Tooluck logoTooluck
SKILL.md

image-creation

Agent skill fromyikart/AiToEarn

Generate or edit raster images for social posts, product shots, covers, mockups, and variants. Use when the user asks to create, edit, restyle, adapt, or redesign images based on provided images, or batch-generate bitmap images, or mentions posters, covers, product photos, illustrations, or reference-image generation.

How to install image-creation

install image-creation
# install the AiToEarn pack with the skills CLI
npx skills add yikart/AiToEarn

# or add only this skill to Claude Code: copy the folder

skills/claude-plugin-aitoearn/skills/image-creation/

# into

~/.claude/skills/image-creation/ (all projects)

.claude/skills/image-creation/ (one project)

skills/claude-plugin-aitoearn/skills/image-creation/SKILL.md

MITFull file
1# Image Creation
2
3Generate or edit raster images with `list_image_models` and `generate_image`.
4
5Shared prompt guidance: `references/prompting.md`.
6Copy/paste recipes: `references/sample-prompts.md`.
7
8## Tools
9
10- `list_image_models`: call first. Use only returned `name`, `sizes`, `qualities`, `styles`, `maxInputImages`, and pricing. Do not invent model ids or sizes.
11- `generate_image`: `prompt` required; `model` optional (omit to use the default `gpt-image-2.5-sunburst`); optional `images`, `size`, `quality`, `style`.
12 - Default model: `gpt-image-2.5-sunburst` when the catalog lists it; otherwise use another GPT Image 2.5 model or the closest available model.
13 - Default size when the user has no size preference (1080p class): 16:9 -> `1536x864`, 9:16 -> `864x1536`, 1:1 -> `1024x1024`; otherwise pick the catalog size matching the requested aspect.
14 - No `images` → new generation.
15 - One or more `images` (URLs) → reference/edit generation. Do not exceed `maxInputImages`.
16- Credit (积分) estimate runs automatically. If the user must confirm, wait. Do not retry a rejected cost.
17
18Do not call other image APIs, CLIs, or local scripts.
19
20## When to use
21
22- New image: concept, product shot, cover, poster, social asset, mockup
23- New image guided by reference images (style, composition, mood, subject)
24- Adapt or redesign an image or design the user provided (change format, layout, device framing, restyle) while keeping its content
25…

Excerpt shown under the repository's MIT license.

More skills in AiToEarn

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Leonxlnx /

taste-skill
113k

Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages

CCCXCU1 skill

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates