Skip to content

Image Generation

Lets the agent create and edit images from text prompts using OpenAI gpt-image-2 via Hive credits.

Repository
aden-hive/hive
Stars
11,132
Licence
Apache-2.0
Files
1 file

What it does

It teaches the agent how to call an image generation tool that turns a written description into a picture, and how to edit or restyle existing images supplied as reference files or URLs. Generation runs in the background, so the agent checks back until the image is ready, then shows it to you in chat. Costs are billed to your Hive credits like an AI text call, so no separate API key is needed, and the skill keeps quality at the cheapest setting by default.

Great for

  • Marketers who need quick logo concepts, banners, or social graphics
  • Designers who want rough mockups or product shots placed on reference photos
  • Anyone who wants a simple illustration without opening an image editor

Skip it if

  • Final, high-resolution print work, because the skill locks quality to low and disables medium and high settings
  • Generating images of real people's likeness, since the skill itself advises against this and prompts may be refused
  • Situations where Hive credits are unavailable, since the skill stops when credits run out

Try asking

  • “Make us a logo for a coffee shop: a friendly bean character, flat vector, brown and cream”
  • “Put this product photo on a marble kitchen counter with soft morning light”
  • “Create a 1536x1024 banner for our launch day with the words "Launch Day" in bold”
  • “Generate a thumbnail image for my blog post about gardening”
Step-by-step guide: how to use Image GenerationInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    image-generation.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip image-generation.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip image-generation.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Describe the subject, style, framing, colors, and any exact text to render in quotes for better results
  • Upload or reference an existing image when you want edits or a consistent look across pictures
  • Ask for several variations only when you need them, since each image is billed separately

What's inside

  • SKILL.md

Redistributed unmodified from aden-hive/hive under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.