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 9 of 26 skillsScript-led Clear all
Script-led1,919 tokens in use

slack-gif-creator

198,136

Design And Visual Art

Anthropic's skill for Slack GIFs: Claude draws frames with Pillow, eases the motion and saves a size-optimized emoji or message GIF that meets Slack's limits.

Skill
50idle
1,919in use
1,919up to
Tokens, counted offlineView skill
Script-led849 tokens in use

Brand

152,223

Design And Visual Art

Keep brand voice, visual identity and messaging in one guidelines file, then sync it to design tokens and check assets against it.

Skill
35idle
849in use
13,446up to
Tokens, counted offlineView skill
Script-led3,588 tokens in use

Design

152,223

Design And Visual Art

One design skill for logos, corporate identity mockups, SVG icons, banners, slides and social images, routing to brand, token and UI styling skills.

Skill
151idle
3,588in use
22,193up to
Tokens, counted offlineView skill
Script-led1,725 tokens in use

Design System

152,223

Design And Visual Art · Frontend And UI Engineering

Three-layer design tokens, component specs and token-compliant slide decks, with scripts that generate CSS and flag hardcoded values.

Skill
52idle
1,725in use
20,797up to
Tokens, counted offlineView skill
Script-led7,632 tokens in use

Taste Skill (design-taste-frontend)

119,418

Design And Visual Art · Frontend And UI Engineering

An agent skill that builds company websites from one design system and checks each page in headless Chrome before the build ends.

Skill
218idle
7,632in use
38,202up to
Tokens, counted offlineView skill
Script-led4,548 tokens in use

hallmark

58,705

Design And Visual Art · Frontend And UI Engineering

A design skill by Together AI that builds new web pages from a catalog of fifty themes under a hard floor of rules, then lints the result in a real browser.

Skill
58idle
4,548in use
63,059up to
Tokens, counted offlineView skill
Script-led6,830 tokens in use

Huashu Design

29,971

Design And Visual Art

Turns one sentence into a finished HTML design: prototypes, decks, animations, infographics and Xiaohongshu image sets, drafted as three real directions first.

Skill
151idle
6,830in use
117,728up to
Tokens, counted offlineView skill
Script-led4,268 tokens in use

character-refs

6,892

Design And Visual Art

Generates a set of reference images for any story character from one description: a front full-body anchor, then headshot, profile, back and detail views.

Skill
305idle
4,268in use
10,125up to
Tokens, counted offlineView skill
Script-led2,272 tokens in use

generate2dmedia

5,892

Design And Visual Art

The art-route layer of the Forge skills: one command that generates an image or image-to-video clip through a configured API or a local Codex or Grok CLI, with a spend ledger.

Skill
213idle
2,272in use
49,545up 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