skills.rest
wecode-ai
wecode-aiOFFICIAL
Explore all skills by this author →
GitHub

wegent-image-generation

Generates images from text prompts or reference images via an MCP image tool.

772|135|Updated Jan 10, 2026
Search Tags:#image generation#mcp#creative#text-to-image#reference images#generate_image#wegent
One-click install
npx skills add https://github.com/wecode-ai/Wegent --skill wegent-image-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wegent-image-generation
Source: https://github.com/wecode-ai/Wegent/tree/main/backend/init_data/skills/wegent-image-generation
Command: npx skills add https://github.com/wecode-ai/Wegent --skill wegent-image-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Users working in Wegent chat sessions often need visual assets but must leave the conversation to use separate image tools. This Skill lets the agent create or revise images directly in the task flow and attach the results to the task automatically.

Core Features & Use Cases

  • Text-to-Image Generation: Calls the generate_image MCP tool with a complete visual description to produce images from natural language prompts.
  • Image-Reference Generation: Accepts user-supplied image attachments or URLs via reference_images to revise or restyle existing visuals, using attachment IDs rather than local sandbox paths.
  • Automatic Attachment Handling: Saves generated images as task attachments and returns image blocks, so no duplicate result cards are created.
  • Use Case: A product designer in a Wegent chat asks for three logo concept variations based on an uploaded sketch; the agent passes the sketch attachment ID and a detailed prompt to generate_image and the results appear as task attachments.

Quick Start

Ask the agent to generate an image, for example: create an illustration of a futuristic city skyline at sunset in watercolor style.

Frequently Asked Questions about wegent-image-generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate an image from a text prompt in Wegent?▼

Describe the image you want in the chat and the agent calls the generate_image tool with your full visual description in the prompt parameter. The generated image is saved as a task attachment and returned as an image block.

How do I revise or restyle an existing image with AI?▼

Attach the image or provide its URL in the conversation, then describe the changes you want. The agent passes the attachment ID through the reference_images parameter along with your prompt to generate the revised image.

Can I generate multiple images in one request?▼

Yes, but only when you explicitly ask for multiple images. By default the tool generates a single image per request, so state the desired count clearly in your prompt.

Why did image generation return an error?▼

The generate_image tool returns an error field when generation fails, for example due to an invalid prompt or unavailable backend. The agent explains the error once and does not retry with unchanged parameters, so adjust your request before trying again.

Which agent shells support the image generation skill?▼

The skill binds to the Chat, Agno, and ClaudeCode shells in Wegent. It connects to the backend image MCP server over streamable-http using a task token for authorization.

Related Skills

Explore More Design & Creative Skills→
danmaraudadanmarauda

Convex Agents Files

Automate file uploads, attachments, and media handling in Convex agent conversations.

Community
Intermediate
allenhutchisonallenhutchison
515

image-generation

Generate images from text prompts and save them to vault attachments.

Community
Intermediate
mishahaninmishahanin
10

image-prompt

Generate photorealistic text-to-image prompts from written content.

Community
Intermediate
HKUDSHKUDS
46.8k

cli-anything-inkscape

Manipulate SVG documents via command-line commands with Inkscape compatibility.

Official
Intermediate