GPT Image

Trust Score 84/100

from gpt-image18

Generate and edit raster images via a CLI-first workflow, with an explicit Codex path for native generation.

triggers:generate an imageedit this imagehero bannerproduct mockupremove the backgroundmake bitmap variations

GitHub SKILL.md

What it does

This skill adds a CLI-first raster image generation and editing workflow that works across Claude Code, GitHub Copilot CLI, and Codex. It provides two modes: a default CLI mode that uses a bundled scripts/image_gen.py for generation/editing, and an explicit Codex mode for environments that prefer Codex-native generation. The skill centralises image tasks (generate, edit, generate-batch) and enforces safe defaults and project-aware output handling.

When to use it

Use this skill when the user asks to generate hero banners, product mockups, blog headers, photoreal scenes, or to edit existing raster images (background removal, compositing, text replacement). Prefer it when you need a reproducible CLI workflow or when Codex-native generation is explicitly requested. Do not use for vector or SVG-native tasks.

What's included

Scripts: mentions bundled scripts/image_gen.py (CLI mode) — check repo for actual script.
References: prompting recipes, CLI docs, and image API references are listed in the skill docs.
Instructions: clear two-mode decision rules, parameter checks, and conservative defaults; guidance for Codex exec usage and file saving conventions.

Compatible agents

Works well with Claude Code and GitHub Copilot CLI; offers an explicit Codex CLI bridge for Codex-native hosts.

Audit Summary

GPT Image skill provides a CLI-first workflow for generating and editing images via OpenAI's GPT Image API, with an explicit Codex delegation path. The bundled script (image_gen.py) is well-structured with argparse subcommands, async batch generation, retry logic, prompt augmentation, and downscaling support. Script exited with code 2 (missing required subcommand) under DRY_RUN — expected behavior since no API key or command was provided.

Watch Out

Requires OPENAI_API_KEY environment variable for CLI mode
No Codex CLI validation — Codex mode assumes `codex` is installed and authenticated

Notes

Clean skill with no security concerns. Script uses argparse properly with thorough input validation. The long SKILL.md is well-organized with clear decision points and mode separation. Dry-run mode is a nice safety feature.

Information

Repository: gpt-image
Stars: 18

Trust Score

Overall84

Security88

Code Quality83

Architecture78

Usefulness72

Related Skills

ds-fix — data-science mid-analysis fixer

Orchestrates diagnosis and targeted fixes mid-analysis: diagnose root cause, apply fixes with output-first verification, and update project learnings.

Readwise Reader Document Management

Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.

ezBookkeeping API Tools

Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi

Tmux Bridge

Give an agent controlled access to a local tmux terminal bridge so it can run shell commands, capture output, and manage sessions on the user's machine.

SourceSage CLI

Generate concise, LLM-friendly repository summaries (Markdown) using the SourceSage CLI — supports lite mode, language switching, and targeted repo analysis.

Nit (Nitter CLI)

Terminal client to browse tweets, view profiles, and search posts via Nitter instances without opening a browser.

hn — Hacker News CLI

Terminal-based Hacker News client with a CLI and optional interactive TUI for browsing top/new/best/ask/show/jobs stories, viewing threads with nested comments,

Runway Prod Checklist

Production checklist and SDK patterns for integrating Runway (AI video/image generation) into production workflows.

Back to Skills