ACOS Visual Generator
Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.
Best use case
ACOS Visual Generator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.
Teams using ACOS Visual Generator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/acos-visual-gen/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ACOS Visual Generator Compares
| Feature / Agent | ACOS Visual Generator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# ACOS Visual Generator
## What This Skill Does
Creates research-grounded images by:
1. Researching the topic via web search
2. Extracting key facts for accuracy
3. Constructing a detailed image prompt
4. Generating via Nano Banana MCP (Gemini 2.5 Flash Image)
## Prerequisites
- Nano Banana MCP server configured
- WebSearch tool available
## Quick Start
```
User: "Create a 3D infographic about quantum computing"
Process:
1. WebSearch → Extract key facts
2. Construct prompt with style instructions
3. mcp__nanobanana__generate_image()
4. Return image with sources
```
---
## Visual Styles
| Style | Description |
|-------|-------------|
| `standard` | Clean scientific illustration, modern, professional |
| `minimalist` | Bauhaus, flat vector, 2-3 colors, negative space |
| `photorealistic` | Cinematic lighting, 8K, detailed textures |
| `3d` | Isometric render, claymorphism, studio lighting |
| `technical` | Da Vinci notebook, ink sketch, annotations |
| `futuristic` | Cyberpunk HUD, neon, holographic |
| `vintage` | 19th century lithograph, sepia, engraving |
| `cartoon` | Educational comic, vibrant, cel-shaded |
## Audience Levels
| Level | Target |
|-------|--------|
| `elementary` | Ages 6-10, bright, simple, fun icons |
| `highschool` | Standard textbook, clean, accurate |
| `college` | Academic journal, high detail, data-rich |
| `expert` | Technical schematic, extremely dense |
---
## Step-by-Step Process
### Step 1: Research
```javascript
WebSearch("{topic} facts key information 2026")
```
Extract 3-5 verifiable facts.
### Step 2: Construct Prompt
```
Create a {aspect_ratio} {style_description} infographic about {topic}.
VISUAL STYLE: {style_instruction}
AUDIENCE: {audience_instruction}
INCLUDE:
- {fact_1_visualized}
- {fact_2_visualized}
- {fact_3_visualized}
COMPOSITION:
- Clear layout with visual hierarchy
- Text should be large and legible
- Include labels and annotations
```
### Step 3: Generate
```javascript
mcp__nanobanana__generate_image({
prompt: "{constructed_prompt}",
aspect_ratio: "16:9",
model_tier: "pro",
enable_grounding: true,
thinking_level: "high",
resolution: "high"
})
```
### Step 4: Present Results
Return:
- Generated image
- Research sources
- Key facts included
- Modification options
---
## Style Instructions (Copy These)
**Standard:**
```
High-quality digital scientific illustration. Clean, modern, highly detailed. Professional color palette.
```
**3D Isometric:**
```
3D Isometric Render. Claymorphism or high-gloss plastic texture, studio lighting, soft shadows, looks like a physical model.
```
**Technical:**
```
Da Vinci Notebook style. Ink on parchment sketch, handwritten annotation style, rough but accurate lines, technical precision.
```
**Futuristic:**
```
Cyberpunk HUD. Glowing neon blue/cyan lines on dark background, holographic data visualization, 3D wireframes.
```
---
## Example Usage
**User:** "Visualize how neural networks learn"
**Research:** WebSearch finds key facts about backpropagation, gradient descent, layers, activation functions.
**Prompt:**
```
Create a 16:9 3D isometric infographic about how neural networks learn.
VISUAL STYLE: 3D Isometric Render with claymorphism aesthetic...
INCLUDE:
- Input layer receiving data
- Hidden layers processing with weights
- Backpropagation arrows showing error correction
- Output layer with predictions
```
**Generate:** Call Nano Banana MCP with grounding enabled.
---
## Integration
This skill integrates with:
- `/infogenius` command in ACOS
- Nano Banana MCP for image generation
- WebSearch for factual grounding
---
*Part of the Agentic Creator OS visual generation pipeline.*Related Skills
adr-generator
Specialized skill for generating and managing Architecture Decision Records (ADRs). Supports Nygard, MADR, and custom templates with auto-numbering, linking, and status management.
open-eth-terminal-action-generator
An agent that can help users with creating new actions to check into the codebase. It should generate action code and link it to the application after querying the user for information about the goal of the action.
academic-homepage-generator
When the user requests to create or customize an academic personal website from a GitHub template repository. This skill handles the complete workflow of forking academic template repositories (like academicpages.github.io), extracting structured personal information from memory or provided data, and systematically updating configuration files (_config.yml), navigation menus (_data/navigation.yml), content pages (_pages/about.md), and publication listings (_publications/). It specifically handles academic profiles including personal details, education background, research experience, publications, skills, and contact information. Triggers include requests to 'fork and customize academic homepage', 'build personal academic website', 'create research portfolio', or 'set up GitHub pages with academic template'.
ability-generator
Generates a structured skill template based on provided specifications.
a11y-annotation-generator
Adds accessibility annotations (ARIA labels, roles, alt text) to make web content accessible. Use when user asks to "add accessibility", "make accessible", "add aria labels", "wcag compliance", or "screen reader support".
web-asset-generator
Generate web assets including favicons, app icons (PWA), and social media meta images (Open Graph) for Facebook, Twitter, WhatsApp, and LinkedIn. Use when users need icons, favicons, social sharing images, or Open Graph images from logos or text slogans. Handles image resizing, text-to-image generation, and provides proper HTML meta tags.
3d-visualizer
Expert in Three.js, 3D graphics, and interactive 3D visualizations
2000s-visualization-expert
Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.
changelog-generator
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
adb-skill-generator
Meta-tool for rapid adb-* skill creation from templates
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.