# Content Image

> Generate AI images for content using Gemini or other image generation APIs. Use when user needs diagrams, illustrations, or visual content.

- Skill: `isaac-flath/content-image` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add isaac-flath/content-image`
- Raw SKILL.md: https://api.skillmd.com/api/skills/isaac-flath/content-image/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: Isaac-Flath (https://skillmd.com/u/isaac-flath)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/isaac-flath/content-image

---


# /content-image

Generate AI images for content.

## Usage

```
/content-image [prompt]
```

## Prerequisites

- `uv` CLI: `brew install uv` or `pip install uv`
- `GEMINI_API_KEY` environment variable

## Run

```bash
# With explicit output path
uv run .claude/skills/content-image/scripts/generate_image.py "prompt" images/diagram.png

# Or use --project to save to project's images/ directory (auto-generates filename)
uv run .claude/skills/content-image/scripts/generate_image.py "prompt" --project .
```

## Output

Saves to `{project}/images/{descriptive-name}.png`

Insert in content: `![Description](images/filename.png)`

## Style Principles

See `.claude/skills/content-image/references/prompts/image-generation.md` for Tufte-style guidelines:
- Clean background, high data-ink ratio
- Minimal text, clear labels
- No decoration that doesn't add meaning

## Good Prompts

- "Flowchart showing [process]"
- "Diagram illustrating [concept]"
- "Architecture diagram for [system]"
- "Minimalist line drawing of..."

