Skip to main content
affpapa.org
RU EN
skill CX Codex

gpt-image-2-skill — Claude Code skill: images and install

A skill and CLI for creating and editing images with OpenAI gpt-image-2. Use it for reference-based edits, masks, and batches of variants.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓ 
npx skills add reason-machines/trending-skills --skill gpt-image-2-skill -a claude-code
Open on GitHub

What gpt-image-2-skill does

This skill lets an agent call gpt-image-2 for text-to-image generation, single-image edits, multi-reference compositions, and masked inpainting. It also includes a collection of 162 prompts covering interface mockups, diagrams, type-focused images, maps, photography, and product scenes.

The gpt-image CLI accepts a prompt plus output path, size, quality, format, and variant count. Results can be written as PNG, JPEG, or WebP. Set OPENAI_API_KEY in the environment or in ~/.env before use; without that key, the call exits with a missing-key error.

What it helps with

  • generate an image from a text brief
  • restyle a scene using one or more references
  • replace a selected area with a PNG mask
  • save several generated variants as separate files

Example prompts for the agent

  • Ask the skill to create a product image from a brief and save it as product.png.
  • Tell the agent to edit photo.jpg using sky_mask.png, changing only the masked sky.
  • Ask it to produce several visual variants and save them through gpt-image.

How to install gpt-image-2-skill

1Skills CLI (Vercel)

npx skills add reason-machines/trending-skills --skill gpt-image-2-skill -a claude-code

2Manually: put the files in place

~/.claude/skills/gpt-image-2-skill/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/gpt-image-2-skill/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about gpt-image-2-skill

How do I install gpt-image-2-skill in Claude Code?

Run npx skills add reason-machines/trending-skills --skill gpt-image-2-skill -a claude-code. The skill file will be available at ~/.claude/skills/gpt-image-2-skill/SKILL.md.

What does gpt-image-2-skill do?

It gives an agent access to image generation and editing with gpt-image-2, including reference images, masks, and batches of outputs. The package also provides a CLI and a prompt collection.

What is required for the skill to work?

Provide an OpenAI key through OPENAI_API_KEY or ~/.env. Masked edits require an input image and a PNG mask with an alpha channel.

Similar skills

All skills for AI and ML →
gpt-image 101-skills Skill that connects OpenAI GPT-Image-2 to your AI coding agent. Text-to-image, reference-based editing, mask inpainting via inference.sh CLI. CX Codex +1 12,300installs gpt-image-2 GargantuaX A Python skill that runs every GPT Image 2 route from the terminal. Covers text-to-image, mask edits, and the Responses API with streaming. CX Codex +1 16,800installs gpt-image-1-5 intellectronica Generates and edits images using OpenAI's GPT Image 1.5 model. It handles text prompts, full image alterations, and precise inpainting with masks. CX Codex +1 615installs gpt-image-2-style-library freestylefly Converts user ideas into production-ready GPT-Image2 prompts using the awesome-gpt-image-2 catalog. Helps configure layout, style tags, and concrete constraints. CX Codex +1 4,000installs codex-gpt-image-2-5-flare MengTo A skill that walks the agent through generating and editing artwork with Claude built-in image gen: transparent PNGs, sprites, emblems and UI graphics. CX Codex +1 475installs scenario-gpt-image scenario-labs A skill that teaches your agent to run Anthropic's Claude Image models on Scenario over MCP: text-to-image, reference edits, alpha-mask inpainting and transparent cutouts. CX Codex +1 402installs

From the same set186

tilekernels-gpu-kernels This skill guides agents through TileKernels GPU kernels for MoE, quantization and other LLM operations. Use it when writing or checking TileLang code. CX Codex +1 363installs aris-autonomous-ml-research A Markdown skill that links ML idea discovery, experiments, paper writing, review, and rebuttal. It fits workflows where one model checks another. CX Codex +1 360installs freellmapi-proxy This skill sets up a self-hosted Anthropic-compatible proxy that puts free-tier keys from many providers behind one endpoint. CX Codex +1 351installs ppt-image-first-workflow Takes a vague deck request through style previews and a locked plan to a PPTX where every slide is one full-page image made with GPT Image 2. CX Codex +1 325installs superlevels-chrome-extension A skill that lets your agent work on SuperLevels, an open-source Chrome extension bundling tab cleaning, cookie editing, dark mode and custom CSS. CX Codex +1 314installs privacy-parser-pii-extraction Returns personal data found in a string as labelled spans with character offsets. Useful when a log or document has to be inspected before it leaves your machine. CX Codex +1 310installs flowdriver-covert-transport Routes SOCKS5 traffic through Google Drive API calls so it survives DPI and SNI filtering. Useful on networks where a normal proxy gets blocked. CX Codex +1 310installs future-agi-platform A skill that walks your coding agent through Future AGI: wiring up tracing, running eval metrics, and self-hosting the platform. CX Codex +1 308installs

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