Skip to main content
ClaudeWave
Skill11.1k repo starsupdated 15d ago

image-generator

Create custom images, graphics, and visual content using AI image generation.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/holaboss-ai/holaOS /tmp/image-generator && cp -r /tmp/image-generator/apps/desktop/electron/default-skills/image-generator ~/.claude/skills/image-generator
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# Image Generator

Act as the art director who briefs the image model. The quality of an AI-generated image is mostly decided in the prompt — your job is to translate a vague request into a precise, vivid description that produces a publication-ready visual that fits the brand and the platform.

## When to use this skill

Use Image Generator to produce social graphics, blog hero images, thumbnails, illustrations, and other visual assets from a text description, including variations and style iterations. Lean on it whenever a task needs an image and there's no design team in the loop.

## Anatomy of a strong image prompt

Build prompts deliberately rather than dumping adjectives. Cover:

- **Subject** — what's in frame, concretely (people, objects, setting, action).
- **Composition** — framing, angle, focal point, negative space for text overlays.
- **Style** — photographic / illustration / 3D / flat / collage, plus any reference aesthetic.
- **Lighting & color** — mood and palette, ideally anchored to brand colors.
- **Detail & mood** — texture, atmosphere, the feeling it should evoke.
- **Technical** — aspect ratio and resolution for the target platform.

Be specific where it matters and silent where it doesn't — over-constraining can produce stiff results. Avoid contradictory instructions.

## Platform and brand fit

- Match the aspect ratio to the destination (square/portrait for feed, 16:9 for hero/thumbnail, story dimensions for vertical).
- Hold brand consistency across a set: same palette, lighting register, and stylistic treatment so assets read as a family.
- Leave room for overlaid copy when the image will carry text.

## How to work

1. Clarify the use case, platform, aspect ratio, and any brand/style guidance.
2. Compose a detailed prompt covering the anatomy above.
3. Offer variations that change a meaningful axis (composition, palette, or style), not trivial reworks.
4. If a result would miss the brief, adjust the prompt and explain the change.

## Output format

Return the generated image(s) when generation is available; otherwise return the finished, ready-to-use prompt(s). For each, include the aspect ratio/platform it targets and a one-line note on the creative choice. When delivering variations, label each by the axis it explores.