# Canvas Design — style skill for art styles

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the use-case page.

Design posters and visual art as PNG or PDF from a written design philosophy, with 54 bundled fonts.

- **Type:** [Style](https://skills.varg.ai/styles.md) · [Art styles](https://skills.varg.ai/browse/skills/art-direction.md)
- **Slug:** `anthropic-canvas-design`
- **Status:** live
- **Publisher:** Anthropic (vendor, verified)
- **License:** Apache-2.0
- **Source:** https://github.com/anthropics/skills/tree/main/skills/canvas-design
- **Works in:** Claude Code, Claude.ai, Codex, Cursor, Gemini CLI
- **Cost:** Free — runs locally (built into paid Claude.ai plans)
- **Adoption:** 122,700 installs, 183,988 GitHub stars (skills.sh, 2026-10-26)

## What it does

Produces original static visual art and posters as `.png` or `.pdf`: the agent first writes a visual philosophy, then composes the canvas, and a mandatory final pass refines rather than adds. It ships 54 open-licensed (OFL) fonts so typography renders consistently, and supports multi-page output.

## Use when

- A poster, cover or art print
- Typographic or abstract visual art
- A multi-page visual piece as PDF

## Not for

- Copying an existing artist's work

## Install

- Claude Code: `/plugin marketplace add anthropics/skills && /plugin install example-skills@anthropic-agent-skills`
- Codex: `npx skills add anthropics/skills --skill canvas-design -a codex`
- Cursor: `npx skills add anthropics/skills --skill canvas-design -a cursor`
- Gemini CLI: `npx skills add anthropics/skills --skill canvas-design -a gemini-cli`

## Example output

https://skills.varg.ai/previews/anthropic-canvas-design.webp — Frame (~60.8 s) from Anthropic's 'Claude can now use Skills' launch video: three 'Shelldon' concept posters Claude made with a poster-design skill that first writes a design philosophy per poster, the approach canvas-design packages (credit: Anthropic (Claude), https://x.com/claudeai/status/1978855432123723909)

## More art styles skills

- [fal Game Dev](https://skills.varg.ai/skills/fal-gamedev.md): Generate 2D pixel-art game assets: characters, sprite sheets, walk and attack cycles, parallax backgrounds.
- [Algorithmic Art](https://skills.varg.ai/skills/anthropic-algorithmic-art.md): Create original generative art in p5.js: write an algorithmic philosophy, then code it with seeded randomness.
- [Lemo-Opuscar Film Styles](https://skills.varg.ai/skills/lemo-opuscar.md): 59 film styles made entirely in code (oil paint, watercolor, ukiyo-e, satellite briefing, exploded teardown).
- [Halftone Collage B-roll](https://skills.varg.ai/skills/gbro-collage-broll.md): Editorial halftone paper-collage B-roll from one line of script, with three approval gates before any video spend.
- [Generative Art (Camille Roux)](https://skills.varg.ai/skills/genart-skill.md): Long-form generative art craft from Camille Roux: hash-seeded determinism, traits and rarity, verification, export.

## Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt