Skip to content
Skill category

Design and Visual Art skills

Agent skills for visual work in Claude: p5.js generative art, poster canvases, preset themes, brand rules, Slack GIFs and distinctive frontend UI design.

26 skills

About Design and Visual Art

Left to itself, a model reaches for the safest palette and the most common layout. The skills in this category push the other way. Most of them make Claude commit to an idea first, a philosophy, a theme or a brand, and then build the piece from it.

What is here

Making art

  • algorithmic-art has Claude write an algorithmic philosophy, then build it as a seeded p5.js sketch inside an interactive HTML viewer with controls, so the same seed reproduces the same piece.
  • canvas-design treats a poster or static artwork like an art movement: Claude writes a design philosophy, then expresses it as a single crafted PDF or PNG canvas using bundled fonts.
  • slack-gif-creator draws animation frames with Pillow, eases the motion and saves a size-optimized GIF that meets Slack’s limits, either as a small emoji or a larger message GIF.

Styling things you already make

  • theme-factory carries ten preset color palettes and font pairings that Claude applies to slides, documents, reports and HTML pages, or it makes a custom theme on the spot.
  • brand-guidelines bakes in Anthropic’s own brand: the official colors, Poppins and Lora typography and accent rules. It is most useful as a model for writing a brand skill of your own.
  • frontend-design is guidance rather than tooling: it steers Claude away from templated UI toward deliberate choices of palette, type, layout and copy, planned against the brief before any code is written.

How to choose

Decide whether you want a new artifact or a consistent look. For a new piece, algorithmic-art suits generative, code-driven work you can re-seed and tweak, canvas-design suits a single finished image, and slack-gif-creator suits short motion for chat. For consistency across things Claude already produces, theme-factory gives ready-made looks and brand-guidelines shows how to pin one brand down. frontend-design sits on the border with development and also appears under developer tools.

Most of these are prose-led and run nothing on the machine; slack-gif-creator is the exception, with Python scripts for composing, easing and validating frames.

Showing 10 of 26 skillsShell Credentials Network Clear all
Mixed4,075 tokens in use

algorithmic-art

198,136

Design And Visual Art

Anthropic's generative art skill: Claude writes an algorithmic philosophy, then builds it as a seeded p5.js sketch in an interactive HTML viewer.

Skill
62idle
4,075in use
8,493up to
Tokens, counted offlineView skill
Model-led455 tokens in use

brand-guidelines

198,136

Design And Visual Art

Anthropic's brand skill: the official colors, Poppins and Lora typography and accent rules Claude applies to make any artifact look on-brand.

Skill
50idle
455in use
455up to
Tokens, counted offlineView skill
Model-led2,271 tokens in use

canvas-design

198,136

Design And Visual Art

Anthropic's skill for posters and static art: Claude writes a design philosophy as an art movement, then expresses it as one crafted PDF or PNG canvas.

Skill
59idle
2,271in use
2,271up to
Tokens, counted offlineView skill
Model-led1,871 tokens in use

frontend-design

198,136

Design And Visual Art · Developer Tools · Frontend And UI Engineering

Design guidance that pushes Claude toward distinctive, intentional UI instead of templated defaults, from palette and type to layout and copy.

Skill
41idle
1,871in use
1,871up to
Tokens, counted offlineView skill
Model-led579 tokens in use

theme-factory

198,136

Design And Visual Art

Anthropic's theming skill: ten preset color palettes and font pairings Claude applies to slides, docs, reports and HTML pages, or a custom theme made on the spot.

Skill
61idle
579in use
579up to
Tokens, counted offlineView skill
Model-led248 tokens in use

Ad Image Generation

11,199

Advertising And Paid Media · Design And Visual Art

Generates paid ad images from a validated creative brief and brand profile through an image provider you configure, with a manifest of what was made.

Skill
61idle
248in use
248up to
Tokens, counted offlineView skill
Model-led1,689 tokens in use

design-md

11,108

Design And Visual Art

Analyzes a Stitch project's screens, HTML and theme through MCP and writes a DESIGN.md that describes the design language in semantic terms.

Skill
18idle
1,689in use
1,689up to
Tokens, counted offlineView skill
Model-led2,878 tokens in use

taste-design

11,108

Design And Visual Art

Generates a DESIGN.md for Stitch that sets premium UI rules: calibrated color, strict typography, asymmetric layouts, spring motion and banned clichés.

Skill
48idle
2,878in use
2,878up to
Tokens, counted offlineView skill
Model-led3,195 tokens in use

ip-as-logo

6,657

Design And Visual Art

Generate extremely simple, cute, rounded mascot characters with an image model: three proposed directions, six independent candidates, two character colors on one solid background.

Skill
78idle
3,195in use
3,195up to
Tokens, counted offlineView skill
Model-led1,379 tokens in use

get-prompt-from-image

6,167

Design And Visual Art

Analyze a reference image and reverse-engineer a high-fidelity positive and negative prompt, in Chinese and English, for recreating it with an image model.

Skill
85idle
1,379in use
5,367up to
Tokens, counted offlineView skill

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers