GPT-Image2 Style Library
gpt-image-2-style-library
A skill picks a matching template and style from a library of GPT-Image2 cases and assembles it into a finished prompt
Low risk
We rate an entry low when it mostly gives the agent instructions and reference material.
Why this level
- The skill only assembles a text prompt; the model itself performs generation and billing separately
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/gpt-image-2-style-libraryDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run in a terminal in the project folder
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library -a claude-code -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit b93c18a
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .claude/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .claude/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library -a cursor -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit b93c18a
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .agents/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .agents/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library -a github-copilot -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit b93c18a
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .github/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .github/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library -a codex -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit b93c18a
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .agents/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .agents/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library -a gemini-cli -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit b93c18a
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .agents/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .agents/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .devin/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .devin/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Formerly Windsurf.
Run in a terminal in the project folder
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library -a cline -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit b93c18a
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .cline/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .cline/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library -a roo -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit b93c18a
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .roo/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .roo/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
A fork of Roo Code, same .roo folders.
Run in a terminal in the project folder
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library -a opencode -yThe skills tool installs the current version from the repository. Add the -g flag to use the skill in every project.
Without third-party tools, from commit b93c18a
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .agents/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .agents/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .agents/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .agents/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Run in a terminal in the project folder
tmp=$(mktemp -d)
git clone --filter=blob:none --no-checkout https://github.com/freestylefly/awesome-gpt-image-2.git "$tmp"
git -C "$tmp" sparse-checkout set --no-cone /agents/skills/gpt-image-2-style-library/
git -C "$tmp" checkout b93c18ad45397c828fcc39a1ed347830433b3de4
mkdir -p .agents/skills
cp -R "$tmp/agents/skills/gpt-image-2-style-library" .agents/skills/gpt-image-2-style-libraryCommands for macOS and Linux, on Windows run them in Git Bash.
Clone the freestylefly/awesome-gpt-image-2 repository, install dependencies, and run npm run install:skill to place the skill in Codex's or another agent's local skills folder.
Other ways from the author
git clone https://github.com/freestylefly/awesome-gpt-image-2.git && cd awesome-gpt-image-2 && npm install && npm run install:skillInstalls the skill into Codex's local skills folder. Also available as a Claude Code plugin through the repository's .claude-plugin/marketplace.json.
This is third-party code. Review the repository files before installing.
What it does
The skill turns a description of a desired image into a ready GPT-Image2 prompt using a reference drawn from the awesome-gpt-image-2 repository, which holds hundreds of parsed cases and dozens of industrial templates across categories such as product, poster, UI, infographic, brand, photo, illustration, and character. The agent first detects the request's language and target output type, then matches a template by category, visual style, or scene, offering two or three options when the choice is ambiguous. The finished prompt is assembled from blocks: subject and task, composition, style and materials, on-image text requirements, aspect ratio, and constraints.
Who it is for. For designers and content specialists who regularly generate images with GPT-Image2 and want a consistent prompt instead of a guessed one.
Good fit when
- You need a GPT-Image2 prompt for a specific job: a poster, a cover, an infographic, or a product render
- You want to quickly compare two or three style options before generating
- You need a prompt with exact requirements for on-image text and aspect ratio
Not a fit when
- You need a prompt for a different image model, not GPT-Image2
- The repository with the style reference is not and will not be cloned locally
Example request
Build a GPT-Image2 prompt for a city life system poster in a flat infographic styleLimitations
The skill does not generate the image itself and does not call the GPT-Image2 API; it only builds a prompt from the repository's local style reference. The reference needs to be kept up to date with the package.json command when the repository's data changes.
How to disable. Delete the gpt-image-2-style-library folder from your agent's local skills folder, where npm run install:skill placed it.
Security check
- The skill only assembles a text prompt; the model itself performs generation and billing separately
README in short
The parent repository is a large library of parsed examples and industrial prompt templates for GPT-Image2, with its own website for browsing the gallery. Inside it sits a reusable gpt-image-2-style-library skill with its own SKILL.md, an install script in bin/install.mjs, and a template reference the agent reads instead of guessing a style from memory. The skill is also distributed as part of a Claude Code plugin marketplace through .claude-plugin/marketplace.json. MIT licensed.
SKILL.md
--- name: gpt-image-2-style-library description: Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases. --- # GPT-Image2 Style Library Use this skill to turn a user's image-generation intent into a production-ready GPT-Image2 prompt using the awesome-gpt-image-2 style library. ## Workflow 1. Detect the user's language and answer in that language. 2. Identify the user's target output: product, poster, UI, infographic, brand, photo, illustration, character, scene, history, document, or special task. 3. Match the request in this order: template category, visual style tag, scene tag, then nearest example cases. 4. If one template is clearly strongest, use it directly. If several are plausible, present 2-3 options with short reasons and ask the user to choose. 5. Build the final prompt with these blocks: subject and task, composition and layout, visual style and materials, text and label requirements, aspect ratio and output format, constraints and negative details.
FAQ
Does the skill generate the image itself?
No, it only assembles the prompt from the template library; the actual image generation is done separately by the GPT-Image2 model.
How does the skill keep its reference current?
The references/style-library.md file is generated from data/style-library.json by running npm run generate:style-skill whenever the repository's data changes.
Related
Skills and CLI from HeyGen: the agent writes HTML compositions and renders them into MP4 videos, captions, motion graphics and decks
Blender MCP
MCP for Blender
An MCP server and Blender addon: the agent creates and edits objects, materials and scenes, pulls assets and runs Python in Blender
Official Remotion skills for making videos in React: compositions, animation, captions, maps and rendering
Agentic video studio for Claude Code, Cursor and Codex: script, voiceover, images, stock footage, music, subtitles and render