Claude Image — AI skill for Claude Code
教 Claude Code/Codex 真正用好 gpt-image-2 的 skill 包 · Drop-in skill teaching agents to actually use GPT Image 2 — intent-first prompting, surgical edits, parallel batching, visual self-verification.
How to install Claude Image
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open jiangmuran/claude-image and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Image does
教 Claude Code/Codex 真正用好 gpt-image-2 的 skill 包 · Drop-in skill teaching agents to actually use GPT Image 2 — intent-first prompting, surgical edits, parallel batching, visual self-verification.
Alternatives in AI
- Free AI Courses — Interactive course teaching Product Managers how to use Claude Code effectively 2.2k ★
- Vllm Mlx — High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon 1.5k ★
- PromptEnhance — Rewrite the following prompt to be clearer, more specific, and more effective for an AI assistant 250 ★
README
Claude image
教 Claude Code、Codex 等 agent 真正用好 GPT Image 2 的 drop-in skill 包。 A drop-in skill that teaches Claude Code, Codex, and other agents to actually use GPT Image 2.
[简体中文](#简体中文) · [English](#english)
简体中文
把这玩意儿丢进 Claude Code 或 Codex,你的 agent 就能从「这是个 curl 命令,祝你好运」进化成一次到位地产出 pitch deck 幻灯片、中文海报、像素图块、写实产品图、外科手术级修图。
GPT Image 2 是 2026 年 4 月发布的——这一代是分水岭:长指令式 prompt 不再丢细节,文字渲染终于正确(中日韩通吃),自定义分辨率最长 3840px,编辑端点用 `change ONLY X / preserve Y exactly` 模式做精准局部修改。
但是问题来了:2026 年 4 月之前训练的 agent 一无所知。它们用老办法写 prompt——*"4K, ultra detailed, masterpiece, trending on artstation"*——这些词在 GPT Image 2 上要么被忽略,要么直接帮倒忙。它们粘 curl 命令而不存文件。它们生成完之后问用户"这看着对吗?",根本不自己看一眼。
这个 skill 把这些全修了。
仓库结构
gpt-image-2/
├── SKILL.md # 入口。Claude 自动加载。
├── README.md # 你正在看的这个。
├── LICENSE # MIT。
├── install.sh # Claude Code 一键安装。
├── .env.example # 两个环境变量,就这一点配置。
├── references/
│ ├── prompting.md # 7 条习惯 + 意图优先框架 + 风格词表
│ ├── use-cases.md # 10+ 复制即用模板:PPT 幻灯片、UI mockup、
│ │ # 中文海报、像素图、角色三视图、信息图、
│ │ # logo、写实摄影、修图……
│ ├── api.md # 完整参数 + 自定义分辨率约束
│ └── post-process.md # 压缩、缩放、转码 (pngquant/cwebp/avifenc)
└── scripts/
└── gpt_image.py # 零依赖 Python CLI (只用 urllib,Python 3.7+)
为什么你的 agent 真的会去调用它
三个让这玩意儿真正起作用而不是装饰品的设计:
**可发现的 description**。frontmatter 里把所有触发词都列了——"海报"、"图标"、"ppt素材"、"改图"、"draw me"、"make an image"——所以 agent 的 skill 选择器在收到图像请求时真的会触发,而不是退回去自己拼 curl。
**一个 CLI,四种能力**。生成 / 编辑 / 局部重绘 / 并行批处理都是一个脚本的子命令。鉴权、重试、b64 vs URL、multipart、文件 IO、并行批处理——都处理好了。Agent 自己手撸基本上某一项会出错。
**视觉自验证写进了工作流**。Skill 明确告诉 Claude 在把结果给用户之前自己 `Read` 一下生成的 PNG,对照 prompt 检查。再也不会出现"图给你了,你看对不对"。
安装
Claude Code(一行)
git clone https://github.com/jiangmuran/claude-image.git ~/.claude/skills/gpt-image-2 \
&& bash ~/.claude/skills/gpt-image-2/install.sh
安装脚本会问你要 API key,写到 `~/.zshrc`,可选跑一个冒烟测试。
装完之后下
Related Skills
Viewtrace AI
See how your coding agent actually worked. A tiny local CLI that turns Claude Code / Codex sessions into fligh
Andrej Karpathy Guideline For AI Coding
Andrej Karpathy-inspired guidelines for Codex and Claude Code that reduce common LLM coding mistakes through c
Sv Edits
SV Edits. Free Photoshop, Illustrator and Premiere by prompting: SV Academy's skill for the open source Craft
Prompting Skill
Portable skill for building reliable LLM prompts. Drop-in for agentic-stack.
Hermes
Multi-agent execution on Claude Code — no theater, just work. Most agent frameworks fake parallelism by prompt
AI Ad Prompt Guide
Universal prompting framework for AI video and image generation — works across all major models. ---
Related Agents
GPT Astra High
External worker: gpt-6-astra at high effort, running in the codex CLI. Give it a self-contained brief with goa
GPT Image Prompter
Prompt engineer for the Codex image generator (gptimage skill, ChatGPT subscription). Turns image ideas — ofte
Report Reviser
Make targeted edits to an existing research report based on a structured issues list. Uses Edit (not Write) to