
Article Illustrator
Plans and generates illustrations for an article using type, style, and palette choices.
- Repository
- JimLiu/baoyu-skills
- Stars
- 27,191
- Licence
- MIT
- Files
- 15 files
What it does
Once installed, the agent reads an article, finds the places where a picture would help, and proposes an illustration for each one. It uses a three-part system (illustration type, visual style, color palette) so the images look consistent together. It saves each image's prompt to a file, then asks you to confirm before generating the pictures through an image backend available in your tool, such as Codex imagegen, Cursor's image tool, or a separate image-generation skill.
Great for
- Bloggers or newsletter writers who want consistent illustrations for long articles
- Content teams producing several article images in one house style
- Users of Codex, Cursor, or Claude Code who already have an image generation tool set up
Skip it if
- Anyone needing exact text, charts, or data graphics inside images, since the skill forbids editing text on generated images and relies on regeneration, which may still be imperfect
- Users without any image generation backend installed, because the skill will stop and ask how to proceed rather than drawing vector or HTML substitutes
- Projects where an AI-generated image must not be used (for example, strict photo or licensing requirements), since the skill produces raster AI images
Try asking
- “Illustrate this article with a few images that fit its sections”
- “为文章配图 (add images to this article)”
- “Generate images for this blog post in a macaron palette with a blueprint style”
- “Suggest where illustrations would help in this draft, then wait for my approval before generating”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 15 original files, the MIT licence and an attribution note.
baoyu-article-illustrator.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip baoyu-article-illustrator.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip baoyu-article-illustrator.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 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
- Let the agent confirm the plan first; it is set to confirm before generating images, which controls cost and output.
- Pin a backend in your EXTEND.md preferences (preferred_image_backend) to avoid repeated backend prompts.
- Keep on-image text minimal in your request, since text in generated images is often imperfect.
What's inside
- prompts/system.md
- references/codex-imagegen.md
- references/config/first-time-setup.md
- references/config/preferences-schema.md
- references/palettes/macaron.md
- references/palettes/mono-ink.md
- references/palettes/neon.md
- references/palettes/warm.md
- references/prompt-construction.md
- references/style-presets.md
- references/styles.md
- references/styles/blueprint.md
- references/styles/chalkboard.md
- references/styles/editorial.md
- SKILL.md
Redistributed unmodified from JimLiu/baoyu-skills 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.