Best agent skills for designers, page 11

Design, derive, optimize, explain, and diagnose cinematic Eastern xianxia camera direction, storyboards, motion choreography, pacing, continuity locks, keyframes, and per-shot image-to-video prompts.

liyue-aigc/xianxia-cinematic-video-director

Add Solar Icons via @solar-icons/cli to any React, Vue, Svelte, Solid, Angular, React Native, Nuxt, Static, vanilla JS, or Laravel Blade project.

saoudi-h/solar-icons

Authors or edits a custom HyperFrames video composition when no specialized workflow fits, such as multi-scene pieces, montages and brand reels.

heygen-com/hyperframes

Lays timed graphic cards such as lower-thirds, data callouts and quotes over an existing talking-head video, synced to the transcript.

heygen-com/hyperframes

Canonical VideoStudio review authorization and state-transition policy.

Orkas-AI/Orkas-VideoStudio

Install and use goey-toast — a gooey, morphing React toast component built on Sonner with Framer Motion.

anl331/goey-toast

Generate and edit images from the CLI using picture-it. An agent skill from geongeorge/picture-it.

geongeorge/picture-it

Web typography from choosing fonts to spacing, wrapping and accessibility.

trycompai/crm

Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library.

OWWZO/ai-agent

Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it.

awss1i/assay

Render an ARIS Markdown / JSON artifact (IDEAREPORT, AUTOREVIEW, KILLARGUMENT, PAPERPLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading.

wanshuiyin/Auto-claude-code-research-in-sleep

Design CCF experiment protocols and evidence schemas: datasets, baselines, metrics, ablations, and result-table contents.

mikubaka88/CCFA-Skills

Turns an idea, article, outline or audio file into a sourced, reviewable AI video, tracking whether narration uses a human, synthetic or cloned voice.

wanghui2323/ai-video-maker

Replaces Codex's built-in image tool with provider-based generation and editing, fetching reference images first whenever visual accuracy actually matters.

yc-duan/api-image

Agent-native design system infrastructure. An agent skill from Railly/tinte.

Railly/tinte

Generate documentation sites for Python packages with Great Docs.

pymc-labs/pathmc

Create, audit, and repair short page-native diary comics around an existing authorized recurring character, with story-directed page rhythm, exact dialogue, directional-surface proof, and…

ZSeven-W/craft-skills

A skill your agent uses when the user's task involves HiUI (@hi-ui/) — writing HiUI components, debugging HiUI issues, querying HiUI props/docs, migrating from HiUI V4 to V5, or setting up React 19…

XiaoMi/hiui

Creates, refines and exports editable OneWorks 3D geometric avatars for mascots, bots or agents, keeping one shared scene state across preview, share link and export.

oneworks-ai/avatar

Convert fragmented cultural visual materials into traceable asset indexes, visual genes, high-end brand visual systems, poster concepts, image-generation prompts, and refined poster/KV/ad/cover…

dacnay816y62-hub/culture-fragment-poster-engine

Migrate TailwindCSS to StyleX. An agent skill from shadcn-labs/shadcn-cssinjs.

shadcn-labs/shadcn-cssinjs

Call fal.ai Model APIs (auth, upload, subscribe/queue, parse responses).

rtadewald/skills

Set up and author a documentation site with @lobehub/docs-kit (the lobedocs CLI, React Router + Vite static docs used by ui.lobehub.com).

lobehub/lobe-ui

Provides comprehensive Tailwind CSS utility-first styling patterns including responsive design, layout utilities, flexbox, grid, spacing, typography, colors, and modern CSS best practices.

ever-works/ever-works

Implement web accessibility (a11y) standards following WCAG 2.1 guidelines.

surrealdb/docs.surrealdb.com

Turn newly recorded talking-head footage into review-ready vertical video drafts with an explicit edit plan, deterministic FFmpeg rendering, captions, hook cards, audio normalization, and visual QA.

ericosiu/ai-marketing-skills

Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA.

vllm-project/vllm-omni

Comprehensive guide for creating effective landing pages using Next.js or React.

bear2u/my-skills

Turn a research brief, finished script, or generated MP4 into a reviewed and verified vertical explainer video.

runesleo/claude-video-kit

论文方法图解——用视觉图解彻底讲清楚一篇论文到底做了什么、怎么做的. An agent skill from zsyggg/paper-craft-skills.

zsyggg/paper-craft-skills

Generate or edit images, videos, or audio in the current task.

clacky-ai/openclacky

交互式动态视觉叙事生成器 v11.0 (Hybrid Drive Edition)。基于用户输入的任意主题关键词， 通过多轮交互式对话收集需求，利用 React 19 + Tailwind 4 驱动的 Minimal Mono 极简编辑器， 实时操纵隔离在 Iframe 中的硬核 GSAP/WebGL 影视级叙事引擎。

pixelxzen/phantom-motion

Design and UI skill for the Worklog desktop project manager.

regisx001/Worklog

Dedicated YouTube thumbnail generator — interviews you for exactly the style elements you want (environment, text budget, extras, accent color), then renders high-contrast, vibrant, face-consistent…

hassancs91/claude-youtube-editor

Make kinetic-typography motion reels (MP4) in code: showreels, portfolio or work reels, product promos, intro films, "motion design"-style videos with bold condensed type, HUD micro-type…

tuzhechen2005/opus-video-skills

Analyze KiCad projects and PDF schematics: schematics, PCB layouts, Gerbers, footprints, symbols, netlists, and design rules.

aklofas/kicad-happy

AI music generation with ACE-Step 1.5 — background music, vocal tracks, covers, stem extraction for video production.

calesthio/OpenMontage

LofiSu的行为人格Skill。基于GitHub公开数据(282次commit/150次README迭代/50+fork/100+contribution) 的Codex深度挖掘分析报告+小红书卖课行为报告的系统蒸馏， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。

zclllyybb/lofisu-identity-engine

当用户要求把采用 JSON 提交后轮询协议的视频或图片供应商接入 ArcReel，或要求编写、验证、测试、保存自定义调用端点定义时使用。

ArcReel/ArcReel

Animation patterns and best practices for Next.js/React applications.

delphi-ai/animate-skill

Universal visual direction engine for AI image, design, and layout work: model-agnostic decision pipeline (intent, analysis, visual language, planning, recovery/refinement) plus swappable adapters…

Yu-0312/editorial-vision-studio

Distill and apply this repository's Next.js Nextra starter architecture, implemented features, extension points, and migration patterns.

pdsuwwz/nextjs-nextra-starter

Build deterministic animation for HyperFrames using motion rules, transitions, scene blueprints, and runtime adapters.

waker240/FullVideoProductionSkill

梳理项目 UI/UX 设计规范并输出 design-spec.md，评审现有界面并给出按优先级排序的修复建议，或整理指定界面的设计规则。用户要求设计系统、设计规范或完整界面评审时使用；单个颜色、字号或按钮大小的简单问题直接回答。

oil-oil/ui-ux-guide

Writes a complete UI component spec with anatomy, variants, sizes, eight interaction states, design-token mapping and accessibility notes before or alongside code.

plugin87/ux-ui-agent-skills

This skill should be used when generating spec artifacts (research.md, requirements.md, design.md, tasks.md), formatting agent output, structuring phase results, or when any Ralph agent needs…

tzachbon/smart-ralph

Generate images, videos, and audio/music via Lovart AI. An agent skill from lovartai/lovart-skill.

lovartai/lovart-skill

MUST use when the user wants to RENDER or GENERATE an actual image from a description (not just craft prompt text).

Kiyoraka/Project-AI-MemoryCore