Skip to content
Get packs

Art Image and Diagram Generator

Creates diagrams, infographics, comics, icons and wallpapers by routing requests to image-model intents.

Source Download skill
Repository
danielmiessler/LifeOS
Stars
19,682
Licence
MIT
Files
15 files

What it does

When installed, the agent answers requests for visual content such as blog header images, technical diagrams, frameworks, comparisons, comics, icons and wallpapers by following a specific named intent. Each intent encodes a technique and palette, then calls a bundled Generate.ts script that uses image models (Nano Banana Pro, Nano Banana or Flux) and checks that the intent was followed. Some diagrams can also be animated into looping GIFs.

Great for

  • Bloggers who need consistent header images and essay illustrations
  • People making technical or architecture diagrams that should look polished
  • Designers building a set of images with a shared style and palette

Skip it if

  • Requests to visualize data or concepts generically, which the skill says belong to a different Visualize skill (routing depends on that skill being present)
  • YouTube or video thumbnails and web UI design, which are handled by other skills; these requests may produce off-target output
  • Work where you cannot send prompts and images to external image-model services, since generation calls a network API

Try asking

  • “Make a blog header image for my essay on habit formation, with a transparent inline version and a thumbnail”
  • “Create a framework 2x2 diagram comparing remote and in-office work trade-offs”
  • “Turn this architecture diagram into an animated GIF for my docs”
  • “Design a square recipe card showing five steps for making sourdough”
Step-by-step guide: how to use Art Image and Diagram GeneratorInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    Art.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip Art.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip Art.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Name the intent or describe the content precisely so the right intent is chosen, and check the output text carefully since labels and numbers can be misspelled by image models
  • Review generated images with the agent's file viewer before using them, because the skill itself notes that verification is required
  • Keep sensitive or unpublished material out of prompts, since image requests are sent to external model providers

What's inside

  • Intents/AnimatedEssay.md
  • Intents/AnnotatedScreenshots.md
  • Intents/Aphorisms.md
  • Intents/Comics.md
  • Intents/Comparisons.md
  • Intents/D3Dashboards.md
  • Intents/EmbossedLogoWallpaper.md
  • Intents/Essay.md
  • Intents/Frameworks.md
  • Intents/LifeOSHero.md
  • Intents/LogoWallpaper.md
  • Intents/Maps.md
  • Intents/Mermaid.md
  • Intents/RecipeCards.md
  • SKILL.md

Redistributed unmodified from danielmiessler/LifeOS under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.