baoyu-article-illustrator skill: have Claude illustrate your article

Makes Claude find where an article needs visuals, generate illustrations in one style and insert them.

Installs: 32.1K; on skills.sh
Stars: 27.2K; on GitHub
Files: 36; besides SKILL.md
Updated: Nov 2026; last repo commit

baoyu-article-illustrator is a skill from Baoyu's skills repo. Claude reads your article, picks the places where a picture helps, and builds an outline. You confirm a type, style, palette and how many images, then Claude saves a prompt per image, generates them and inserts the image links into the article.

The skill does not draw by itself. It needs an image backend, such as baoyu-image-gen with a provider key in Claude Code. Generation uses your provider credits, and the last step edits your article file.

Good for

Bloggers and technical writers adding diagrams and scenes to long posts
Content teams who want one consistent visual style across a series
WeChat and newsletter authors who illustrate every section

Install baoyu-article-illustrator

Claude Code

Copy this prompt.

Install the baoyu-article-illustrator skill in Claude Code. Run this command:

npx skills add jimliu/baoyu-skills --skill baoyu-article-illustrator --skill baoyu-image-gen

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js, An image provider API key.

baoyu-article-illustrator does not draw images itself. It hands the saved prompt to an image backend, and the SKILL.md names baoyu-image-gen as an example backend, so the command also installs it from the same repo. The README lists more providers (Azure OpenAI, Z.AI, MiniMax, Seedream, Replicate and others). If the Codex CLI is installed and logged in, baoyu-image-gen can use it instead of a key. The README advises installing only the skills you need.

From the vendor's docs. Source.

What's in the skill

When it loads

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".

Sections in SKILL.md

User Input Tools
Image Generation Tools
Batch Generation Policy
Confirmation Policy
Reference Images
Three Dimensions
Types
Styles
Workflow
Step 1: Pre-check
Step 2: Analyze
Step 3: Confirm Settings ⚠️
Step 4: Generate Outline
Illustration 1
Step 5: Generate Images
Step 6: Finalize

Key facts

Author: jimliu (Baoyu)
Repo: jimliu/baoyu-skills
Installs on skills.sh: 32,128 as of Nov 2, 2026
GitHub stars: 27,159 for the whole jimliu/baoyu-skills repo, Nov 2, 2026
License: MIT
Last repo commit: Nov 1, 2026
What is inside: 37 files including SKILL.md: style and palette guides, a long workflow and prompt guide, and setup notes
skills.sh audits: Gen Agent Trust Hub warn, Socket pass, Snyk pass
Makes: Several illustrations for one article, inserted at the right paragraphs
Choices: Type (6), style and optional palette, density from minimal to rich, or a preset
Needs: An image backend: baoyu-image-gen with a provider key, Codex's imagegen, or Cursor's GenerateImage
Output folder: imgs/ next to the article by default, with outline.md and prompts/

What it includes

Loads EXTEND.md, saves reference images, picks the output folder
First run asks preference questions and saves EXTEND.md.
Try: “Illustrate article.md.”
Write · Pre-check
Finds content type, purpose, 2 to 5 core arguments and where visuals help
Metaphors become the underlying concept, not a literal picture.
Analyze
A hard gate: preset or type, density, style, palette and language
Density options: minimal (1 to 2), balanced (3 to 5), per-section (recommended), rich (6+).
Confirm settings
Saves outline.md listing each illustration's position, purpose and filename
Generate the outline
Saves one prompt file per image, then generates in batches of 4 by default
Prompts must be saved first. Failed items are retried once.
Runs code · Generate images
Inserts ![description](path) after the matching paragraphs in your article
This edits your article file.
Write · Finalize
infographic, scene, flowchart, comparison, framework, timeline
Types
Styles such as notion, blueprint and watercolor; palettes macaron, warm, neon
Styles and palettes
--preset gives a type, style and palette in one flag
For example --preset edu-visual.
Presets
Edit, add or delete one illustration and update the outline and article
Existing outputs are renamed to a backup before regenerating.
Modification
imgs-subdir (default), same-dir, illustrations-subdir or independent
Pasted text always goes to illustrations/<topic-slug>/.
Output folder options

From the official docs

Permissions

Medium risk

Claude sends your article to an image provider and spends its credits, writes images into your project and edits your article to link them. Work under version control.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Image generation uses your provider credits
Each image is a paid call on the provider whose key you set. Check the confirmed options before approving, since regenerating text fixes means new calls. github.com
Your content is sent to the image provider
The prompt includes your source text and any reference images you pass. Do not feed it private material you cannot share with that provider. github.com
It edits your article
The final step inserts image links after paragraphs in the file you gave it. Keep the article under version control so you can review the diff. github.com
It writes files and renames old ones
It saves outputs in a new folder and renames an existing prompt or image file to a -backup-timestamp name before regenerating. Check the output folder before you commit. github.com
It runs backend scripts through bun
baoyu-image-gen runs TypeScript scripts with bun, or fetches bun with npx -y bun. Read the first command Claude proposes. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	SKILL.md defines no read-only mode. It confirms type, density, style, palette and language with you before generating, unless you explicitly skip confirmation.
Talks to	The image provider you pick, through baoyu-image-gen: your prompt and any reference images. Package downloads if bun is fetched with npx -y bun
Sign-in and keys	Provider API keys live in .env files you create: ~/.baoyu-skills/.env or .baoyu-skills/.env in the project. The README says not to commit them.
Scopes	Claude saves source copies, analysis, prompt files and the image in your project Claude inserts image links into your article file Claude runs the image backend's scripts with bun, or npx -y bun if bun is missing A first run asks preference questions and saves an EXTEND.md file

Questions

What does baoyu-article-illustrator do?

It makes Claude read an article, decide where illustrations help, and generate them in a consistent type, style and palette. It then inserts the image links into the article.

How do I install baoyu-article-illustrator?

Use the install box at the top of this page. In Claude Code it installs baoyu-image-gen with it, because the skill needs an image backend to make the picture. You also need one image provider API key. In Codex the skill uses Codex's own image tool.

Does baoyu-article-illustrator need an API key?

In Claude Code, yes. SKILL.md names native image tools only for Codex (imagegen) and Cursor (GenerateImage), so in Claude Code the skill uses baoyu-image-gen, which calls an image provider with a key you put in a .env file. It can also use a logged-in Codex CLI. In Codex or Cursor the skill uses the app's own image tool.

Will it change my article file?

Yes. The last step inserts image links after the matching paragraphs. Existing images and files are renamed with a backup suffix before they are replaced, but keep the article under version control.

Does it ask before generating?

Yes. By default it confirms the options with you first. It skips that only when you say so explicitly, for example with a no-confirm or quick option.

What if the text in the image is wrong?

It regenerates from a corrected prompt in a new file and keeps the flawed one for comparison. The skill forbids painting over or editing the text in a generated image with code.

Does it work in the Claude app?

No documented route. It needs scripts and an image backend on your machine, so the install box has no Claude app tab. Use Claude Code or Codex.

Is baoyu-article-illustrator safe?

It sends your article text and reference images to an image provider you choose, spends that provider's credits, edits your article to insert image links and writes files in your project. Work on a copy under version control and confirm the settings.

Information

updated Nov 2, 2026

Repository: jimliu/baoyu-skills
Folder: skills/baoyu-article-illustrator

jimliu/baoyu-skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 6

baoyu-skills README · github.com
skills CLI commands · github.com
baoyu-image-gen SKILL.md · github.com
baoyu-article-illustrator SKILL.md · github.com
workflow.md · github.com
skills.sh listing · skills.sh