Token导航 LogoToken导航

Agent Skill · 图像处理

grok-image-cli(grok 图像 CLI)

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制;涉及人物、品牌、商品或公开展示素材时,应额外核对授权、真实性和内容合规边界。

grok-image-cli 是图像处理类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在图像处理类的 1,562 个 Skill 里排第 91。

总安装 44,793周安装 1,812GitHub Stars 公开资料未说明下载 14,061核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
0.2.1

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:grok-image-cli(grok 图像 CLI)
来源仓库:https://github.com/cyberash-dev/grok-image-cli
安装命令:
openclaw skills install grok-image-cli
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install grok-image-cli

这个 Skill 是做什么的

图像处理类 Skill 处理生成、裁剪、压缩和批量转换图片的任务。

从命令行调用 Grok API 生成和编辑图像,支持批量处理和多种纵横比。适合在 OpenClaw 中集成到自动化脚本或批处理工作流中进行视觉素材生产。通过 clawhub 安装,安装命令为 openclaw skills install grok-image-cli,内置安全凭证存储。

使用前需验证 xAI API 密钥有效性,并关注模型输出质量和延迟表现。涉及人物、品牌或公共素材时应审慎审核结果,防止误导或声誉风险。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install grok-image-cli;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

grok-image-cli 怎么安装?

在终端执行 openclaw skills install grok-image-cli。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

grok-image-cli 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

grok-image-cli 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

grok-image-cli 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

grok-image-cli 用的人多吗?

公开数据是累计安装 44,793 次,近一周安装 1,812 次,下载 14,061 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

grok-image-cli 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理图像处理类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

图像处理类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
ai-image-generation

AI 图像生成 · Codex、Claude

4,365,552382调用外部服务未明确有提醒
openai-image-gen

OpenAI 图像生成 · OpenClaw

1,906,88432需要联网MIT-0有提醒
image

图像 · OpenClaw

525,99926需要联网MIT-0通过
baoyu-cover-image

宝玉封面图 · Codex、Claude

474,24016,779只读MIT有提醒
baoyu-image-gen

宝玉图像生成器 · Codex、Claude

468,00716,778接触敏感数据MIT通过
grok-image-cli

grok 图像 CLI · 本页

44,793—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
grok-image-cli
description
Generate and edit images via Grok API from the command line. Cross-platform secure credential storage for xAI API key. Supports batch generation, aspect ratios, and style transfer.
metadata
{"clawdbot":{"emoji":"🎨","os":["macos","windows","linux"],"requires":{"bins":["grok-img","node"],"env":{"XAI_API_KEY":{"required":false,"description":"xAI API key (fallback when no credential store entry exists)"}}},"credentials":[{"id":"xai-api-key","label":"xAI API key","storage":"cross-keychain","service":"grok-image-cli","account":"api-key","env_fallback":"XAI_API_KEY"}],"install":[{"id":"npm","kind":"shell","command":"npm install -g grok-image-cli","bins":["grok-img"],"label":"Install grok-image-cli via npm"},{"id":"source","kind":"shell","command":"git clone https://github.com/cyberash-dev/grok-image-cli.git && cd grok-image-cli && npm install && npm run build && npm link","bins":["grok-img"],"label":"Install from source (audit before running)"}],"source":"https://github.com/cyberash-dev/grok-image-cli"}}

grok-image-cli

A CLI for generating and editing images using the xAI Grok API. Supports multiple models: grok-imagine-image (default), grok-imagine-image-pro, grok-2-image-1212. Powered by the official @ai-sdk/xai SDK. Credentials are stored in the OS native credential store (macOS Keychain, Windows Credential Manager, Linux Secret Service) via cross-keychain.

Installation

Requires Node.js >= 20.19.0. Works on macOS, Windows, and Linux. The package is fully open source under the MIT license: https://github.com/cyberash-dev/grok-image-cli

npm install -g grok-image-cli

The npm package is published with provenance attestation, linking each release to its source commit via GitHub Actions. You can verify the published contents before installing:

npm pack grok-image-cli --dry-run

Install from source (if you prefer to audit the code before running):

git clone https://github.com/cyberash-dev/grok-image-cli.git
cd grok-image-cli
npm install && npm run build && npm link

After installation the grok-img command is available globally.

Quick Start

grok-img auth login                                                      # Interactive prompt: enter xAI API key
grok-img generate "A futuristic city skyline at night"                   # Generate with default model
grok-img generate "A futuristic city skyline at night" -m grok-imagine-image-pro  # Use pro model
grok-img edit "Make it a watercolor painting" -i ./photo.jpg             # Edit an existing image

API Key Management

Store API key (interactive prompt):

grok-img auth login

Show stored key (masked) and source:

grok-img auth status

Remove key from credential store:

grok-img auth logout

The CLI also supports the XAI_API_KEY environment variable as a fallback when no credential store entry is found.

Image Generation

grok-img generate "A collage of London landmarks in street-art style"
grok-img generate "Mountain landscape at sunrise" -n 4 -a 16:9
grok-img generate "A serene Japanese garden" -o ./my-images
grok-img generate "Photorealistic portrait" -m grok-imagine-image-pro
grok-img generate "Abstract art" -m grok-2-image-1212

Image Editing

Edit a local file or a remote URL:

grok-img edit "Change the landmarks to New York City" -i ./landmarks.jpg
grok-img edit "Render as a pencil sketch" -i https://example.com/portrait.jpg
grok-img edit "Add a vintage film grain effect" -i ./photo.jpg -a 3:2 -o ./edited

Flag Reference

generate

FlagDescriptionDefault
-m, --model <model>Model (grok-imagine-image, grok-imagine-image-pro, grok-2-image-1212)grok-imagine-image
-a, --aspect-ratio <ratio>Aspect ratio (1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2, 19.5:9, 9:19.5, 20:9, 9:20, auto)auto
-n, --count <number>Number of images to generate (1-10)1
-o, --output <dir>Output directory./grok-images

edit

FlagDescriptionDefault
-i, --image <path>Source image (local file path or URL)required
-m, --model <model>Model (grok-imagine-image, grok-imagine-image-pro, grok-2-image-1212)grok-imagine-image
-a, --aspect-ratio <ratio>Aspect ratioauto
-o, --output <dir>Output directory./grok-images

Security and Data Storage

The following properties are by design and can be verified in the source code:

  • xAI API key: stored in the OS native credential store via cross-keychain (macOS Keychain / Windows Credential Manager / Linux Secret Service; service: grok-image-cli, account: api-key). By design, never written to disk in plaintext. If no credential store entry is found, the CLI falls back to the XAI_API_KEY environment variable. See src/infrastructure/adapters/credential-store.adapter.ts for the implementation.
  • No config files: all settings are passed via CLI flags. Nothing is stored on disk besides the credential store entry.
  • Network: the API key is only sent to api.x.ai over HTTPS via the official @ai-sdk/xai SDK. When editing images with a remote URL (-i https://...), the SDK makes an additional outbound HTTPS request to fetch the source image. No other outbound connections are made by the CLI itself (npm/git fetches during installation are standard package manager behavior). See src/infrastructure/adapters/grok-api.adapter.ts.
  • Generated images: saved to the local output directory (default: ./grok-images). No images are cached or uploaded elsewhere.

API Reference

This CLI wraps the xAI Image Generation API via the Vercel AI SDK:

  • Generation: POST /v1/images/generations
  • Editing: POST /v1/images/edits

Documentation: https://docs.x.ai/docs/guides/image-generation

平台分布

OpenClaw

86.87%
按下载量换算12,215

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills