npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

image-studio-codex-skill

v0.1.1

Published

Cross-platform AI agent Skill and CLI for the Image-studio OpenAI-compatible Images API client

Readme

Image-studio Skill

image-studio-codex-skill 是独立、公开、跨平台的 AI Agent Skill 与 CLI,通过 OpenAI-compatible Images API 提供图像能力:

  • Windows、macOS 和 Linux 通用;
  • Node.js 20+;
  • 通过 npm 安装;
  • 通过 OpenAI-compatible Images API 调用;
  • 支持文生图、图生图、局部编辑和遮罩;
  • API key 只从本地配置、运行时环境变量或显式参数读取,不写入 npm 包;
  • 源码、安装器和 Cloudflare Worker 部署配置均在本仓库公开审查。

一键安装网站

安装页面已部署到 Cloudflare Workers,并绑定自定义域名:

https://image-studio.api-info.net/

机器可读入口(适合直接发给 AI):

https://image-studio.api-info.net/llms.txt

完整 Markdown:

https://image-studio.api-info.net/INSTALL.md

安装 CLI

发布到 npm 后:

npm install --global image-studio-codex-skill
image-studio --help

发布流程、登录、包名检查、版本升级和常见错误处理见 PUBLISHING.md。

不安装到全局也可以直接调用:

npx image-studio-codex-skill --help

安装 Codex skill

安装 npm 包后,在包目录执行:

image-studio install-skill

当前版本的 install-skill 入口也支持直接从源码目录执行:

node bin/image-studio.mjs install-skill

安装位置:

$CODEX_HOME/skills/image-studio/SKILL.md

如果没有设置 CODEX_HOME,默认使用:

  • Windows:%USERPROFILE%/.codex/skills/image-studio
  • macOS/Linux:$HOME/.codex/skills/image-studio

安装完成后重启 Codex,使 skill 被重新扫描。Skill 的完整调用约定见同目录的 SKILL.md。

API key and persistent config

不需要每次执行 $env: 或 export。推荐使用 CLI 写入用户级配置文件:

image-studio config set --api-key "你的 API key" --base-url "https://www.api-info.net/v1"
image-studio config path
image-studio config show

配置文件位置:

  • Windows:%APPDATA%\Image-studio\config.env
  • macOS:~/Library/Application Support/Image-studio/config.env
  • Linux:$XDG_CONFIG_HOME/image-studio/config.env 或 ~/.config/image-studio/config.env

如果设置了 IMAGE_STUDIO_CONFIG,则使用该路径。命令行参数优先级最高,其次是运行时环境变量,再其次是配置文件。

也可以手工维护配置文件,内容类似:

IMAGE_STUDIO_API_KEY="你的 API key"
OPENAI_BASE_URL="https://www.api-info.net/v1"
IMAGE_STUDIO_MODEL="gpt-image-2"
IMAGE_STUDIO_OUTPUT_DIR="./outputs"

macOS/Linux 环境变量写法:

export IMAGE_STUDIO_API_KEY='你的 API key'
export OPENAI_BASE_URL='https://www.api-info.net/v1'

Windows PowerShell 环境变量写法:

$env:IMAGE_STUDIO_API_KEY = '你的 API key'
$env:OPENAI_BASE_URL = 'https://www.api-info.net/v1'

不要把真实 API key 放入源码、README、截图、Git 提交或聊天记录。config show 只显示脱敏后的 key。

调用示例

image-studio health --json
image-studio models --json
image-studio generate --prompt "一间明亮的工作室,写实摄影风格" --output ./outputs/
image-studio edit --prompt "去除划痕并提高细节" --image ./old-photo.png --output ./outputs/

本地开发

npm install
npm run check
npm test
npm run pack:check
npm run site:check

本地预览和部署安装网站:

npm run site:dev
npm run site:deploy

Cloudflare Worker、自定义域名和发布说明见 docs/DEPLOYING.md。npm 发布流程见 PUBLISHING.md。