Design · Source review 2026-10-20

Anthropic Canvas Design Skill

Develops a visual concept and expresses it as a static PNG or PDF composition. It is aimed at original artwork and graphic layout, with a written design rationale supporting decisions about shape, spacing, color and typography.

Publisher: Anthropic · Editorial profile by AI Tools Ratings · Review method

Not runtime tested; source-document review only. No security certification.

What task is this skill designed for?

Produce an original event poster with one approved headline, a date and a restrained visual concept suitable for a specified print size.

What input and output should you expect?

Input: The poster’s purpose, approved wording, intended dimensions, export format and any brand or asset restrictions.

Output: Expected, not independently tested: a design rationale and a static PNG or PDF. These files should not be presented as editable Figma components or an interactive web page.

What does it need to run?

An agent environment that can create files and render a graphic or PDF, plus any font or drawing dependencies used by the chosen implementation. Bundled assets and fonts require their own availability and license checks.

Published by Anthropic as a Claude skill example; its repository documents Claude Code installation. Not independently installed or executed here.

How should you approach installation?

  1. Inspect the pinned source, accompanying assets and license terms.
  2. Set up a non-sensitive local output folder and the rendering environment.
  3. Generate a small trial composition and verify the export format before creating a final deliverable.

Installation guide: discovery, dependencies and runtime checks

What files, accounts or data can it access?

Can read approved assets, write image or PDF files and invoke rendering tools. Keep output paths explicit so trial artwork does not overwrite source material.

What does the skill cost?

Skill source has no listed purchase price. Rendering software, paid fonts and agent usage may add costs.

What are its limits and alternatives?

A visually pleasing export may still be unsuitable for print because of dimensions, resolution or color handling. Text-heavy documents and interactive layouts need a different workflow. The source asks for original work rather than copying an artist’s existing design.

Use frontend-design for a responsive page and a document-specific tool for a report with substantial text. Choose canvas-design for a static composition with a clear visual brief.

What could you ask in a small trial?

Try this with a small sample:

Create an original A4 event-poster concept using only this approved headline and date. Export a PDF and preview PNG, and state the dimensions and fonts used. Do not copy a named artist’s work.

How would you verify the result?

  1. Inspect the export at its intended size for clipped or unreadable text.
  2. Confirm dimensions and image resolution with the intended delivery requirements.
  3. Verify fonts and supplied assets are permitted for the actual use.

Use a baseline and record acceptance evidence before treating a successful task as a reliable workflow.

Which source and license were checked?

Read the reviewed SKILL.md at its pinned commit · Complete reviewed folder

Repository and current publisher guidance

Checked:

Apache-2.0 — identified in skills/canvas-design/LICENSE.txt at the reviewed commit. Third-party assets and dependencies may have separate terms. License evidence

Version details and review scope

Source: anthropics/skills/skills/canvas-design
Reviewed commit: dbd4588f9e1033efb41dad4bef2f7947c8993d44

SKILL.md SHA-256: a1f288079624402f30682753c1d43920b6664785698d21d3e7aa197450a6448b

Source-document review. Source text and stated dependencies were inspected for this profile. Referenced code was not comprehensively audited, no runtime test was performed, and source files are not mirrored here.

Report an error, license concern or request a new review.

Compare related design workflows

Design · Codex source

OpenAI Figma MCP Skill

Coordinates Figma design context and screenshots before implementing a selected frame in a codebase. The workflow asks the agent to translate the design into existing components and tokens instead of treating generated example code as the project’s final architecture.

Source checked 2026-10-20 · Not runtime tested

Design · Claude Code source

Anthropic Frontend Design Skill

Helps an agent choose a deliberate visual direction when building or reshaping a frontend. The instructions emphasize grounding typography, layout and styling in the real product brief, then reviewing the result for generic or mismatched choices.

Source checked 2026-10-20 · Not runtime tested

Design · Claude Code source

Anthropic Brand Guidelines Skill

Applies Anthropic-specific colors and typography to suitable artifacts. This is a concrete example of packaging one organization’s visual conventions, not a universal brand system for unrelated companies.

Source checked 2026-10-20 · Not runtime tested

Get listed

Put your AI tool in front of people who are already comparing options.

Submit a listing for editorial review. Include a live website, current pricing and a clear use case. We may request more information before publication.

Submit a tool