Overview
Posters and graphic layouts as crafted objects with a thesis: write a short visual philosophy first — name the direction in two words, 'Brutalist Joy', 'Chromatic Silence' — saying how it lives in space, color, scale and composition; then deduce the quiet conceptual thread from your brief and compose one canvas at ninety percent visual, ten percent essential text.
The artifact is generated from a layout spec, using the fonts' real measurements to block the two classic disasters — content running off the page and text colliding — with coverage checks for Chinese and Japanese glyphs. Measurements catch blunders, not every optical edge case, so a human look is the final step. Fonts come bundled; nothing external is downloaded.
SVG and web pages are the source files; a full-size image or PDF is produced by rendering through the app for real, never promised from an unrendered file.
Where it helps
- Compose an event poster carrying a subtle conceptual thread
- Build a consistent masthead system for a report or column
- Produce mixed Chinese/Latin visual material with glyph coverage checked
- Derive a full palette and composition from a one-line style prompt
#design#poster#layout#export#fonts
Examples
Examples describe the request and the shape of the expected deliverable; they are not completed run results.
01Example prompt
Tone-set a poster for a jazz book club: write a Concrete-Poetry-style philosophy, hide a Bill Evans tune title in the composition, then output the poster layout and SVG.
Expected output
A philosophy file, a layout carrying the quiet reference and the generated SVG — off-page and overlap faults caught at generation.
02Example prompt
I need this poster as a full-size PNG: render it in the app and capture the real image — don't claim the source file exports raster by itself.
Expected output
A capture-backed image with its provenance stated; formats that were never rendered don't appear in the delivery.
Requirements and limits
- Install platforms
- iOS
- Script runtime
- Runs scripts in the task environment
- Minimum app version
- 1.7.62
Reviewed permission scope
- Capabilities
- Interact with web pagesObserve web pagesRemote executionRead workspace filesWrite workspace files
- Reviewed tools
- browser.click · browser.exportFile · browser.navigate · browser.observe · browser.screenshot · exec.localService · Shell commands · jobs.cancel · jobs.result · jobs.status · jobs.submit · workspace.publishOutput
- Review decision
- Approved
- Review stage
- Guest execution qualification
- Reviewed on
- 2026-10-27
Implementation and runtime details
- Adaptation stage
- frozen
- Tools
- browser.click · browser.exportFile · browser.navigate · browser.observe · browser.screenshot · exec.localService · Shell commands · jobs.cancel · jobs.result · jobs.status · jobs.submit · workspace.publishOutput
- Capabilities
- Interact with web pagesObserve web pagesRemote executionRead workspace filesWrite workspace files
- Runtime environment
- linux / riscv64 · guest-verified
License and source
Source and trace details
License
Apache-2.0
Apache-2.0 (per-skill LICENSE.txt)
Pinned per-skill Apache-2.0 license preserved; Floe renderer code is separately identified as MPL-2.0. Bundled font faces, where present, retain their full SIL OFL notices and exact hashes.
- Source
- https://github.com/anthropics/skills
- Upstream path
- skills/canvas-design
- Source checked
- 2026-10-26
- Publisher
- JiangNanGenius
- Publication commit (retrieval)
- 25e07dbeeb6cc93c2fe83ddc72a34302cc40832a
- Audited source commit
- 84c524b6fb483e4cad94db076e7d9c9962966c19
- Signed catalog digest
- iOS 46196ba57ed7ea7f22085e74b113207f31193e820ab8983cf7a60eee953f2340 · Android 16de89d019e2057804a40f215485ccb09d5495a25864b34d681168eeaf8f9697
- Publication snapshot (UTC)
- 2026-10-31
Publication commit 25e07dbeeb, audited source 84c524b6fb; catalog digest iOS 46196ba57ed7… · Android 16de89d019e2….
Versions and status
Version records ship with the signed catalog; the target and released versions are shown below.
- Adaptation
- Ready
- Publication state
- Curated skills are available
- Deep adaptation
- Yes
- Released version
- iOS 1.1.0