# GPT Image 2 Style Library — style skill for style references

> **For AI agents:** find the right skill in one call — `curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"` returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the use-case page.

Pick styles and industrial prompt templates for GPT Image 2/2.5 from a 530+ case library (a 35K-star repo).

- **Type:** [Style](https://skills.varg.ai/styles.md) · [Style references](https://skills.varg.ai/browse/skills/style-refs.md)
- **Slug:** `gpt-image-2-style-library`
- **Status:** live
- **Publisher:** Canghe (community)
- **License:** MIT
- **Source:** https://github.com/freestylefly/awesome-gpt-image-2/tree/main/agents/skills/gpt-image-2-style-library
- **Works in:** Claude Code, Codex
- **Cost:** Free prompt library; generation billed by your image provider
- **Adoption:** 4,036 installs, 35,064 GitHub stars (GitHub + skills.sh, 2026-10-26)

## What it does

The agent-facing skill of awesome-gpt-image-2, one of the most-starred image prompt libraries on GitHub (35K stars): 530+ cases with full prompts and generation records, 20+ industrial templates, and a section comparing GPT Image 2.5 outputs for the same prompt. The skill chooses visual styles and templates from the library by category, style tag and scene tag, rewrites or classifies prompts, and flags known pitfalls with example cases.

## Use when

- Write or improve a GPT Image 2/2.5 prompt from a proven template
- Classify a prompt by style and scene

## Not for

- Generating the image itself (pair it with your image tool)

## Install

- Claude Code: `npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library --agent claude-code codex --global --yes --copy`
- Codex: `npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-library --agent claude-code codex --global --yes --copy`

**Models it drives:** gpt_image_2, gpt_image_2_5

## Example output

https://skills.varg.ai/previews/gpt-image-2-style-library.webp — The skill's documented example output: a 'city life system map' infographic generated from the request 用 gpt-image-2-style-library 技能生成城市生命系统图谱. (credit: 苍何 Canghe (freestylefly / awesome-gpt-image-2), https://github.com/freestylefly/awesome-gpt-image-2/tree/main/agents/skills/gpt-image-2-style-library)

## More style references skills

- [FrameThrower Film References](https://skills.varg.ai/skills/framethrower.md): Film stills from 5,489 films, searchable by lighting, lens, shot size, color and mood.
- [Are.na MCP](https://skills.varg.ai/skills/arena-mcp.md): Build and read Are.na moodboard channels from your agent.

## Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt