library/skills/core-components/SKILL.md
Core component library and design system patterns. Use when building UI, using design tokens, or working with the component library.
npx skillsauth add superesty/unified-ag-kit core-componentsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use components from your core library instead of raw platform components. This ensures consistent styling and behavior.
NEVER hard-code values. Always use design tokens.
// CORRECT - Use tokens
<Box padding="$4" marginBottom="$2" />
// WRONG - Hard-coded values
<Box padding={16} marginBottom={8} />
| Token | Value |
|-------|-------|
| $1 | 4px |
| $2 | 8px |
| $3 | 12px |
| $4 | 16px |
| $6 | 24px |
| $8 | 32px |
// CORRECT - Semantic tokens
<Text color="$textPrimary" />
<Box backgroundColor="$backgroundSecondary" />
// WRONG - Hard-coded colors
<Text color="#333333" />
<Box backgroundColor="rgb(245, 245, 245)" />
| Semantic Token | Use For |
|----------------|---------|
| $textPrimary | Main text |
| $textSecondary | Supporting text |
| $textTertiary | Disabled/hint text |
| $primary500 | Brand/accent color |
| $statusError | Error states |
| $statusSuccess | Success states |
<Text fontSize="$lg" fontWeight="$semibold" />
| Token | Size |
|-------|------|
| $xs | 12px |
| $sm | 14px |
| $md | 16px |
| $lg | 18px |
| $xl | 20px |
| $2xl | 24px |
Base layout component with token support:
<Box
padding="$4"
backgroundColor="$backgroundPrimary"
borderRadius="$lg"
>
{children}
</Box>
Horizontal and vertical flex layouts:
<HStack gap="$3" alignItems="center">
<Icon name="user" />
<Text>Username</Text>
</HStack>
<VStack gap="$4" padding="$4">
<Heading>Title</Heading>
<Text>Content</Text>
</VStack>
Typography with token support:
<Text
fontSize="$lg"
fontWeight="$semibold"
color="$textPrimary"
>
Hello World
</Text>
Interactive button with variants:
<Button
onPress={handlePress}
variant="solid"
size="md"
isLoading={loading}
isDisabled={disabled}
>
Click Me
</Button>
| Variant | Use For |
|---------|---------|
| solid | Primary actions |
| outline | Secondary actions |
| ghost | Tertiary/subtle actions |
| link | Inline actions |
Form input with validation:
<Input
value={value}
onChangeText={setValue}
placeholder="Enter text"
error={touched ? errors.field : undefined}
label="Field Name"
/>
Content container:
<Card padding="$4" gap="$3">
<CardHeader>
<Heading size="sm">Card Title</Heading>
</CardHeader>
<CardBody>
<Text>Card content</Text>
</CardBody>
</Card>
const MyScreen = () => (
<Screen>
<ScreenHeader title="Page Title" />
<ScreenContent padding="$4">
{/* Content */}
</ScreenContent>
</Screen>
);
<VStack gap="$4" padding="$4">
<Input label="Name" {...nameProps} />
<Input label="Email" {...emailProps} />
<Button isLoading={loading}>Submit</Button>
</VStack>
<HStack
padding="$4"
gap="$3"
alignItems="center"
borderBottomWidth={1}
borderColor="$borderLight"
>
<Avatar source={{ uri: imageUrl }} size="md" />
<VStack flex={1}>
<Text fontWeight="$semibold">{title}</Text>
<Text color="$textSecondary" fontSize="$sm">{subtitle}</Text>
</VStack>
<Icon name="chevron-right" color="$textTertiary" />
</HStack>
// WRONG - Hard-coded values
<View style={{ padding: 16, backgroundColor: '#fff' }}>
// CORRECT - Design tokens
<Box padding="$4" backgroundColor="$backgroundPrimary">
// WRONG - Raw platform components
import { View, Text } from 'react-native';
// CORRECT - Core components
import { Box, Text } from 'components/core';
// WRONG - Inline styles
<Text style={{ fontSize: 18, fontWeight: '600' }}>
// CORRECT - Token props
<Text fontSize="$lg" fontWeight="$semibold">
When creating components, use token-based props:
interface CardProps {
padding?: '$2' | '$4' | '$6';
variant?: 'elevated' | 'outlined' | 'filled';
children: React.ReactNode;
}
const Card = ({ padding = '$4', variant = 'elevated', children }: CardProps) => (
<Box
padding={padding}
backgroundColor="$backgroundPrimary"
borderRadius="$lg"
{...variantStyles[variant]}
>
{children}
</Box>
);
development
Expert in LangGraph - the production-grade framework for building stateful, multi-actor AI applications. Covers graph construction, state management, cycles and branches, persistence with checkpointers, human-in-the-loop patterns, and the ReAct agent pattern. Used in production at LinkedIn, Uber, and 400+ companies. This is LangChain's recommended approach for building agents. Use when: langgraph, langchain agent, stateful agent, agent graph, react agent.
development
Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.
tools
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
development
Expert Kubernetes architect specializing in cloud-native infrastructure, advanced GitOps workflows (ArgoCD/Flux), and enterprise container orchestration. Masters EKS/AKS/GKE, service mesh (Istio/Linkerd), progressive delivery, multi-tenancy, and platform engineering. Handles security, observability, cost optimization, and developer experience. Use PROACTIVELY for K8s architecture, GitOps implementation, or cloud-native platform design.