Skip to content
Skills Library
AI & agents · Building & coding

image-forge-create

/image-forge-create

Create a new image from a text prompt with the image-forge MCP server (generate_image). Use when the user asks to generate, draw, render or design a picture, illustration, photo, logo, banner or mockup, and the image-forge MCP is available.

Licence
MIT
Last repository change
29.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 29.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Create a new image from a text prompt with the image-forge MCP server (generate_image). Use when the user asks to generate, draw, render or design a picture, illustration, photo, logo, banner or mockup, and the image-forge MCP is available.

Original author description

Create a new image from a text prompt with the image-forge MCP server (generate_image). Use when the user asks to generate, draw, render or design a picture, illustration, photo, logo, banner or mockup, and the image-forge MCP is available.

How it works

  1. What to do
  2. Notes
Original SKILL.md headings · 26 lines, 234 words
SKILL.md preview
---
name: image-forge-create
description: Create a new image from a text prompt with the image-forge MCP server (generate_image). Use when the user asks to generate, draw, render or design a picture, illustration, photo, logo, banner or mockup, and the image-forge MCP is available.
license: MIT
compatibility: opencode
metadata:
  mcp: image-forge
  model: flux-2-klein-4b
---

# Create an image

## What to do

1. Call `generate_image` on the `image-forge` MCP server. Never call it more than once in
   parallel: each call spends the daily Neurons allowance.
2. Do not pass `model`. The server default is `flux-2-klein-4b` (~126 neurons per 1024px image,
   ~79 images/day on the free plan), and it is the model this MCP is tuned for.
3. Write the prompt as a description of the final image, not of an action: subject, style,
   lighting, framing, palette, background. Keep it under 4000 characters.
4. Pass `width` and `height` only when the aspect ratio matters; otherwise 1024x1024 is used.
   Minimum 256, maximum 2048. `steps` defaults to the model value; `seed` only to reproduce.
5. Ask for `count` variants only when the user wants alternatives (max 4 per call).
6. Report the returned file paths. Do not paste the image back into the conversation.

## Notes

- `negative_prompt` and `strength` are ignored by `flux-2-klein-4b`; do not pass them.
- `sd15-img2img` cannot generate from text alone (it errors) and returns 403 / error 5018 on
  accounts without access. Use it only if the user says their account has access.
- If the tool reports a quota error, tell the user: lower `count`, wait for the 00:00 UTC reset,
  or raise `IMAGE_FORGE_HARD_NEURONS` if they accept the spend.
- Missing credentials show up as a CONFIG error: point the user to `image-forge/.env`
  (`CLOUDFLARE_ACCOUNT_ID`, `CLOUDFLARE_API_TOKEN`).

Versions

The database has no other skills named image-forge-create.

Database snapshot: 13.11.2026 · package version a456163138d5 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90image-forge-variant
    Create an exact variant of an existing image with the image-forge MCP server (edit_image). Use when the user says "make a variant of this image", "copy this image but change X", "same image with another color/text", or provides an image path or URL and wants a new version of it.
  • 100image-generation
    Generate or edit images from text prompts. Use when the user asks to create, draw, design, or edit an image, illustration, photo, icon, poster, or any visual content.
  • 95cf-image
    Generate an image from a text description using Cloudflare Workers AI (the flux-1-schnell model). Use this skill whenever the user wants to create, generate, make, or draw an image / picture / logo / icon / thumbnail / wallpaper / banner from a text idea and mentions Cloudflare,…
  • 100image-analysis
    Analyze an image — screenshot, diagram, UI mockup, or chart — with Claude's vision. Triggers on: analyze this image, look at this screenshot, what's in this diagram, read this mockup, describe this picture, analyze image.
  • 98image-generation
    Generate an image from a text description and save it to disk. Uses Gemini (Antigravity CLI or API key), OpenAI (API key), the free Pollinations service or a local model, whichever the user has set up. Use when the user asks to create, generate, draw, or make an image, picture,…
  • 100generate-image
    Generate, edit, or restyle a still image on Comfy Cloud. Use when the user asks to create, draw, design, edit, inpaint, or restyle a picture, photo, illustration, poster, or other still image, including from text or from a source image they provide.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.