image-generation

Generate or edit raster images with the image_generate tool.

IndexedMIT★ 159

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hybridaione-image-generation

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Generate or edit raster images with the image_generate tool.

Use cases: writing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/image-generation

What's inside

Skill name: image-generation
Description: Generate or edit raster images with the image_generate tool.
License: MIT
Instructions: 31 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# Image Generation

Use the `image_generate` tool when the user asks you to create, generate,
render, edit, restyle, or make a deliverable raster image.

The tool comes from the `media-tools` plugin. If it is not in your tool list,
tell the user to enable it with `hybridclaw plugin install media-tools`.

Do not use `image_generate` to inspect or describe an existing image. Use
`vision_analyze` for image understanding.

## Workflow

1. Call `image_generate` with `action: "list"` if you need to check whether an
   image provider is configured or explain missing auth/model setup.
2. For generation, pass a clear `prompt` and optional `aspectRatio`, `size`,
   `quality`, and `count`. The native provider layer supports GPT Image 2,
   Nano Banana 2, Grok Imagine, and FLUX.2 when those providers are configured.
3. For image-to-image edits, pass reference media paths in the
   `image_generate` `image` or `images` arguments. Paths may come from
   `/workspace`, `/discord-media-cache`, `/uploaded-media-cache`, or safe
   current-turn Discord CDN URLs.
4. Treat provider `warnings` as user-relevant when they change requested
   options such as quality, size, aspect ratio, or count.
5. Return the generated artifact directly in the final response. The tool owns
   provider auth, provider quirks, file persistence, and media delivery paths.

Keep prompts concrete and visual. Include subject, composition, style, colors,
format, and any text that must appear in the image.

From HybridAIOne/hybridclaw, MIT.

Signals

Stars: 159
Forks: 17
Open issues: 323
Last commit (this folder): Sep 25, 2026 (1 month ago)
Last release: Oct 24, 2026 (4 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: MIT
Repository: github.com/HybridAIOne/hybridclaw
Website: www.hybridclaw.io/
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from HybridAIOne

Cite this page

image-generation skill. Agent Mart. https://agentmart.dev/skills/hybridaione-image-generation (last updated 2026-10-24)