Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nexu-io/canvas-design
Create beautiful visual art in PNG and PDF documents using design philosophy and aesthetic principles for posters, illustrations, and static pieces.
Passed 4 of 21 test cases with the skill, and 2 of 21 without it.
and 2 more in the full report
4 fixed1 passed either way19 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Create a poster for a modern architecture exhibition titled "Concrete & Light". I am tempted to just put bright yellow text on a white background with no margins or grid. How should this poster be designed and delivered as static artwork in PDF and PNG?
| Checked | Without skill | With skill |
|---|---|---|
| recommends high-contrast typography on a visual grid layout | Passed | Passed |
| provides output poster artwork in PDF and PNG document formats | Missed | Passed |
The instructions your model reads when the skill loads.
Curated from Anthropic's official skills repository.
Create beautiful visual art in PNG and PDF documents using design philosophy and aesthetic principles for posters, illustrations, and static pieces.
image-generationThis catalogue entry advertises the skill in OpenDesign so the agent discovers it during planning. To run the full upstream workflow with its original assets, scripts, and references, install the upstream bundle into your active agent's skills directory:
# Inspect the upstream README for exact paths
open https://github.com/anthropics/skills/tree/main/skills/canvas-design
Then ask the agent to invoke this skill by name (canvas-design) or with
one of the trigger phrases listed in this skill's frontmatter.
test cases passed, vs 2 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.