K-Dense-AI / infographics

Skill Content

---
name: infographics
description: "Create professional infographics using Nano Banana Pro AI with smart iterative refinement. Uses Gemini 3 Pro for quality review. Integrates research-lookup and web search for accurate data. Supports 10 infographic types, 8 industry styles, and colorblind-safe palettes."
allowed-tools: Read Write Edit Bash
---

# Infographics

## Overview

Infographics are visual representations of information, data, or knowledge designed to present complex content quickly and clearly. **This skill uses Nano Banana Pro AI for infographic generation with Gemini 3 Pro quality review and Perplexity Sonar for research.**

**How it works:**
- (Optional) **Research phase**: Gather accurate facts and statistics using Perplexity Sonar
- Describe your infographic in natural language
- Nano Banana Pro generates publication-quality infographics automatically
- **Gemini 3 Pro reviews quality** against document-type thresholds
- **Smart iteration**: Only regenerates if quality is below threshold
- Professional-ready output in minutes
- No design skills required

**Quality Thresholds by Document Type:**
| Document Type | Threshold | Description |
|---------------|-----------|-------------|
| marketing | 8.5/10 | Marketing materials - must be compelling |
| report | 8.0/10 | Business reports - professional quality |
| presentation | 7.5/10 | Slides, talks - clear and engaging |
| social | 7.0/10 | Social media content |
| internal | 7.0/10 | Internal use |
| draft | 6.5/10 | Working drafts |
| default | 7.5/10 | General purpose |

**Simply describe what you want, and Nano Banana Pro creates it.**

## Quick Start

Generate any infographic by simply describing it:

```bash
# Generate a list infographic (default threshold 7.5/10)
python skills/infographics/scripts/generate_infographic.py \
  "5 benefits of regular exercise" \
  -o figures/exercise_benefits.png --type list

# Generate for marketing (highest threshold: 8.5/10)
python skills/infographics/scripts/generate_infographic.py \
  "Product features comparison" \
  -o figures/product_comparison.png --type comparison --doc-type marketing

# Generate with corporate style
python skills/infographics/scripts/generate_infographic.py \
  "Company milestones 2010-2025" \
  -o figures/timeline.png --type timeline --style corporate

# Generate with colorblind-safe palette
python skills/infographics/scripts/generate_infographic.py \
  "Heart disease statistics worldwide" \
  -o figures/health_stats.png --type statistical --palette wong

# Generate WITH RESEARCH for accurate, up-to-date data
python skills/infographics/scripts/generate_infographic.py \
  "Global AI market size and growth projections" \
  -o figures/ai_market.png --type statistical --research
```

**What happens behind the scenes:**
1. **(Optional) Research**: Perplexity Sonar gathers accurate facts, statistics, and data
2. **Generation 1**: Nano Banana Pro creates initial infographic following design best practices
3. **Review 1**: **Gemini 3 Pro** evaluates quality against document-type threshold
4. **Decision**: If quality >= threshold → **DONE** (no more iterations needed!)
5. **If below threshold**: Improved prompt based on critique, regenerate
6. **Repeat**: Until quality meets threshold OR max iterations reached

**Smart Iteration Benefits:**
- ✅ Saves API calls if first generation is good enough
- ✅ Higher quality standards for marketing materials
- ✅ Faster turnaround for drafts/internal use
- ✅ Appropriate quality for each use case

**Output**: Versioned images plus a detailed review log with quality scores, critiques, and early-stop information.

## When to Use This Skill

Use the **infographics** skill when:
- Presenting data or statistics in a visual format
- Creating timeline visualizations for project milestones or history
- Explaining processes, workflows, or step-by-step guides
- Comparing options, products, or concepts side-by-side
- Summarizing key points in an engaging visual format
- Creating geographic or map-based data visualizations
- Building hierarchical or organizational charts
- Designing social media content or marketing materials

**Use scientific-schematics instead for:**
- Technical flowcharts and circuit diagrams
- Biological pathways and molecular diagrams
- Neural network architecture diagrams
- CONSORT/PRISMA methodology diagrams

---

## Research Integration

### Automatic Data Gathering (`--research`)

When creating infographics that require accurate, up-to-date data, use the `--research` flag to automatically gather facts and statistics using **Perplexity Sonar Pro**.

```bash
# Research and generate statistical infographic
python skills/infographics/scripts/generate_infographic.py \
  "Global renewable energy adoption rates by country" \
  -o figures/renewable_energy.png --type statistical --research

# Research for timeline infographic
python skills/infographics/scripts/generate_infographic.py \
  "History of artificial intelligence breakthroughs" \
  -o figures/ai_history.png --type timeline --research

# Research for comparison infographic
python skills/infographics/scripts/generate_infographic.py \
  "Electric vehicles vs hydrogen vehicles comparison" \
  -o figures/ev_hydrogen.png --type comparison --research
```

### What Research Provides

The research phase automatically:

1. **Gathers Key Facts**: 5-8 relevant facts and statistics about the topic
2. **Provides Context**: Background information for accurate representation
3. **Finds Data Points**: Specific numbers, percentages, and dates
4. **Cites Sources**: Mentions major studies or sources
5. **Prioritizes Recency**: Focuses on 2023-2026 information

### When to Use Research

**Enable research (`--research`) for:**
- Statistical infographics requiring accurate numbers
- Market data, industry statistics, or trends
- Scientific or medical information
- Current events or recent developments
- Any topic where accuracy is critical

**Skip research for:**
- Simple conceptual infographics
- Internal process documentation
- Topics where you provide all the data in the prompt
- Speed-critical generation

### Research Output

When research is enabled, additional files are created:
- `{name}_research.json` - Raw research data and sources
- Research content is automatically incorporated into the infographic prompt

---

## Infographic Types

### 1. Statistical/Data-Driven (`--type statistical`)

Best for: Presenting numbers, percentages, survey results, and quantitative data.

**Key Elements:** Charts (bar, pie, line, donut), large numerical callouts, data comparisons, trend indicators.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "Global internet usage 2025: 5.5 billion users (68% of population), \
   Asia Pacific 53%, Europe 15%, Americas 20%, Africa 12%" \
  -o figures/internet_stats.png --type statistical --style technology
```

---

### 2. Timeline (`--type timeline`)

Best for: Historical events, project milestones, company history, evolution of concepts.

**Key Elements:** Chronological flow, date markers, event nodes, connecting lines.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "History of AI: 1950 Turing Test, 1956 Dartmouth Conference, \
   1997 Deep Blue, 2016 AlphaGo, 2022 ChatGPT" \
  -o figures/ai_history.png --type timeline --style technology
```

---

### 3. Process/How-To (`--type process`)

Best for: Step-by-step instructions, workflows, procedures, tutorials.

**Key Elements:** Numbered steps, directional arrows, action icons, clear flow.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "How to start a podcast: 1. Choose your niche, 2. Plan content, \
   3. Set up equipment, 4. Record episodes, 5. Publish and promote" \
  -o figures/podcast_process.png --type process --style marketing
```

---

### 4. Comparison (`--type comparison`)

Best for: Product comparisons, pros/cons, before/after, option evaluation.

**Key Elements:** Side-by-side layout, matching categories, check/cross indicators.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "Electric vs Gas Cars: Fuel cost (lower vs higher), \
   Maintenance (less vs more), Range (improving vs established)" \
  -o figures/ev_comparison.png --type comparison --style nature
```

---

### 5. List/Informational (`--type list`)

Best for: Tips, facts, key points, summaries, quick reference guides.

**Key Elements:** Numbered or bulleted points, icons, clear hierarchy.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "7 Habits of Highly Effective People: Be Proactive, \
   Begin with End in Mind, Put First Things First, Think Win-Win, \
   Seek First to Understand, Synergize, Sharpen the Saw" \
  -o figures/habits.png --type list --style corporate
```

---

### 6. Geographic (`--type geographic`)

Best for: Regional data, demographics, location-based statistics, global trends.

**Key Elements:** Map visualization, color coding, data overlays, legend.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "Renewable energy adoption by region: Iceland 100%, Norway 98%, \
   Germany 50%, USA 22%, India 20%" \
  -o figures/renewable_map.png --type geographic --style nature
```

---

### 7. Hierarchical/Pyramid (`--type hierarchical`)

Best for: Organizational structures, priority levels, importance ranking.

**Key Elements:** Pyramid or tree structure, distinct levels, size progression.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "Maslow's Hierarchy: Physiological, Safety, Love/Belonging, \
   Esteem, Self-Actualization" \
  -o figures/maslow.png --type hierarchical --style education
```

---

### 8. Anatomical/Visual Metaphor (`--type anatomical`)

Best for: Explaining complex systems using familiar visual metaphors.

**Key Elements:** Central metaphor image, labeled parts, connection lines.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "Business as a human body: Brain=Leadership, Heart=Culture, \
   Arms=Sales, Legs=Operations, Skeleton=Systems" \
  -o figures/business_body.png --type anatomical --style corporate
```

---

### 9. Resume/Professional (`--type resume`)

Best for: Personal branding, CVs, portfolio highlights, professional achievements.

**Key Elements:** Photo area, skills visualization, timeline, contact info.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "UX Designer resume: Skills - User Research 95%, Wireframing 90%, \
   Prototyping 85%. Experience - 2020-2022 Junior, 2022-2025 Senior" \
  -o figures/resume.png --type resume --style technology
```

---

### 10. Social Media (`--type social`)

Best for: Instagram, LinkedIn, Twitter/X posts, shareable graphics.

**Key Elements:** Bold headline, minimal text, maximum impact, vibrant colors.

```bash
python skills/infographics/scripts/generate_infographic.py \
  "Save Water, Save Life: 2.2 billion people lack safe drinking water. \
   Tips: shorter showers, fix leaks, full loads only" \
  -o figures/water_social.png --type social --style marketing
```

---

## Style Presets

### Industry Styles (`--style`)

| Style | Colors | Best For |
|-------|--------|----------|
| `corporate` | Navy, steel blue, gold | Business reports, finance |
| `healthcare` | Medical blue, cyan, light cyan | Medical, wellness |
| `technology` | Tech blue, slate, violet | Software, data, AI |
| `nature` | Forest green, mint, earth brown | Environmental, organic |
| `education` | Academic blue, light blue, coral | Learning, academic |
| `marketing` | Coral, teal, yellow | Social media, campaigns |
| `finance` | Navy, gold, green/red | Investment, banking |
| `nonprofit` | Warm orange, sage, sand | Social causes, charities |

```bash
# Corporate style
python skills/infographics/scripts/generate_infographic.py \
  "Q4 Results" -o q4.png --type statistical --style corporate

# Healthcare style
python skills/infographics/scripts/generate_infographic.py \
  "Patient Journey" -o journey.png --type process --style healthcare
```

---

## Colorblind-Safe Palettes

### Available Palettes (`--palette`)

| Palette | Colors | Description |
|---------|--------|-------------|
| `wong` | Orange, sky blue, green, blue, vermillion | Most widely recommended |
| `ibm` | Ultramarine, indigo, magenta, orange, gold | IBM's accessible palette |
| `tol` | 12-color extended palette | For many categories |

```bash
# Wong's colorblind-safe palette
python skills/infographics/scripts/generate_infographic.py \
  "Survey results by category" -o survey.png --type statistical --palette wong
```

---

## Smart Iterative Refinement

### How It Works

```
┌─────────────────────────────────────────────────────┐
│  1. Generate infographic with Nano Banana Pro       │
│                    ↓                                │
│  2. Review quality with Gemini 3 Pro                │
│                    ↓                                │
│  3. Score >= threshold?                             │
│       YES → DONE! (early stop)                      │
│       NO  → Improve prompt, go to step 1            │
│                    ↓                                │
│  4. Repeat until quality met OR max iterations      │
└─────────────────────────────────────────────────────┘
```

### Quality Review Criteria

Gemini 3 Pro evaluates each infographic on:

1. **Visual Hierarchy & Layout** (0-2 points)
   - Clear visual hierarchy
   - Logical reading flow
   - Balanced composition

2. **Typography & Readability** (0-2 points)
   - Readable text
   - Bold headlines
   - No overlapping

3. **Data Visualization** (0-2 points)
   - Prominent numbers
   - Clear charts/icons
   - Proper labels

4. **Color & Accessibility** (0-2 points)
   - Professional colors
   - Sufficient contrast
   - Colorblind-friendly

5. **Overall Impact** (0-2 points)
   - Professional appearance
   - Free of visual bugs
   - Achieves communication goal

### Review Log

Each generation produces a JSON review log:
```json
{
  "user_prompt": "5 benefits of exercise...",
  "infographic_type": "list",
  "style": "healthcare",
  "doc_type": "marketing",
  "quality_threshold": 8.5,
  "iterations": [
    {
      "iteration": 1,
      "image_path": "figures/exercise_v1.png",
      "score": 8.7,
      "needs_improvement": false,
      "critique": "SCORE: 8.7\nSTRENGTHS:..."
    }
  ],
  "final_score": 8.7,
  "early_stop": true,
  "early_stop_reason": "Quality score 8.7 meets threshold 8.5"
}
```

---

## Command-Line Reference

```bash
python skills/infographics/scripts/generate_infographic.py [OPTIONS] PROMPT

Arguments:
  PROMPT                    Description of the infographic content

Options:
  -o, --output PATH         Output file path (required)
  -t, --type TYPE           Infographic type preset
  -s, --style STYLE         Industry style preset
  -p, --palette PALETTE     Colorblind-safe palette
  -b, --background COLOR    Background color (default: white)
  --doc-type TYPE           Document type for quality threshold
  --iterations N            Maximum refinement iterations (default: 3)
  --api-key KEY             OpenRouter API key
  -v, --verbose             Verbose output
  --list-options            List all available options
```

### List All Options

```bash
python skills/infographics/scripts/generate_infographic.py --list-options
```

---

## Configuration

### API Key Setup

Set your OpenRouter API key:
```bash
export OPENROUTER_API_KEY='your_api_key_here'
```

Get an API key at: https://openrouter.ai/keys

---

## Prompt Engineering Tips

### Be Specific About Content

✓ **Good prompts** (specific, detailed):
```
"5 benefits of meditation: reduces stress, improves focus, 
better sleep, lower blood pressure, emotional balance"
```

✗ **Avoid vague prompts**:
```
"meditation infographic"
```

### Include Data Points

✓ **Good**:
```
"Market growth from $10B (2020) to $45B (2025), CAGR 35%"
```

✗ **Vague**:
```
"market is growing"
```

### Specify Visual Elements

✓ **Good**:
```
"Timeline showing 5 milestones with icons for each event"
```

---

## Reference Files

For detailed guidance, load these reference files:

- **`references/infographic_types.md`**: Extended templates for all 10+ types
- **`references/design_principles.md`**: Visual hierarchy, layout, typography
- **`references/color_palettes.md`**: Full palette specifications

---

## Troubleshooting

### Common Issues

**Problem**: Text in infographic is unreadable
- **Solution**: Reduce text content; use --type to specify layout type

**Problem**: Colors clash or are inaccessible
- **Solution**: Use `--palette wong` for colorblind-safe colors

**Problem**: Quality score too low
- **Solution**: Increase iterations with `--iterations 3`; use more specific prompt

**Problem**: Wrong infographic type generated
- **Solution**: Always specify `--type` flag for consistent results

---

## Integration with Other Skills

This skill works synergistically with:

- **scientific-schematics**: For technical diagrams and flowcharts
- **market-research-reports**: Infographics for business reports
- **scientific-slides**: Infographic elements for presentations
- **generate-image**: For non-infographic visual content

---

## Quick Reference Checklist

Before generating:
- [ ] Clear, specific content description
- [ ] Infographic type selected (`--type`)
- [ ] Style appropriate for audience (`--style`)
- [ ] Output path specified (`-o`)
- [ ] API key configured

After generating:
- [ ] Review the generated image
- [ ] Check the review log for scores
- [ ] Regenerate with more specific prompt if needed

---

Use this skill to create professional, accessible, and visually compelling infographics using the power of Nano Banana Pro AI with intelligent quality review.