image-gen · dotslashsimran — Claude Code skill for image generation and setup
The image-gen Claude Code skill generates and edits images from requests. It activates for illustrations, icons, thumbnails, textures, and image series that need a consistent subject.
MIT ★ 541 updated 2026-11-09
npx skills add dotslashsimran/simcraft --skill image-gen -a claude-codeWhat image-gen does
The skill runs a Python script that sends prompts to Gemini or OpenAI and saves each image with a JSON file containing its settings. Options cover aspect ratio, reference images, provider selection, and multiple variations. For collage assets, it can produce a transparent PNG.
It requires python3 and either GEMINI_API_KEY or OPENAI_API_KEY. Set the key in the environment or store it in ~/.config/simcraft/keys.env. Image generation cannot run without a key. For a series, create an anchor image first and pass it as the reference for each later image.
What it helps with
- generate an illustration from a text prompt
- edit an image using reference files
- create a series with the same character
- make a transparent cut-out for a collage
- produce image variations to compare
Example prompts for the agent
- Create a square watercolor illustration of a cat.
- Make a transparent cut-out of this object for a collage.
- Create a series featuring the same character, using the first result as the reference.
How to install image-gen
1Skills CLI (Vercel)
npx skills add dotslashsimran/simcraft --skill image-gen -a claude-code2Manually: put the files in place
~/.claude/skills/image-gen/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/image-gen/
1Skills CLI (Vercel)
npx skills add dotslashsimran/simcraft --skill image-gen -a codex2Manually: put the files in place
.agents/skills/image-gen/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add dotslashsimran/simcraft --skill image-gen -a cursor2Manually: put the files in place
.cursor/skills/image-gen/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install dotslashsimran/simcraft skills/design/image-gen2Manually: put the files in place
.github/skills/image-gen/SKILL.md1Skills CLI (Vercel)
npx skills add dotslashsimran/simcraft --skill image-gen -a gemini-cli2Platform CLI
gemini skills install https://github.com/dotslashsimran/simcraft --path skills/design/image-genManually: put the files in place
.devin/skills/image-gen/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about image-gen
How do I install image-gen in Claude Code?
Run npx skills add dotslashsimran/simcraft --skill image-gen -a claude-code. The skill file is at ~/.claude/skills/image-gen/SKILL.md.
What does image-gen do?
It generates and edits images through Gemini or OpenAI. It also supports reference images, consistent subjects across a series, and transparent cut-outs.
What does image-gen need to run?
It requires python3 and either GEMINI_API_KEY or OPENAI_API_KEY. Provide the key through the environment or store it in ~/.config/simcraft/keys.env.
Source text
SKILL.md · MIT
--- name: image-gen description: Generate images with the user's own API keys (Google Gemini "Nano Banana" or OpenAI gpt-image). Use when asked to generate, create or make an image, illustration, icon, cut-out, sticker, thumbnail, texture, mockup or visual asset, to edit an image, or to make several images that stay consistent (same character or object). Also used by the vox-explainer skill for collage cut-outs. --- # Image gen ``` python3 ~/simcraft/skills/design/image-gen/scripts/gen_image.py "<prompt>" --out <dir> --name <name> [options] ``` Standard library only, so any `python3` works. ## Keys The script reads `GEMINI_API_KEY` and `OPENAI_API_KEY` from the environment, or from `~/.config/simcraft/keys.env` (one `NAME=value` per line, chmod 600). - Run `--check` to see which keys are set. It never prints a key. - If no key is set, tell the user to open the file themselves (`open -e ~/.config/simcraft/keys.env`) and paste it in. Never ask them to paste a key into chat, and never read keys out of other projects' files. - Keys go only in request headers. They never go in a URL, a log, or a sidecar file. - Get a Gemini key at aistudio.google.com/apikey (it has a free tier). Get an OpenAI key at platform.openai.com/api-keys. ## Options | Option | What it does | |---|---| | `--n 4` | Makes 4 variations in parallel, plus `<name>_sheet.png` to pick from. Use this for anything that matters. | | `--aspect 16:9` | Sets the shape: 16:9, 9:16, 1:1, 4:3 or 3:4. Match it to where the image goes. | | `--ref a.png b.png` | Reference images. Use them to edit an image, match a style, or keep the same character or object across images. | | `--cutout` | Gives a transparent PNG for collages. Gemini generates on chroma green and the script keys it out with clean edges. OpenAI makes real transparency. | | `--provider gemini\|openai` | Picks the provider. Default: Gemini if its key is set. | | `--model M` | Picks the model. By default Gemini picks the newest image model the key can use (`--models` lists them), and OpenAI uses gpt-image-2. | | `--quality low\|medium\|high` | OpenAI only. Default high. | | `--brand devin` | Adds a brand kit's image style and palette to the prompt. **For any brand work, run the brand-kit skill first.** | Every image gets a `<name>.json` sidecar with the exact prompt, model and settings, so it can be remade or tweaked later. ## Which provider - **Gemini:** fast and cheap. Best for iterating, for edits, and for keeping things consistent with `--ref`. - **OpenAI gpt-image:** best for images with text in them, and for true transparent cut-outs. ## Prompting - Describe the subject, the medium, the light and the framing, in that order. Say what to leave out. - **No text in images** unless the user asks for it. Models still misspell words. Add type afterwards in code. - For a series, generate one anchor image first. Then pass that same anchor as `--ref` to every other image. Never chain image 2 into image 3, because small errors pile up. - Show the user the contact sheet before using images anywhere. Regenerate one variation instead of all of them.
© dotslashsimran · MIT · dotslashsimran/simcraft
Similar skills
All skills for Design →image-gen by other authors comes first.