awesome-gpt-image-2 is a collection of prompts and reusable templates for generating images with GPT-Image-2. It helps people study, adapt, and apply image-generation prompts across different styles and scenarios.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add freestylefly/awesome-gpt-image-2 --skill gpt-image-2-style-librarygit clone --depth 1 https://github.com/freestylefly/awesome-gpt-image-2Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/freestylefly/awesome-gpt-image-2/gpt-image-2-style-library)<a href="https://agentmods.dev/skills/freestylefly/awesome-gpt-image-2/gpt-image-2-style-library"><img src="https://agentmods.dev/badge/skills/freestylefly/awesome-gpt-image-2/gpt-image-2-style-library/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/freestylefly/awesome-gpt-image-2/gpt-image-2-style-library"><img src="https://agentmods.dev/badge/skills/freestylefly/awesome-gpt-image-2/gpt-image-2-style-library.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.00522 |
| Opus 5 | $0.00036 | $0.00261 |
| Sonnet 5 | $0.00014 | $0.00104 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
gpt-image-2-style-library scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
Example Output
Example request: 用 gpt-image-2-style-library 技能生成城市生命系统图谱
Reference
- Read
references/style-library.mdbefore choosing a template or style. - The reference is generated from
data/style-library.jsonin the repository. - Prefer the reference over memory when template names, categories, covers, or style tags matter.
Workflow
- Detect the user's language and answer in that language.
- Identify the user's target output: product, poster, UI, infographic, brand, photo, illustration, character, scene, history, document, or special task.
- Match the request in this order: template category, visual style tag, scene tag, then nearest example cases.
- 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.
- 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
- Include the selected template name and any useful example case IDs.
Output Defaults
- Provide a copyable prompt first.
- Keep constraints concrete: exact text, aspect ratio, readable labels, layout hierarchy, and avoided artifacts.
- For Chinese requests, write the final prompt in Chinese unless the user asks for English.
- For English requests, write the final prompt in English unless the user asks for Chinese.
- When the user asks for multiple concepts, reuse one template and vary subject, composition, palette, and scene.
Maintenance
When the source repository changes, run:
npm run generate:style-skill
To install the skill into the local Codex skill folder, run:
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 58 lines · 72 tokens per session scan A 98519a3bfd28
gpt-image-2-style-library is a skill published in the GitHub repository freestylefly/awesome-gpt-image-2 (31,343 stars, last pushed today), licensed MIT. It adds 72 tokens to every session and 522 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
female-portrait-director
Generate, visually expand, optimize, diagnose, and route structured AI image prompts for adult female portraits. Use for lifestyle, curve-focused, fashion, oriental, fantasy, realism, beauty, CCD, low-key cinematic, studio, sport, travel, and e-commerce portrait requests; onboarding or usage help; parameter…
gpt-image-2-prompt-engine
A structured prompt-writing tool for GPT-Image-2, using reusable JSON templates and a four-step workflow. It is designed for controlled commercial images such as product photos, posters, infographics, brand visuals, UI screenshots, and character designs.
gpt-image-2-portrait-library
Choose, inspect, attribute, and safely adapt original-language GPT Image 2 portrait-editing prompts from a 519-record provenance-first library. Use its two-level task and scenario taxonomy for restoration, natural retouching, professional identity photos, lifestyle portraits, and identity-preserved transformations.
gpt-image-2-prompt-architect
Research real GPT Image 2 prompt examples and turn rough image ideas into structured prompt packs, reference-image edit instructions, product visuals, layouts, and debugging loops. Use for prompt search, prompt rewriting, ecommerce images, readable text, posters, social creatives, character sheets, storyboards, or…
font-aesthetics
A Chinese-language visual design skill for creating concept posters where typography is the main subject. It turns words and phrases into images through letter shapes, layout, materials, and visual metaphors.
swarms
Build agents and multi-agent systems with the Swarms framework — the Agent class, tools, autonomous loops, memory, and the 15+ multi-agent architectures (SequentialWorkflow, ConcurrentWorkflow, GraphWorkflow, HierarchicalSwarm, SwarmRouter, and more). Use whenever writing, reviewing, or debugging code that imports…