Art & Design

Excalidraw canvas toolkit for creating, editing, and refining diagrams on a live canvas. Use when an agent needs to (1) draw or lay out diagrams, (2) iteratively refine them by describing the scene and screenshotting its own work, (3) export/import .excalidraw files or PNG/SVG images, (4) save/restore canvas snapshots, (5) convert Mermaid to Excalidraw, or (6) perform element-level CRUD, alignment, distribution, grouping, duplication, and locking. Primary interface is the bundled CLI (npx -y mcp-excalidraw-server <command>) which auto-starts the canvas server; MCP tools and a REST API are equivalent alternatives.

This skill should be used when the user explicitly says "Nothing style", "Nothing design", "/nothing-design", or directly asks to use/apply the Nothing design system. NEVER trigger automatically for generic UI or design tasks.

Create, revise, critique, or document high-attention color themes for interiors, graphics, brands, web pages, interfaces, data displays, and print. Use whenever a request needs a coordinated palette, color scheme, proportions, placement, mixing, or visual hierarchy; not for one isolated color choice.

Skills that teach a coding agent how to set up Peak in a repository

日本での暮らしを手伝うAIエージェント向けスキル集 - 気象庁・内閣府・カーリルの公式データを使ったログイン不要の照会スキル

台灣日常生活查詢的 AI 代理技能集(官方公開資料・免登入免金鑰)/ AI-agent skills for daily life in Taiwan - keyless official open data

Fan-built, unofficial agent skills for BTS fans. First skill: ticket-scam safety with a deterministic official-domain allowlist. English-first, Korean summaries. MIT.

Codex Skill for turning product requirements and UI prototypes into functional, visually verified web interfaces.

Codex skill for photo-based architectural reconstruction prompts and analysis illustrations

Codex skill for generating technically accurate educational infographic images.

A Codex skill for reviewed image2 page previews, editable Figma designs, and responsive frontend implementation.

Open-source Codex skill for free-form AI slide design and editable PowerPoint reconstruction using Agent interpretation and OpenCV measurement.

Disciplined ideation and analogical inference, packaged as a Claude skill (bilingual TR/EN). Every generated idea ships with its illet, breaking point, cheapest refutation, named prior art and arbiter.

Evidence-gated Codex Skill for industrial sensor reference image briefs.

A Codex skill for TTRPG rules research, adventure design, character creation, homebrew development, and game mastering, with source citations.

Reusable Codex and Claude skills for mobile UI craft and AI-generated UI audits

A family of portable Agent Skills for the software-development lifecycle, built to the Skill Design Specification (SDS)

Production-ready Image-to-2D-Game-Asset Agent Skill & Pipeline (Godot, Unity, Phaser, PixiJS)

Session ritual for coding agents: durable git-committed memory, a start rite, a wrap rite, and the guards that keep them honest. Claude Code + Cursor plugin.

A curated UI design guide: discover inspiration, tools, components and AI skills by task. 前端 UI 设计资源与 Skills 选择指南。

General-purpose Claude Code skills: a design-to-build workflow (grill-me, design-brief, information-architecture, design-tokens, brief-to-tasks, frontend-design, design-review) plus token-saver and work-report.

摸鱼搭子角色设计师：渐进问答、完整动画角色制作与网页审核的 Codex skill

Multi-model orchestration plugin for Claude Code: an Opus supervisor delegates coding tasks to Haiku/Sonnet subagents, consults a Fable advisor, reviews every diff, and optionally routes work to OpenAI Codex. One orchestrator, the right model for every job.

14 agent skills for sales and client success: discovery, proposals, pipeline health, and renewals.