Skill Relationships
Skill → Skill usage relationships, with cross-layer references. Same color blocks indicate the same skill form.
Skill Composition
Each skill is designed for a specific kind of caller — some only fire when you name them, others load automatically when the model judges them relevant. The split below summarises both modes at a glance.
These skills only fire when you call them by name. The agent will not load them on its own — they stay inert until invoked.
These skills are loaded automatically by the agent when it judges the context relevant. You usually don't need to call them yourself.
Skill List
A reverse-lookup glossary that maps vague descriptions of web animations or motion effects to their exact terms. By reading user intent and quoting a curated glossary, it returns precise names with definitions. Value: helps users name effects correctly to prompt AIs or designers instead of building them.
A style guide translating Apple's fluid interface and motion design principles to the web. Provides rules for gesture-driven UI, spring animations, interruptibility, velocity handoff, and spatial consistency with code examples. Helps developers build and review Apple-style interfaces that feel physical and alive.
Encodes Emil Kowalski's UI polish philosophy: animation decisions, component design, invisible details. Uses a Before/After review table and a 4-step animation framework with custom easings and spring configs. Outputs actionable craft guidance that makes software feel great.
A read-only search skill that sweeps a codebase or UI for moments genuinely needing motion, rejecting most candidates via a 4-question gate (frequency, purpose, speed, function). It proposes precise animation recipes with exact values and hands off implementation. Value: restrained, high-leverage motion suggestions that avoid over-animation.
Acts as a senior motion advisor to survey a codebase's animation and motion code, then produce a prioritized audit and self-contained implementation plans for other agents to execute. Uses read-only recon, parallel audit, vetting, and precise plan authoring. Delivers a roadmap of high-leverage animation fixes without modifying source code.
Reviews animation and motion code against a high craft bar from Emil Kowalski's design engineering philosophy. Method: measure diffs against ten non-negotiable standards and escalation triggers, then output a findings table and tiered verdict (Block/Approve). Value: catches sluggish, non-GPU, or mis-origined motion before merge, earning approval only on truly crafted animation.
Installation
Copy and run in your terminal to add emilkowalski/skills to your Agent environment.
npx skills add emilkowalski/skills