ClaudeMap

GPT Image Skill

Generate and edit GPT images from Claude Code or Codex through your ChatGPT subscription — not the separately billed Images API.

Skills & Commandsskillimage-generationchatgptcodex
Visit projectGENEXIS-AI/gpt-image-skill

Bridges the built-in $imagegen / gpt-image capability of a ChatGPT/Codex subscription to local coding agents: direct prompts pass through unchanged; when you delegate several concepts, the agent writes a distinct image-ready prompt for each. Real reference files feed into generation, transparent-PNG outputs are checked for alpha support, results land in <project>/generated-images/, and batches run with bounded parallelism. The repo is explicit about the boundary: it does not call the OpenAI Images API, does not use OPENAI_API_KEY, and generation consumes your included plan usage (not available on the Free plan).

What it does

  • Works from Codex, Claude Code, and Google Antigravity via one skill install ($gpt-image / /gpt-image / mention gpt-image)
  • Reference-image edits and multi-concept delegation: the agent drafts a distinct image-ready prompt per concept instead of one vague prompt for everything
  • Transparent-PNG bridge outputs are checked for alpha/transparency support before use; ready outputs run with bounded parallelism into <project>/generated-images/*.png
  • No Images API, no API key, no separate billing — a CI workflow validates the skill, and AGENT_INSTALL.md is the one-time installation contract

When to use it

When you already pay for ChatGPT and want your coding agent to produce UI mockups, diagrams and marketing images in-repo, without standing up an Images API billing relationship.

Getting started

# paste this into Codex / Claude Code / Antigravity:
Install and verify GPT Image Skill for the current user from:
https://github.com/GENEXIS-AI/gpt-image-skill
(then follow AGENT_INSTALL.md as the one-time installation contract)

# needs: Git, Node.js 22+ LTS, Codex CLI, and Sign in with ChatGPT device authorization

Things to know

Generations consume included ChatGPT/Codex usage, and image generation is not available on the Free plan. The install prompt authorizes real environment changes (user-level installs, device auth) — read AGENT_INSTALL.md before pasting it into an environment you care about.

Repository

GENEXIS-AI/gpt-image-skill

Charted

Related on the map

  • guizang-product-video-skill

    Skill

    Guizang's agent skill turns your repo's recent updates into a finished promo video — real components, code-rendered animation, an original code-written soundtrack — no video editor involved.

    • agent-skill
    • video
    • promo
    • marketing
    View

  • geo-sleuth

    Skill

    An agent skill that geolocates a photo with nothing readable in it — OSM geometry, elevation skylines and satellite tiles turn “where was this taken?” into a measured answer with an error radius.

    • agent-skill
    • geolocation
    • osint
    • openstreetmap
    View

  • Birdview

    Skill

    A skill that makes AI coding agents map the architecture and declare the blast radius before they touch a line of code — rendered as one standalone HTML page.

    • skill
    • architecture
    • code-visualization
    • change-scope
    View