Agent skill

Gpt Image 2 Prompt Engine

面向电商设计师、海报美工、品牌视觉、UI设计师、信息图编辑、商业摄影师、内容创作者等需要高质量可控出图的角色，在需要用 GPT-Image-2 生成电商主图、电影海报、信息图、品牌视觉、UI截图、古籍国风、角色IP等场景时，通过「Prompt as Code」原子化Schema+20+工业JSON模板+四步工作流，产出结构化、可复用、可批量的生图提示词，再调用 imagegeneration…

MITAuto-check passedMedia & Creative

Install Gpt Image 2 Prompt Engine

skills CLI

$ npx skills add anbeime/skill --skill gpt-image-2-prompt-engine -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install anbeime/skill gpt-image-2-prompt-engine --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/anbeime/skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/gpt-image-2-prompt-engine .claude/skills/gpt-image-2-prompt-engine && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "gpt-image-2-prompt-engine" agent skill from https://github.com/anbeime/skill/tree/main/skills/gpt-image-2-prompt-engine into .claude/skills/gpt-image-2-prompt-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-prompt-engine", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/anbeime/skill/tree/main/skills/gpt-image-2-prompt-engine

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add anbeime/skill --skill gpt-image-2-prompt-engine -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install anbeime/skill gpt-image-2-prompt-engine --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/anbeime/skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/gpt-image-2-prompt-engine .agents/skills/gpt-image-2-prompt-engine && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "gpt-image-2-prompt-engine" agent skill from https://github.com/anbeime/skill/tree/main/skills/gpt-image-2-prompt-engine into .agents/skills/gpt-image-2-prompt-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-prompt-engine", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add anbeime/skill --skill gpt-image-2-prompt-engine -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install anbeime/skill gpt-image-2-prompt-engine --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/anbeime/skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/gpt-image-2-prompt-engine .cursor/skills/gpt-image-2-prompt-engine && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "gpt-image-2-prompt-engine" agent skill from https://github.com/anbeime/skill/tree/main/skills/gpt-image-2-prompt-engine into .cursor/skills/gpt-image-2-prompt-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-prompt-engine", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/anbeime/skill.git --path skills/gpt-image-2-prompt-engine

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add anbeime/skill --skill gpt-image-2-prompt-engine -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install anbeime/skill gpt-image-2-prompt-engine --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/anbeime/skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/gpt-image-2-prompt-engine .gemini/skills/gpt-image-2-prompt-engine && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "gpt-image-2-prompt-engine" agent skill from https://github.com/anbeime/skill/tree/main/skills/gpt-image-2-prompt-engine into .gemini/skills/gpt-image-2-prompt-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-prompt-engine", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install anbeime/skill gpt-image-2-prompt-engine

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add anbeime/skill --skill gpt-image-2-prompt-engine -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/anbeime/skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/gpt-image-2-prompt-engine .github/skills/gpt-image-2-prompt-engine && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "gpt-image-2-prompt-engine" agent skill from https://github.com/anbeime/skill/tree/main/skills/gpt-image-2-prompt-engine into .github/skills/gpt-image-2-prompt-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-prompt-engine", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add anbeime/skill --skill gpt-image-2-prompt-engine -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install anbeime/skill gpt-image-2-prompt-engine --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/anbeime/skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/gpt-image-2-prompt-engine .opencode/skills/gpt-image-2-prompt-engine && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "gpt-image-2-prompt-engine" agent skill from https://github.com/anbeime/skill/tree/main/skills/gpt-image-2-prompt-engine into .opencode/skills/gpt-image-2-prompt-engine/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gpt-image-2-prompt-engine", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: gpt-image-2-prompt-engine
GitHub stars: 7.8k
Token cost: ~1.4k tokens
SKILL.md length: 245 words
Files: 3 (incl. scripts, references)
Skills in repo: 62
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Works in 4 steps: ：选类别 → ：检索案例（抄结构） → ：套模板填变量 → …
Tasks that involve Image generation
SKILL.md covers 任务目标, 核心方法论：Prompt as Code, 四步工作流 and 5 个稳定性实测技巧, plus 3 more sections
Runs Python scripts from its folder; calls python3

What it does

Gpt Image 2 Prompt Engine is an agent skill from anbeime/skill. 面向电商设计师、海报美工、品牌视觉、UI设计师、信息图编辑、商业摄影师、内容创作者等需要高质量可控出图的角色，在需要用 GPT-Image-2 生成电商主图、电影海报、信息图、品牌视觉、UI截图、古籍国风、角色IP等场景时，通过「Prompt as Code」原子化Schema+20+工业JSON模板+四步工作流，产出结构化、可复用、可批量的生图提示词，再调用 imagegeneration 出图。不适用于随意生图或简单风景照。

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts and reference files (for example `references/style-library.md` and `scripts/query_templates.py`).

It sits in Media & Creative, covering Image generation. The repository describes itself as: 收录最全、更新最快的技能Skills商店：精选原创技能包（涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流），全部打包好可直接安装使用！同时自动抓取GitHub上万个Skills项目，按分类、更新时间、Star数量整理。The most comprehensive and frequently updated AI Agent skill… The licence is MIT.

When your agent uses it

Tasks that involve Image generation

Example prompts

“/gpt-image-2-prompt-engine”

Requirements

Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

：选类别
：检索案例（抄结构）
：套模板填变量
：生成与迭代

What it can do on your machine

Read from SKILL.md and the folder at commit db1e192. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
- python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
- raw.githubusercontent.com
- github.com
- gpt-image2.canghe.ai
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gpt Image 2 Prompt Engine loads about 1.4k tokens when it runs, and up to ~8k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 245 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~61
When it runs · the whole SKILL.md, loaded when a task matches: ~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from anbeime/skill at commit db1e192, republished under its MIT licence (© anbeime). 245 words, ~1,427 tokens.

Download SKILL.mdSave it as .claude/skills/gpt-image-2-prompt-engine/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: gpt-image-2-prompt-engine
description: 面向电商设计师、海报美工、品牌视觉、UI设计师、信息图编辑、商业摄影师、内容创作者等需要高质量可控出图的角色，在需要用 GPT-Image-2 生成电商主图、电影海报、信息图、品牌视觉、UI截图、古籍国风、角色IP等场景时，通过「Prompt as Code」原子化Schema+20+工业JSON模板+四步工作流，产出结构化、可复用、可批量的生图提示词，再调用 image_generation 出图。不适用于随意生图或简单风景照。
version: 1.0.0
author: anbeime
tags: gpt-image-2, prompt-engineering, image-generation, 提示词工程, 电商设计, 海报, 信息图, 品牌视觉
license: MIT

GPT-Image-2 Prompt Engine

基于 freestylefly/awesome-gpt-image-2（⭐18k+，MIT）工业级提示词引擎方法论，沉淀为可执行的生图提示词构造工作流。

任务目标

本技能用于：将模糊的出图需求转化为 GPT-Image-2 可稳定执行的结构化提示词
能力包含：
1. 原子化 Schema 拆解：Subject / Composition / Material / Typography / Lighting / Style / Constraints 七大维度
2. 20+ 工业级 JSON 模板：覆盖 UI截图、信息图、海报、电商主图、品牌视觉、商业摄影、角色IP、古籍国风、叙事插画等场景
3. 四步工作流：选类别 → 检索案例（抄结构）→ 套模板填变量 → 生成与图生图迭代
4. 5 个稳定性实测技巧：文字锁定、比例前置、模块限量、平台特征区分、负向约束
触发条件：
- ✅ 电商主图/详情页、电影/活动海报、信息图/知识图谱、品牌视觉、UI截图、商业摄影、角色/IP设计、叙事插画、古籍国风、3D渲染
- ❌ 随意生图、简单风景照、不需要精确控制的随手画 → 走基础 image_generation

核心方法论：Prompt as Code

万能结构公式

[主体与任务] + [构图与布局] + [视觉风格与材质] + [文字与标签要求] + [比例与输出格式] + [约束与负向细节]

原子化 Schema

维度	字段	说明	示例
Subject	主体	画面核心对象，越具体越好	"一瓶30ml透明玻璃香水瓶，金色瓶盖"
Composition	构图	布局、视角、景别	"居中对称，45度俯拍，浅景深"
Material	材质	物体表面质感与触感	"磨砂玻璃，金属反光，水滴凝结"
Typography	文字	画面中文字内容、字体、位置	"标题'限时特惠'，粗黑体，左上角"
Lighting	光线	光源方向、色温、氛围	"柔和侧逆光，暖色调，丁达尔效应"
Style	风格	整体视觉调性	"高端商业摄影，极简白底，8K"
Constraints	约束	负向提示与硬性限制	"禁止乱码文字，禁止多余手指，9:16"

四步工作流

Step 1：选类别

根据用户需求匹配模板类别：

类别	模板ID	适用场景
UI与界面	`ui-screenshot-system`	App截图、仪表盘、社媒截图、直播界面
图表与信息可视化	`infographic-engine`	解释图、技术图解、时间线、知识卡片
科学尺度图	`scientific-scale-diagram`	微观到宏观的尺度递进图
海报与排版	`poster-campaign`	活动海报、电影海报、概念字体海报
电商主图	`ecommerce-hero`	产品主图、详情页banner、带货图
品牌视觉	`brand-identity`	品牌KV、VI应用、包装设计
商业摄影	`commercial-photo`	产品静物、人像、美食摄影
角色与IP	`character-design`	角色设定、IP形象、表情包
叙事插画	`narrative-illustration`	故事场景、绘本、编辑插画
古籍国风	`classical-chinese`	国画、工笔、水墨、敦煌风格

Step 2：检索案例（抄结构）

使用 scripts/query_templates.py 检索本地克隆仓库的模板与案例：

bash

python3 scripts/query_templates.py --category ecommerce
python3 scripts/query_templates.py --keyword "香水 海报"

未克隆仓库时，脚本会优雅降级，输出在线 raw 链接：

也可直接 web_fetch 上述链接获取最新案例。

Step 3：套模板填变量

选择匹配的 JSON 模板，将用户需求填入变量。以下为 3 个核心模板示例：

模板A：信息图

json

{
  "type": "Infographic",
  "topic": "<主题，明确具体>",
  "audience": "<目标读者>",
  "structure": {
    "title_area": "<主标题>",
    "layout": "<布局描述，如：等距切角，N个编号面板>",
    "modules": [
      {"title": "<模块1>", "icon": "<图标名>", "text": "<1-2句说明>"},
      {"title": "<模块2>", "icon": "<图标名>", "text": "<1-2句说明>"}
    ]
  },
  "style": {
    "aesthetic": "<风格，如：科学图鉴/扁平插画/商务报告>",
    "colors": "<配色方案>",
    "background": "<背景>"
  },
  "constraints": "No gibberish text, strict structural layout, <比例>"
}

模板B：电影/活动海报

json

{
  "type": "Poster",
  "subject": "<主体描述>",
  "title": {
    "text": "<标题，必须精确显示>",
    "style": "<字体风格，如：粗黑体/书法体/衬线体>",
    "position": "<位置，如：居中/底部/对角>"
  },
  "composition": "<构图描述>",
  "visual_style": "<视觉风格，如：赛博朋克/复古胶片/极简>",
  "color_palette": ["<主色>", "<辅色>", "<点缀色>"],
  "mood": "<情绪关键词>",
  "constraints": "Title must be spelled exactly, readable text, <比例>, no random text"
}

模板C：电商主图

json

{
  "type": "Ecommerce",
  "product": {
    "name": "<产品名>",
    "material": "<材质>",
    "color": "<颜色>",
    "key_feature": "<核心卖点>"
  },
  "scene": "<使用场景/背景>",
  "composition": "<构图，如：居中45度俯拍>",
  "lighting": "<光线描述>",
  "style": "<风格，如：高端商业摄影/极简白底/生活方式>",
  "text_overlay": {
    "headline": "<主文案>",
    "subtext": "<副文案>",
    "position": "<位置>"
  },
  "constraints": "Product must be accurate, readable text, <比例>, no watermark"
}

Step 4：生成与迭代

将填好变量的 JSON 转为自然语言提示词
调用 image_generation 出图（中文需求用中文提示词，英文需求用英文）
检查出图结果：文字是否准确、构图是否符合、比例是否正确
不满足则调整对应 Schema 维度后重新生成（图生图模式可传入参考图）

5 个稳定性实测技巧

文字锁定：凡是画面中有文字，必须写"文字必须准确显示指定内容，禁止乱码和占位文本"，并把原文逐字写出
比例前置：宽高比写在提示词最前面或 constraints 第一条，否则模型默认出 1:1 或 9:16
模块限量：信息图先锁定 3-5 个模块再补细节，模块过多必然混乱
平台特征区分：UI截图必须指定平台（iOS/Android/小红书/抖音），各平台状态栏、Tab、交互元素差异大
负向约束具体化：不要只写"no artifacts"，要写"禁止多余手指""禁止乱码按钮""禁止产品变形"

使用方式

输入

参数	类型	必填	说明
category	string	是	出图类别：ui/infographic/poster/ecommerce/brand/photo/character/narrative/classical
subject	string	是	主体描述
style	string	否	视觉风格偏好
aspect_ratio	string	否	宽高比（默认 1:1）
text_content	string	否	画面中需要显示的文字
reference_image	string	否	参考图路径/URL（图生图模式）
extra_constraints	string	否	额外约束

输出

一份结构化的 GPT-Image-2 提示词（可直接复制使用）
对应的 JSON Schema（可复用/批量修改）
选中的模板名称和参考案例ID
负向约束清单

资源引用

上游项目：freestylefly/awesome-gpt-image-2（⭐18k+，MIT License）
在线画廊：https://gpt-image2.canghe.ai
npm 包：gpt-image-2-style-library
完整模板库：references/style-library.md（20+ 模板详细索引）
案例库：530+ 逆向工程案例，见上游 docs/gallery.md

⚠️ 第三方案例商用授权提示：本技能引用的案例仅供学习参考，商用前请确认对应案例的授权范围。

注意事项

本技能不新增生图工具，出图仍需调用 image_generation 技能
中文需求默认输出中文提示词，英文需求输出英文提示词
批量生成时复用同一模板，仅变更 subject / composition / palette
仓库克隆被 403 拦截时，以在线 raw 链接检索为主路径

Files

SKILL.md and 2 other files (scripts, references) in skills/gpt-image-2-prompt-engine of anbeime/skill.

SKILL.md
references/style-library.md
scripts/query_templates.py

Open the folder on GitHubat commit db1e192

Compare with similar skills

Gpt Image 2 Prompt Engine next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gpt Image 2 Prompt Engine compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Gpt Image 2 Prompt Engine this skillanbeime/skill	7.8k	—	~1.4k	Automated safety check: Pass	MIT	yesterday
AI Image Generation and Editingzhayujie/CowAgent	47k	—	~1.3k	Automated safety check: Pass	MIT	today
Structured Image Generationbytedance/deer-flow	84k	4 repos	~2.9k	Automated safety check: Pass	MIT	today
Canghe Comicfreestylefly/canghe-skills	461	8 repos	~3.2k	Automated safety check: Pass	None	4 mo ago
Generate Imageynulihao/AgentSkillOS	618	10 repos	~1.7k	Automated safety check: Notes	None	7 mo ago
GPT Image Generation CLIwuyoscar/GPT-Image2-Skill	5.7k	—	~2.5k	Automated safety check: Notes	MIT	10 days ago

Similar skills

AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
47k GitHub stars~1.3k tokensUpdated today
Media & CreativeAuto-check passed
Structured Image Generation
bytedance/deer-flow
Turns an image request into a structured JSON prompt and runs a bundled Python script to generate the picture, optionally guided by reference images.
84k GitHub starsUsed in 4 repos~2.9k tokens
Media & CreativeAuto-check passed
Canghe Comic
freestylefly/canghe-skills
Knowledge comic creator supporting multiple art styles and tones.
461 GitHub starsUsed in 8 repos~3.2k tokens
Media & CreativeAuto-check passed
Generate Image
ynulihao/AgentSkillOS
Generate or edit images using AI models (FLUX, Gemini). An agent skill from ynulihao/AgentSkillOS.
618 GitHub starsUsed in 10 repos~1.7k tokens
Media & CreativeAuto-check: notes
GPT Image Generation CLI
wuyoscar/GPT-Image2-Skill
Generates and edits images with GPT Image 2 or 2.5 through a packaged CLI and a prompt gallery, after settling which model fits the request.
5.7k GitHub stars~2.5k tokensUpdated 10 days ago
Media & CreativeAuto-check: notes
Minimal Zine Poster Generator
LiamGvchi/gc-minimal-zine-poster
Creates or analyzes quiet, paper-texture zine posters with big negative space, one color accent and experimental type, returning an image prompt and the generated poster.
7.3k GitHub stars~2.9k tokensUpdated 1 mo ago
Media & CreativeAuto-check passed

Questions about Gpt Image 2 Prompt Engine

What does Gpt Image 2 Prompt Engine do?

When should I use Gpt Image 2 Prompt Engine?

Gpt Image 2 Prompt Engine fits situations like: tasks that involve Image generation.

How do I install Gpt Image 2 Prompt Engine in Claude Code?

Run `npx skills add anbeime/skill --skill gpt-image-2-prompt-engine -a claude-code`. Or copy the skill folder (skills/gpt-image-2-prompt-engine in anbeime/skill) into .claude/skills/gpt-image-2-prompt-engine in your project. Claude Code loads it when a task matches its description.

How do I install Gpt Image 2 Prompt Engine in Codex?

Run `npx skills add anbeime/skill --skill gpt-image-2-prompt-engine -a codex`. Or copy the skill folder (skills/gpt-image-2-prompt-engine in anbeime/skill) into .agents/skills/gpt-image-2-prompt-engine in your project. Codex loads it when a task matches its description.

Can I use Gpt Image 2 Prompt Engine in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anbeime/skill --skill gpt-image-2-prompt-engine -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gpt-image-2-prompt-engine, .gemini/skills/gpt-image-2-prompt-engine, .github/skills/gpt-image-2-prompt-engine and .opencode/skills/gpt-image-2-prompt-engine in your project.

What does Gpt Image 2 Prompt Engine need to run?

Going by SKILL.md and its folder, Gpt Image 2 Prompt Engine needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Gpt Image 2 Prompt Engine access the network?

SKILL.md names 3 domains. As links in the text: raw.githubusercontent.com, github.com and gpt-image2.canghe.ai. This is read from the text; nothing was executed.

Is Gpt Image 2 Prompt Engine safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Gpt Image 2 Prompt Engine use?

Gpt Image 2 Prompt Engine is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gpt Image 2 Prompt Engine use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.6k tokens, read only when the agent opens those files.

What are the alternatives to Gpt Image 2 Prompt Engine?

Skills that share tags, products or a category with Gpt Image 2 Prompt Engine: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Structured Image Generation (bytedance/deer-flow, 84k stars), Canghe Comic (freestylefly/canghe-skills, 461 stars) and Generate Image (ynulihao/AgentSkillOS, 618 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gpt Image 2 Prompt Engine?

anbeime (a GitHub user) maintains it in anbeime/skill, which has 7,760 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 9, 2026.

Source: anbeime/skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Gpt Image 2 Prompt Engine

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

GPT-Image-2 Prompt Engine

任务目标

核心方法论：Prompt as Code

万能结构公式

原子化 Schema

四步工作流

Step 1：选类别

Step 2：检索案例（抄结构）

Step 3：套模板填变量

模板A：信息图

模板B：电影/活动海报

模板C：电商主图

Step 4：生成与迭代

5 个稳定性实测技巧

使用方式

输入

输出

资源引用

注意事项

Files

Compare with similar skills

Similar skills

More from anbeime/skill

Related

Questions about Gpt Image 2 Prompt Engine