle = {
  backgroundColor: theme.color.bgPrimary,
  padding: theme.space[2],
};

<View style={[styles.container, dynamicStyle, style]} />;

Inline styles

  • Mobile components should all expose a style and styles object props for overriding default styles.
  • As styling is a concern of that specific component, the style and styles props should never be on the *BaseProps type.
  • styles can be used for granular overrides on child elements within the component.
  • Always merge styles into a react-native style array with useMemo in the correct order (default styles => style prop => styles[ELEMENT_NAME] prop).

Example:

tsx
type ComponentProps = ComponentBaseProps & {
  style?: StyleProp<ViewStyle>;
  styles?: {
    root?: StyleProp<ViewStyle>;
    label?: StyleProp<TextStyle>;
  };
};

const theme = useTheme();
const containerStyles = useMemo(
  () => [
    { backgroundColor: theme.color.bgPrimary }, // default styles
    style, // from props
    styles.root, // from props
  ],
  [theme.color.bgPrimary, animatedStyles, style]
);

// Apply to component
<Box style={containerStyles}>

Animation

React Native Reanimated

tsx
import Animated, { useAnimatedStyle, useSharedValue, withTiming } from 'react-native-reanimated';

const opacity = useSharedValue(0);
const animatedStyle = useAnimatedStyle(() => ({
  opacity: opacity.value,
  transform: [{ translateY: withTiming(opacity.value * -8) }],
}));

<Animated.View style={animatedStyle} />;

We DO NOT use React-Spring anymore for animations on mobile.

Gesture Handling

Use react-native-gesture-handler:

tsx
import { Gesture, GestureDetector } from 'react-native-gesture-handler';

const panGesture = useMemo(
  () =>
    Gesture.Pan()
      .onStart(() => {
        /* ... */
      })
      .onUpdate(({ translationX }) => {
        /* ... */
      })
      .onEnd(({ translationX, velocityX }) => {
        /* ... */
      })
      .withTestId(testID)
      .runOnJS(true),
  [dependencies],
);

<GestureDetector gesture={panGesture}>
  <Animated.View>{/* ... */}</Animated.View>
</GestureDetector>;

Layout Measurement

Use onLayout callback instead of ResizeObserver:

tsx
const [size, onLayout] = useLayout();
<View onLayout={onLayout} />

// Or inline
<View onLayout={(e) => setHeight(e.nativeEvent.layout.height)} />

Accessibility

  • Use appropriate accessibilityLabel, accessibilityHint, and accessibilityRole, accessibilityState props
  • Support screen readers (VoiceOver and TalkBack)
  • Ensure touch targets meet minimum size requirements (44x44 points)

Example: Use React Native accessibility props:

tsx
<View
  accessible
  accessibilityRole="adjustable"
  accessibilityLabel="Product carousel"
  accessibilityLiveRegion="polite"
>
  <Pressable
    accessibilityState={{ selected: isActive, disabled }}
    accessibilityActions={[{ name: 'activate' }]}
    onAccessibilityAction={handleAccessibilityAction}
  />
</View>

Screen Reader Content

tsx
// Hide visual content from screen readers
<View accessibilityElementsHidden importantForAccessibility="no-hide-descendants">
  {/* Animated/visual content */}
</View>

// Provide accessible alternative
<Text
  importantForAccessibility="yes"
  accessibilityLiveRegion="polite"
  style={{ color: 'transparent', position: 'absolute' }}
>
  {accessibleLabel}
</Text>

Reference Components

  • SlideButton: gesture handling, spring animations, accessibility actions
  • RollingNumber: Reanimated, measurement patterns, screen reader content
  • Select (alpha/): controlled/uncontrolled, Drawer integration
  • Stepper: direction-based defaults, shared logic from cds-common
  • Tour: animations, complexity
  • DatePicker: complexity

Frequently asked questions

What does the Dev.Cds Mobile AI skill do?

USE THIS when asked to work on a new or existing (MOBILE) CDS React component in packages/mobile

Why use Dev.Cds Mobile on TypingMind?

Because you install it once and use it with any model. Dev.Cds Mobile 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 Dev.Cds Mobile in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/coinbase/cds/tree/master/.claude/skills/dev.cds-mobile. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Dev.Cds Mobile?

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 Dev.Cds Mobile?

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

Is the Dev.Cds Mobile AI skill free?

It is published on GitHub by coinbase. 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.

View all

Set up your own AI workspace now

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