skills.rest
cocyuhao
cocyuhaoCOMMUNITY
Explore all skills by this author →
GitHub

article-batch-illustration

Generate per-paragraph illustration prompts and visuals from Markdown articles via Gemini API.

1|Updated May 12, 2026
Search Tags:#article-visuals#prompt-generation#gemini-api#obsidian-integration#batch-illustrations#markdown-images
One-click install
npx skills add https://github.com/cocyuhao/my-ai-skills-library --skill article-batch-illustration
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: article-batch-illustration
Source: https://github.com/cocyuhao/my-ai-skills-library/tree/main/article-batch-illustration
Command: npx skills add https://github.com/cocyuhao/my-ai-skills-library --skill article-batch-illustration

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill analyzes Markdown articles’ structure (by H2/H3 headings), generates per-paragraph illustration prompts, batch-creates visuals via Gemini API, and automatically inserts image references into the document, saving time for content creators.

Core Features & Use Cases

  • Phase 1: Structure analysis & prompt generation: split content by headings, extract core ideas, and produce global style instructions and per-paragraph prompts.
  • Phase 2: Image generation & insertion: batch-requests to Gemini, save images to Obsidian’s image directory, and insert ![[path]] links after each section heading.
  • Use Case: Ideal for blog posts, research notes, and educational articles requiring visual summaries and consistent visuals.

Quick Start

Open a Markdown article and trigger the batch illustration workflow to generate per-paragraph prompts, create images with Gemini, save them to Obsidian, and insert image references.

Frequently Asked Questions about article-batch-illustration

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I batch-generate illustrations for Markdown articles?▼

Batch-generate illustrations by parsing Markdown headings, extracting core ideas to form prompts, rendering visuals via Gemini API, and automatically inserting image links back into the article sections.

Can I automatically insert generated images into Obsidian folders?▼

Yes, generated visuals are saved directly to Obsidian’s image directory, and ![[path]] links are automatically inserted after section headings to integrate the images.

How does per-paragraph prompt generation work for article visuals?▼

It works by splitting article content by headings, extracting core ideas from each section, and producing global style instructions alongside specific prompts to render consistent visuals.

Does this batch illustration workflow require any external dependencies?▼

No external Skill dependencies are required, but the workflow relies on the Gemini API for image rendering and an Obsidian environment for saving media and inserting Markdown links.

What is the best way to add visual summaries to research notes?▼

The best way is to use a batch illustration workflow that parses document structure, generates section-specific prompts, and renders consistent visuals via the Gemini API for educational content.

When should I use automated image generation for blog posts?▼

Use automated image generation when you need end-to-end visualization for blog posts, requiring consistent styling across sections and automatic media insertion without manual prompt crafting.

Related Skills

Explore More Content & Communication Skills→
hulusi-tunchulusi-tunc
3

heading-structure

Enforce single H1 and nested H2/H3 headings for screen reader navigation.

Community
Intermediate
builtby-winbuiltby-win

manage-blog

Scan a configured directory for markdown blog posts and manage drafts.

Official
Intermediate
SpaceZephyrSpaceZephyr
333

image-skill-builder

Create a custom batch image generation skill from interactive user requirements.

Community
Advanced
GeeveGeorgeGeeveGeorge
9

openNanoBanana

Search and verify web images to ground AI image generation in real-world visuals.

Community
Intermediate