基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/tomevault-io/skills-registry --skill openai-images命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
| name | openai-images |
| description | Generate images via OpenAI's DALL-E and GPT Image APIs. Use when this capability is needed. |
| metadata | {"author":"aidiss"} |
Generate images using DALL-E 3, DALL-E 2, or GPT Image models.
curl -s https://api.openai.com/v1/images/generations \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "dall-e-3",
"prompt": "A white siamese cat",
"n": 1,
"size": "1024x1024"
}' | jq -r '.data[0].url'
Download the image:
URL=$(curl -s https://api.openai.com/v1/images/generations \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "dall-e-3",
"prompt": "A futuristic cityscape at sunset",
"n": 1,
"size": "1792x1024",
"quality": "hd"
}' | jq -r '.data[0].url')
curl -s "$URL" -o image.png
| Parameter | Values | Default |
|---|---|---|
| size | 1024x1024, 1792x1024, 1024x1792 | 1024x1024 |
| quality | standard, hd | standard |
| style | vivid, natural | vivid |
| n | 1 only | 1 |
HD quality example:
curl -s https://api.openai.com/v1/images/generations \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "dall-e-3",
"prompt": "Detailed oil painting of a mountain landscape",
"size": "1792x1024",
"quality": "hd",
"style": "natural"
}' | jq -r '.data[0].url'
Supports multiple images per request:
curl -s https://api.openai.com/v1/images/generations \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "dall-e-2",
"prompt": "A cute robot",
"n": 4,
"size": "512x512"
}' | jq -r '.data[].url'
DALL-E 2 sizes: 256x256, 512x512, 1024x1024
Create variations of an existing image:
curl -s https://api.openai.com/v1/images/variations \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-F image="@original.png" \
-F n=2 \
-F size="1024x1024" | jq -r '.data[].url'
Edit an image with a mask:
curl -s https://api.openai.com/v1/images/edits \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-F image="@original.png" \
-F mask="@mask.png" \
-F prompt="A sunlit indoor lounge area with a pool" \
-F n=1 \
-F size="1024x1024" | jq -r '.data[0].url'
Get image as base64 instead of URL:
curl -s https://api.openai.com/v1/images/generations \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "dall-e-3",
"prompt": "A simple icon",
"response_format": "b64_json"
}' | jq -r '.data[0].b64_json' | base64 -d > image.png
revised_prompt in responseConverted and distributed by TomeVault — claim your Tome and manage your conversions.
| Use when this capability is needed.
> Use when this capability is needed.
Review architecture and API design for the vfs-s3 project. Use when the user mentions @architect, asks to review an issue's design, discuss module boundaries, API shape, or architectural decisions for vfs-s3. Also trigger when the user wants to create an ADR (Architecture Decision Record) or evaluate a technical approach for the project. Intended for dispatch from Codex automation or Claude routines; GitHub trigger phrase: @vfs-s3-bot please prepare design doc Use when this capability is needed.