Agentic Skills and CLI for GPT Image 2

wuyoscar/gpt_image_2_skill

933

+122/day

PythonAI/ML💎 Hidden Gem

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

AI Analysis

A collection of curated prompts and standardized skill wrappers for integrating GPT Image 2 into agents.

Built for AI engineers and developers building autonomous agents who need reliable image generation capabilities.

From the README

GPT Image 2 Agentic Skill OpenAI GPT Image 2 agentic skill + CLI — curated, copy-paste prompts and runnable examples for skill-capable agents.

✨ At a glance

Item
Value


Gallery size
162 prompts / 162 image assets · README shows a selected showcase


Surfaces
Agentic Skill + CLI — Claude Code / Codex, OpenClaw, Hermes Agent and other skill-capable agent runtimes


Last update
2026-04-24


Docs
English + 中文

Contributions are welcome — see CONTRIBUTING.md, CODE_OF_CONDUCT.md, and SECURITY.md.

📥 Install

Claude Code

/plugin marketplace add wuyoscar/gpt_image_2_skill
/plugin install gpt-image@wuyoscar-skills

Codex

$skill-installer

Manual agent-skill install

Set AGENT_SKILLS_DIR to the skills directory used by your agent runtime, then symlink this repo's skill folder into it.

git clone 
cd gpt_image_2_skill

# Choose the skill directory for your runtime.
# Examples:
#   Codex:      ~/.codex/skills
#   Claude Code / OpenClaw / Hermes Agent / other runtimes: use that runtime's documented skills directory.
export AGENT_SKILLS_DIR="/path/to/your/agent/skills"

mkdir -p "$AGENT_SKILLS_DIR"
ln -s "$PWD/skills/gpt-image" "$AGENT_SKILLS_DIR/gpt-image"

CLI

uvx --from git+ gpt-image -p "a cat astronaut"

# or install to PATH
uv tool install git+
gpt-image -p "a cat astronaut"

Update

# plugin: use Claude Code's update flow
# codex skill: rerun the installer
# manual git clone
cd gpt_image_2_skill && git pull

# CLI
uv tool upgrade gpt-image-cli

Reads OPENAI_API_KEY from the environment or ~/.env.

⚡ Quick Usage & Prompting Fundamentals

CLI quick usage

After install, every gallery entry below can be copy-pasted as gpt-image -p "…" or requested from any skill-capable agent runtime in natural language, e.g. "generate the Boston Spring poster from the skill gallery".

Text → image

gpt-image -p "a photorealistic convenience store at 10pm" --size 1k --quality high -f store.png

Under the hood: POST /v1/images/generations with model=gpt-image-2.

Text + reference image → image (edit)

# Single-reference edit / restyle
gpt-image -p "Make it a winter evening with heavy snowfall" \
  -i chess.png --quality high -f

View on GitHub