Art Skill

Contents: Ideal State · Intent Routing · Safety gates · Tool contract · Data & Config · Gotchas · Examples

Generates static visual content across 20+ formats — blog headers, technical and architecture diagrams, frameworks, taxonomies, timelines, comparisons, stat cards, comics, icons, wallpapers, D3 charts, Mermaid diagrams — using Flux and Nano Banana Pro (Gemini 3 Pro). Every request routes through a named intent that encodes the technique and palette, then calls Generate.ts with --intent=<name> plus model/size/output flags, and Generate.ts itself enforces that the intent was followed. Output defaults to $LIFEOS_DOWNLOADS_DIR (default ~/Downloads/ when unset) unless --output names another path, so every intent passes --output into a working directory outside Downloads (§ Output staging). Blog headers run with --thumbnail to ship both a transparent inline PNG and an opaque listing thumbnail on the page ground (ArtConfig.json thumbnailGround); the site builds its social card separately (References/BlogHeaders.md).

Ideal State

Every image comes from the intent that matches the request, and its composition is reasoned from the specific argument or content it illustrates: scene concepts weighed against each other, every element in the frame carrying a narrative role, never a subject list dropped into a prompt.
Every image holds its intent's technique and palette, or the style PREFERENCES.md sets, unless the principal names another style, and every person in it follows the figure treatment described in Gotchas.
Every label, number, value and arrow in a diagram, stat card or annotated image is factually correct and spelled exactly as the source has it; one misspelled word, garbled digit or wrong hex value fails the image however good the art is. When the request asks for an image rendered from authored SVG, the delivered file comes from that SVG, never from an image model.
An edit of an existing photo or reference image changes only what the request names: the subject's identity, and every element the request did not mention, read the same in the output as in the source.
A set of images made for one deck or page reads as one set: the same medium, palette, ground and figure style as the style references the request names.
Every image is rendered in a working directory outside Downloads (or the staging directory its intent names), passes the ArtDirection quality loop there, and reaches Downloads only through ArtDirection's Deliver.ts; nothing is copied into a project before that hand-off, except where an intent wires its own winner in without handing back.
A finished file is verified, not assumed: it was looked at with the Read tool in this turn, file reports real RGBA where transparency was the point, its native dimensions fit the destination, and a blog header ships both the transparent inline image and the opaque -thumb.png and carries the signature stamp the Essay intent applies.
A one-of-a-kind generation survives any background cut: its raw stays on disk until the cut PNG has been read and every subject in it confirmed present.