#111111th of 389 in Skills, plugins and prompts
skills
Agent skills for UI animation, design review and mobile-native polish
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 56k
- License
- MIT
- Last commit
- Nov 2026
- Language
- Markdown
1,241 on 20 Apr 202656,027 on 9 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A set of 17 markdown skill files for coding agents, written by Emil Kowalski, covering UI animation, design review and related frontend work. Skills include animate, review-animations, improve-animations, animation-performance, mobile-native, break-ui, write-swift and a guide to the Sonner toast library. They encode rules such as easing choice so agents avoid common mistakes.
Who it is for: Frontend engineers and designers using coding agents to build polished UIs
Strengths
- Covers animation end to end: build, review, audit, choreograph, remove, performance
- Includes React Native/Expo and Swift skills alongside web
- One-line install with npx skills@latest add emilkowalski/skills
- Plain markdown skill files, easy to read and adapt
Weaknesses
- Opinionated rules from one author's experience, not configurable
- Only useful with agents that support the skills format
- Several skills are web-specific, such as ask-sonner and pick-ui-library
- No tests or evals shown to measure the effect on agent output
What it needs
- no GPU
- Needs Node.js (npx), skills CLI
Quick answers
Is skills open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 389| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |