Claude skills for Visual
7 skills in the bank are filed under Visual. They are grouped here because they compete for the same jobs — which is the reason an agent reaching for one of them sometimes gets another.
- Algorithmic Artanthropics/skillsArt that is generated rather than drawn: flow fields, particle systems, seeded randomness you can re-roll and tune. Code is the medium.
- Brand Guidelinesanthropics/skillsApplies Anthropic's own brand colours and type to an artifact. Only right when the thing genuinely should look like Anthropic made it.
- Canvas Designanthropics/skillsStill visual art delivered as a .png or print-ready .pdf: a poster, a flyer, a one-page piece meant to be looked at rather than clicked.
- Frontend Designanthropics/skillsDeciding how a UI should look and feel before you build it: typography, colour, hierarchy, and escaping the default templated appearance.
- Slack GIF Creatoranthropics/skillsAnimated GIFs built to survive Slack's size and dimension limits. For when someone says make me a GIF of X doing Y.
- Theme Factoryanthropics/skillsPut a consistent look on something already built: pick or generate a colour-and-font theme and apply it across slides, docs, or a page.
- Web Artifacts Builderanthropics/skillsAmbitious claude.ai artifacts with many moving parts: React, Tailwind, component libraries, real state and routing rather than a single static page.
The Visual pairs people mix up
Side-by-side, with a worked situation for each side.
- Algorithmic Art vs Canvas Design
- Algorithmic Art vs Frontend Design
- Algorithmic Art vs Theme Factory
- Algorithmic Art vs Web Artifacts Builder
- Canvas Design vs Frontend Design
- Canvas Design vs Theme Factory
- Canvas Design vs Web Artifacts Builder
- Frontend Design vs Theme Factory
- Frontend Design vs Web Artifacts Builder
- Theme Factory vs Web Artifacts Builder
Knowing the Visual list is the easy half. Picking from it under time pressure is the game.
Today's session