LIVE
CliffCompaction: A Context-Compaction Method to Cut Costs of Coding Agents22/09/26|FleXray: A Generalist Model for Whole-Body X-ray Segmentation22/09/26|Anthropic unveils Claude Opus 5.522/09/26 · Anthropic|Court filings reveal internal admissions on AI content scraping19/09/26|US Military Avoids Close Call After AI-Generated Intelligence Hallucination18/09/26|Study finds gender bias in GPT models is not reduced but reshaped across generations17/09/26 · OpenAI|Google DeepMind adds secure server-side memory to Private AI Compute23/09/26 · Google DeepMind|Google DeepMind adds text-to-speech to Gemini 3.823/09/26 · Google DeepMind|NVIDIA releases Nemotron 3 Diarization for real-time speaker identification23/09/26 · NVIDIA|OpenAI extends its Daybreak cyber program to Ukraine for civilian defense23/09/26 · OpenAI|OpenAI enlists influencers to burnish its public image23/09/26 · OpenAI|Claude Code Reportedly Reads AGENTS.md Only When Telemetry Is Enabled23/09/26 · Anthropic|CliffCompaction: A Context-Compaction Method to Cut Costs of Coding Agents22/09/26|FleXray: A Generalist Model for Whole-Body X-ray Segmentation22/09/26|Anthropic unveils Claude Opus 5.522/09/26 · Anthropic|Court filings reveal internal admissions on AI content scraping19/09/26|US Military Avoids Close Call After AI-Generated Intelligence Hallucination18/09/26|Study finds gender bias in GPT models is not reduced but reshaped across generations17/09/26 · OpenAI|Google DeepMind adds secure server-side memory to Private AI Compute23/09/26 · Google DeepMind|Google DeepMind adds text-to-speech to Gemini 3.823/09/26 · Google DeepMind|NVIDIA releases Nemotron 3 Diarization for real-time speaker identification23/09/26 · NVIDIA|OpenAI extends its Daybreak cyber program to Ukraine for civilian defense23/09/26 · OpenAI|OpenAI enlists influencers to burnish its public image23/09/26 · OpenAI|Claude Code Reportedly Reads AGENTS.md Only When Telemetry Is Enabled23/09/26 · Anthropic|
SkillNewofficial publisher

canvas-design (Anthropic)

Skill : A reusable method: instructions, procedures, sometimes scripts or templates · requires claude-code

Official skill that makes Claude produce polished static visuals (posters, visuals, compositions) in PNG or PDF.

Useful for simple, clean visuals without a design tool; not a replacement for Figma or an image generator.

Overall score
8.2 /10
Security: nothing to flag
Utility
6.0
Reliability
10.0
Security
No caveat on record
Ease
1 click · Beginner

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Creating a polished visual without design software often requires time and technical skills. canvas-design is an official Anthropic skill that enables Claude to produce static graphic compositions, such as posters or presentation visuals, directly as PNG or PDF files.

In practice, the skill loads a set of embedded instructions and fonts that Claude uses to generate the requested image or PDF file. It only writes the produced files and does not touch anything else on the machine. The user describes what they want, and Claude applies the skill's rules to deliver a consistent result.

This skill is aimed at people who need simple, clean visuals without going through a dedicated design tool: an event poster, an internal communication visual, a quick composition. It is available on Claude.ai for paid plans, and in Claude Code via the plugin marketplace.

It is not suited for those looking for an AI image generator, a collaborative design tool like Figma, or complex compositions with many layers and interactions. Results are static and limited to what Claude can produce from text instructions.

What it offers

  • ·Generation of static visuals (posters, graphic compositions) in PNG or PDF from a text description. (paid)
  • ·Fonts embedded in the skill to ensure consistent rendering without external dependencies.
  • ·Design instructions dynamically loaded by Claude when the skill is used.
  • ·Writing limited to the produced image or PDF files only, without modifying other files.
  • ·Installation via the Claude Code plugin marketplace with a dedicated command.
  • ·Available directly on Claude.ai for users on paid plans, with no additional configuration. (paid)
  • ·Also usable via the Claude API for developers who want to integrate visual generation into their own workflows.

In practice

Price
Free
Commercial use
Commercial use: yes
Available on
GitHub anthropics/skills, Claude.ai
Host
claude-code
Licence
Apache-2.0
FR interface
No

Security and data

Rating
Security: nothing to flag
Your data
Data stays local
Maintenance
Active

Links and repository checked on 23 September 2026 · added on 23 September 2026

How to install canvas-design (Anthropic)

1. Open Claude Code in your terminal. 2. Register the Anthropic marketplace: /plugin marketplace add anthropics/skills 3. Install the skill: /plugin install example-skills@anthropic-agent-skills 4. In your conversation, explicitly mention canvas-design to activate the skill. 5. On Claude.ai (paid plan), the skill is already available without installation: follow the instructions on the "Using skills in Claude" help page.
/plugin install example-skills@anthropic-agent-skills

Official documentation

In the same category

Whole category Design & slides