Agent skill · design visual · aradotso
gpt-image-2-skill
GPT Image 2 prompt gallery, agentic skill, and CLI for OpenAI image generation and editing with curated prompts and reference workflows
Why this skill is useful
Provides a curated gallery of 162 prompts and a CLI for OpenAI image generation that enhances the AI's ability to generate specific types of images effectively.
What it needs
Requires uv installed locally. Requires openai account access. About 8k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
GPT Image 2 Skill Skill by ara.so — Daily 2026 Skills collection. A prompt gallery, CLI, and agentic skill for OpenAI's gpt-image-2 model. Provides 162 curated prompts across categories (research figures, UI mockups, typography, photography, anime, maps, product shots), a full-featured CLI, and skill integrations for Claude Code, Codex, and other agent runtimes. --- Install CLI (fastest) Claude Code Codex Manual agent-skill install --- Configuration The CLI and skill read your OpenAI key from the environment or ~/.env: No other configuration is required. --- CLI Reference Text → Image (generation) Text + Reference Image → Image (edit / restyle) Mask-based Inpainting Full Parameter Reference Flag Values Default Notes --- --- --- --- -p, --prompt string required Full prompt text -f, --file path auto-timestamped .png Output file path -i, --image path (repeatable) — Triggers /v1/images/edits; pass multiple for multi-ref -m, --mask path (PNG with alpha) — Requires -i; transparent = regenerate --size 1k 2k 4k portrait landscape square wide tall or 1024x1024 1024x1024 Literals must be 16-px multiples, max edge 3840 --quality auto low medium high high Budget dial: low=drafts, high=final/text-heavy -n, --n int 1 Batch count; suffixes files 0, 1, … --background auto opaque API default opaque disables transparency --moderation auto low low low for broader exploration --format png jpeg webp png Response encoding format --compression 0–100 — JPEG/WebP only Exit codes: 0 success · 1 API/refusal error · 2 bad args or missing key --- Python SDK Usage Text → Image Portrait / Tall Generation Image Edit (single reference) Multi-Reference Edit Mask-Based Inpainting Batch Generation with Saving --- Prompt Engineering Patterns Structure template Research paper figure UI mockup Typography poster Photorealistic product shot Put required text in quotes --- Quality / Budget Strategy Stage --quality When to use --- --- --- Exploration sweep low Generating 8–16 variants to find direction Norma …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/gpt-image-2-skill