Skip to main content
affpapa.org
RU EN
skill Claude Code CX Codex Cursor GitHub Copilot

ai-image-generation · 101-skills — Claude Code skill: install guide

Generates and edits images through belt with selectable models. Use it for illustrations, mockups, and changes to existing images.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add 101-skills/superpowers --skill ai-image-generation -a claude-code
Open on GitHub

What ai-image-generation does

This skill lets an agent run image apps through the belt CLI and inference.sh. It covers GPT-Image-2, FLUX variants, Gemini, Grok, Seedream, Reve, plus more than 50 models. Tasks include prompt-based creation, image edits, inpainting, LoRA use, upscaling, and text in images.

The agent runs an app with belt app run and passes JSON input. You can target an app ID such as openai/gpt-image-2 for edits or falai/reve when text rendering matters. Use belt app list --category image to view image apps.

You need the belt CLI and a belt login session. Set that up first, because the skill cannot run image requests without belt.

What it helps with

  • create an illustration from a text prompt
  • replace an image background
  • fill in a missing image area
  • upscale an image
  • join images into a horizontal strip

Example prompts for the agent

  • Use the `ai-image-generation` skill to make a poster with large text.
  • With `ai-image-generation`, change this image background to a beach at sunset.
  • Run `falai/topaz-image-upscaler` through the `ai-image-generation` skill for an image URL.

How to install ai-image-generation

1Skills CLI (Vercel)

npx skills add 101-skills/superpowers --skill ai-image-generation -a claude-code

2Manually: put the files in place

~/.claude/skills/ai-image-generation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/ai-image-generation/

From the same set3

The whole set →
ai-video-generation 101-skills Generate videos with Google Veo, Seedance, HappyHorse and 40+ models directly in your editor. Supports text-to-video, image animation, lipsync and audio generation. Claude Code CX Codex Cursor +1 862,400installs twitter-automation 101-skills Automates Twitter and X interactions through the belt command-line interface. It posts content, manages direct messages, tracks profiles, and handles likes. Claude Code CX Codex Cursor +1 861,000installs

Other versions of ai-image-generation

ai-image-generation prime-skills This skill creates images from text and edits existing ones through the RunComfy CLI. It picks a model for the task, such as rendering poster text or making a photorealistic portrait. Claude Code CX Codex Cursor +1 382,600installs

Similar

scikit-learn K-Dense-AI A skill for Python machine learning tasks: classification, regression, clustering, preprocessing, and building ML pipelines with scikit-learn 1.9.1. Claude Code CX Codex Cursor +1 2,200installs semantic-kernel official github This skill helps build and inspect Semantic Kernel applications using current documentation. Use it for projects involving plugins, function calling, or AI integrations. GitHub Copilot 1,700installs agent-memory-systems sickn33 Skill for designing agent memory with per-user and per-tenant isolation. Build RAG, conversation history, and vector stores so that one client's data stays separate from another. Claude Code CX Codex Cursor +1 2,000installs vision-analysis MiniMax-AI Describes images, extracts text, and reviews UI mockups using the MiniMax vision MCP tool. Handy when an agent needs to understand a screenshot or design file. Claude Code CX Codex Cursor +1 2,700installs markitdown K-Dense-AI A Claude Code skill that runs Microsoft MarkItDown over PDFs, Office files, HTML and CSV so the text ends up as Markdown ready for search or RAG. Claude Code CX Codex Cursor +1 2,100installs skill-creator official anthropics Creates and refines skills, then tests them with prompts, evaluations, and performance checks. Claude Code Claude.ai 414,180installs writing-for-agents Matt Pocock Guidance for writing skills and agent-facing documents. Use it when editing AGENTS.md, CLAUDE.md, or reference files reached from them. Claude Code 466,719installs media-use heygen-com Finds or generates media for HyperFrames videos, including voiceovers, music, cutouts, and color grades. Stores files locally in assets. Claude Code CX Codex Cursor +1 1,100,000installs

Questions about ai-image-generation

How do I install ai-image-generation in Claude Code?

Run npx skills add 101-skills/superpowers --skill ai-image-generation -a claude-code, then run npx skills add 101-skills/superpowers --skill ai-image-generation -a claude-code again. The skill file is at ~/.claude/skills/ai-image-generation/SKILL.md.

What does ai-image-generation do?

It gives an agent commands to create and modify images through belt. The skill supports generation, edits, LoRA, upscaling, and text rendering through selectable apps.

What is required to run image requests?

Install the belt CLI with npx skills add belt-sh/cli and sign in using belt login. The agent then starts apps with belt app run.

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor