agent-harness-design
Designing agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool…
Use when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation. Do not use for static styling, backend/API work, or animation in another runtime unless
$ npx -y skills add AnastasiyaW/codex-claude-code-config --skill motion-framer --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/motion-framerContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation. Do not use for static styling, backend/API work, or animation in another runtime unless
name: motion-framer description: Use when implementing Motion or Framer Motion in React/JavaScript: interactive UI components, micro-interactions, gestures, layout or page transitions, and scroll-based animation. Do not use for static styling, backend/API work, or animation in another runtime unless Motion/Framer Motion is an explicit dependency.
Motion (formerly Framer Motion) is a production-ready animation library for React and JavaScript that enables declarative, performant animations with minimal code. It provides `motion` components that wrap HTML elements with animation superpowers, supports gesture recognition (hover, tap, drag, focus), and includes advanced features like layout animations, exit animations, and spring physics.
**When to use this skill:**
**Technology:**
Convert any HTML/SVG element into an animatable component by prefixing with `motion.`:
import { motion } from "framer-motion"
// Regular HTML becomes motion component
<motion.div />
<motion.button />
<motion.svg />
<motion.path />Every motion component accepts animation props like `animate`, `initial`, `transition`, and gesture props like `whileHover`, `whileTap`, etc.
The `animate` prop defines the target animation state. When values change, Motion automatically animates to them:
// Simple animation - x position changes
<motion.div animate={{ x: 100 }} />
// Multiple properties
<motion.div animate={{ x: 100, opacity: 1, scale: 1.2 }} />
// Animates when state changes
const [isOpen, setIsOpen] = useState(false)
<motion.div animate={{ width: isOpen ? 300 : 100 }} />Set the initial state before animation using the `initial` prop:
<motion.div
initial={{ opacity: 0, y: 50 }}
animate={{ opacity: 1, y: 0 }}
/>Set `initial={false}` to disable initial animations on mount.
Control how animations move between states using the `transition` prop:
// Duration-based
<motion.div
animate={{ x: 100 }}
transition={{ duration: 0.5, ease: "easeInOut" }}
/>
// Spring physics
<motion.div
animate={{ scale: 1.2 }}
transition={{ type: "spring", stiffness: 300, damping: 20 }}
/>
// Different transitions for different properties
<motion.div
animate={{ x: 100, opacity: 1 }}
transition={{
x: { type: "spring", stiffness: 300 },
opacity: { duration: 0.2 }
}}
/>**Transition types:**
Organize animation states using named variants for cleaner code and propagation to children:
const variants = {
hidden: { opacity: 0, y: 20 },
visible: { opacity: 1, y: 0 },
exit: { opacity: 0, scale: 0.9 }
}
<motion.div
variants={variants}
initial="hidden"
animate="visible"
exit="exit"
/>**Variant propagation** - Children automatically inherit parent variant states:
const containerVariants = {
hidden: { opacity: 0 },
visible: {
opacity: 1,
transition: {
staggerChildren: 0.1 // Stagger child animations
}
}
}
const itemVariants = {
hidden: { x: -20, opacity: 0 },
visible: { x: 0, opacity: 1 }
}
<motion.ul variants={containerVariants} initial="hidden" animate="visible">
<motion.li variants={itemVariants} />
<motion.li variants={itemVariants} />
<motion.li variants={itemVariants} />
</motion.ul>Animate on hover using `whileHover` prop:
// Simple hover effect
<motion.button
whileHover={{ scale: 1.1 }}
transition={{ duration: 0.2 }}
>
Hover me
</motion.button>
// Multiple properties
<motion.div
whileHover={{
scale: 1.05,
backgroundColor: "#f0f0f0",
boxShadow: "0px 10px 30px rgba(0, 0, 0, 0.2)"
}}
>
Hover card
</motion.div>
// With custom transition
<motion.button
whileHover={{
scale: 1.2,
transition: { duration: 0.1 } // Transition for gesture start
}}
transition={{ duration: 0.5 }} // Transition for gesture end
>
Button
</motion.button>**Hover with nested elements:**
<motion.div whileHover="hover" variants={cardVariants}>
<motion.h3 variants={titleVariants}>Title</motion.h3>
<motion.img variants={imageVariants} />
</motion.div>Animate on tap/press using `whileTap` prop:
// Scale down on tap
<motion.button
whileTap={{ scale: 0.9 }}
>
Click me
</motion.button>
// Combined hover + tap
<motion.button
whileHover={{ scale: 1.1 }}
whileTap={{ scale: 0.95, rotate: 3 }}
>
Interactive button
</motion.button>
// With variants
const buttonVariants = {
rest: { scale: 1 },
hover: { scale: 1.1 },
pressed: { scale: 0.95 }
}
<motion.button
variants={buttonVariants}
initial="rest"
whileHover="hover"
whileTap="pressed"
>
Button
</motion.button>Make elements draggable with the `drag` prop:
// Basic dragging (both axes) <motion.div drag /> // Constrain to axis <motion.div drag="x" /> // Only horizontal <motion.div drag="y" /> // Only vertical // Drag constraints
A practical configuration kit for Claude Code, Codex, and other coding agents. It contains architectural principles, enforcement hooks, skills, drop-in rules, starter templates, and dynamic-workflow commands.
Designing agent harnesses and tool systems — risk taxonomy for tools, permission decisions, draft/commit pattern, structured tool…
Use when designing, auditing, refactoring, or explaining an agentic harness for any domain, especially when work must continue…
Практическая инженерия диффузионных моделей: архитектуры, обучение, инференс, оптимизация памяти. Использовать при любых задачах…
Expert prompt engineering for FLUX.2 [klein] image generation and editing model. Use this skill whenever the user wants to create…
Plan or review LoRA and edit-training work specifically for FLUX.2 Klein or Qwen-Image-Edit, including paired datasets,…
Forensic image-to-prompt compiler for image generation models. Use this skill whenever the user wants to: convert/describe an…