content / skill
GPT-Image2 Prompt System
A GPT-Image2 prompt case gallery and template library, with an agent skill for choosing image styles, templates, categories and scene tags.
At a glance
- Purpose
- A GPT-Image2 prompt case gallery and template library, with an agent skill for choosing image styles, templates, categories and scene tags.
- Runs in
- Local agent with shell, Web service
- Operating systems
- Not stated
- Needs
- Runtime: Not stated; Needs internet: Yes; Needs accounts or API keys beyond your agent: Not stated
- Files and data
- Reads files: Not stated; Writes files: Yes; Sends data to other services: Yes
- Tool type
- Skill
- Delivery
- From GitHub
- Version
- Latest on the main branch
- Access
- Code on GitHub
- Compatibility
- According to the README: Claude Code, Codex, Cursor and other tools supported by the skills package. The README says the npm CLI's install all command writes the skill to local folders used by Codex and Claude Code. A Claude Code plugin marketplace entry is also offered.
- External costs
- The repository is MIT-licensed. The README describes APIMart generation, platform credits, membership plans, credit packs and a paid community, with website billing configured through Stripe and Alipay. The README identifies APIMart as a project sponsor and links to it through an affiliate registration link. The README also advertises sponsored API services with usage-based charges, subscriptions or paid storage. Your coding agent or model provider may charge for usage.
- Permissions
- The skill acts through your coding agent with the access you give it. The README shows a global skills installation and global npm package installations. The README says install all writes into ~/.codex/skills, ~/.claude/skills and ~/.agents/skills. The README describes website generation using a personal browser-only APIMart API key or signed-in access through Supabase and a server-side APIMart key. The README's website setup includes applying Supabase migrations, configuring authentication redirects and providers, installing server-side service and billing keys, configuring a Stripe webhook, and granting Google Analytics analytics.readonly access through an OAuth browser flow. The README says Supabase service-role and Stripe keys belong in server-side environment variables.
- Usage terms
- MIT License, as stated in the repository. See its LICENSE file for the exact terms. The README says third-party prompt and image copyright belongs to the original authors or platforms, and references source licences such as CC BY 4.0 and applicable platform rules. The README says to obtain authorization from the original rights holder before commercial use of third-party content.
Code on GitHub
freestylefly/awesome-gpt-image-2
MITPrompt as Code | GPT Image 2 / 2.5 提示词与案例库，530+ 个案例、20+ 套工业级模板与可复用 Skills，新增 2.5 同提示词对比专区，附完整提示词与生成记录，持续更新。
Topics: agents ai-image-generation chatgpt dsh-plugin gpt-image-2 image-prompts prompt-as-code prompt-engineering
Public GitHub data fetched · 0 days old
Skill folders in this repository (1)
Folders that contain a SKILL.md file, from GitHub's file list on .
What it does
This repository is a GPT-Image2 prompt gallery and template library. The README describes organizing community examples into structured prompts for agents and automation workflows. The README presents case categories including UI and interfaces, posters and typography, products and e-commerce, and photography. The README points to docs/templates.md for template text and a pitfalls guide.The README describes GPT-Image2 Style Library as an agent skill for choosing styles, templates, categories and scene tags from the website's data. The README gives the example request: Use gpt-image-2-style-library to create an infographic prompt about Codex.
The README describes a visual website for browsing cases, copying prompts and trying generation after Google sign-in. The README also describes a separate GPT Image 2.5 spotlight with shared-prompt comparisons and says it does not add live 2.5 image generation. The README's website setup covers authentication, credits and payments separately from skill installation.
Who it is for
People who write GPT-Image2 image prompts and use a coding agent such as Claude Code or Codex to pick styles and templates.Example tasks
Use gpt-image-2-style-library to create an infographic prompt about CodexBrowse the case gallery by category to find a visual direction
Open a prompt template category to turn a visual direction into reusable structure
Install the style library skill for Claude Code and Codex with the npx skills add command
Compare GPT Image 2.5 results for a shared prompt in the spotlight