Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill helps prompt engineers translate existing photographs, 3D renders, and illustrations into precise AI generation prompts. By analyzing composition, lighting, and materials, it allows users to recreate or imitate specific visual styles across various formats including typography, logos, and landscapes.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
Setup
Claude Code plugin: gpt-image
Installs: Installs the gpt-image plugin from the wuyoscar-skills marketplace. The repository also contains get-prompt-from-image, but the supplied marketplace manifest only establishes the gpt-image plugin mapping. · Claude Code
Before you start
Claude Code with its plugin marketplace commands available
Python 3.11 or newer
For CLI/API image operations: an existing gpt-image, uv, or uvx executable
For CLI/API image operations: OPENAI_API_KEY; successful calls may incur OpenAI API charges
Before installing, check Claude Code's skill or plugin status. Preserve existing skill folders and API-key files, and obtain approval before using a global or shared installation directory.
In a Claude Code session, add the author's plugin marketplace.
Installs: Installs only the gpt-image skill from its GitHub skill-folder URL. · Codex
Before you start
Codex with the built-in $skill-installer helper
Python 3.11 or newer
For CLI/API image operations: an existing gpt-image, uv, or uvx executable
For CLI/API image operations: OPENAI_API_KEY; successful calls may incur OpenAI API charges
Before installing, check Codex's skill status. Preserve existing skill folders and API-key files, and obtain approval before using a global or shared installation directory.
Open Codex and enter this complete request in the agent session; these are not terminal commands.
$skill-installer
Install this skill from GitHub:
https://github.com/wuyoscar/gpt_image_2_skill/tree/main/skills/gpt-image
Installs: Installs the repository's standalone gpt-image CLI to PATH; this is a CLI installation, not an agent-skill installation.
Before you start
Python 3.11 or newer
uv already installed
OPENAI_API_KEY is required for CLI/API image operations; successful calls may incur OpenAI API charges
In a terminal, run the documented checks for an existing CLI installation, uv-managed installation, and process-level API-key presence. The key's value remains hidden.
command -v gpt-image || true
command -v uv >/dev/null && uv tool list | grep -E '^gpt-image-cli([[:space:]]|$)' || true
test -n "${OPENAI_API_KEY:-}" && echo "OPENAI_API_KEY is already set (value hidden)"
In a terminal, install the CLI to PATH only when gpt-image is not already available.
OPENAI_API_KEY for the CLI path, or a requested host-native image-generation path
Approval for the API call, which may incur charges
Use the gpt-image skill to generate one original flat leaf icon, centered with generous padding on a transparent background. Use the exact model gpt-image-2.5-flare, medium quality, PNG format, and save it as leaf.png. Proceed without reconfirming the exact valid model.
Replace <REFERENCE_IMAGE_PATH> with the path to a user-provided reference image
Optional target image model, language, format, or prompt length; otherwise the skill's default format applies
Make sure get-prompt-from-image is installed in your agent before trying this task.
Use the get-prompt-from-image skill to inspect the image at <REFERENCE_IMAGE_PATH> and return its default final positive and negative image-generation prompts. Focus on the reproduction-critical composition, subject, lighting, materials, background, color relationships, spatial layers, mood, and medium without inventing unclear details.
Claude
Codex
Gemini CLI
OpenClaw
OpenCode
Hermes
DeepSeek