首页龙虾技能列表 › xAI / Grok — 技能工具

xAI / Grok — 技能工具

v1.0.2

[自动翻译] Chat with Grok models via xAI API. Supports Grok-3, Grok-3-mini, vision, and more.

15· 10,264·7 当前·8 累计·💬 3
下载技能包
License
MIT-0
最后更新
2026/4/10
安全扫描
VirusTotal
可疑
查看报告
OpenClaw
安全
high confidence
The skill's code, runtime instructions, and required environment variables are consistent with a Grok/xAI client: it only needs node and an XAI_API_KEY and talks to api.x.ai for chat, vision, and X search functionality.
评估建议
This skill appears coherent and limited to acting as an xAI/Grok client. Before installing: (1) confirm you trust the skill source (the repository owner is unknown here); (2) only provide a dedicated xAI API key (avoid reusing broad or admin keys) and consider key rotation; (3) review the bundled scripts yourself if you have doubts — they read any image path you pass (so avoid sending sensitive images); (4) be aware network requests go to api.x.ai (inspect network policy if you require allowlist...
详细分析 ▾
用途与能力
The name/description (xAI / Grok) aligns with the included scripts: chat.js, models.js, and search-x.js. Requested binary (node) and primary env var (XAI_API_KEY) are exactly what a client for xAI would need.
指令范围
SKILL.md and the scripts limit behavior to sending prompts/images to api.x.ai and listing models; image uploads are constrained to specific extensions. The scripts do not read arbitrary config files or extra environment variables beyond XAI_API_KEY/XAI_MODEL. There are no instructions to transmit data to endpoints other than api.x.ai.
安装机制
No install spec — code files are bundled and executed via node. No downloads or archive extraction are performed by the skill itself; risk from installation is low.
凭证需求
Only XAI_API_KEY (and optional XAI_MODEL) are required. These credentials are proportional and necessary for the described functionality; no unrelated secrets or config paths are requested.
持久化与权限
The skill does not request always:true and declares disable-model-invocation:true (no autonomous invocation). It does not modify other skills or system-wide config and does not persist credentials itself.
安全有层次,运行前请审查代码。

License

MIT-0

可自由使用、修改和再分发,无需署名。

运行时依赖

无特殊依赖

版本

latestv1.0.22026/2/21

- Added a prominent link to external installation and use instructions at the top of the setup section. - No changes to functionality or commands; documentation update only.

● 可疑

安装命令 点击复制

官方npx clawhub@latest install x-ai
镜像加速npx clawhub@latest install x-ai --registry https://www.longxiaskill.com

技能文档

Chat with xAI's Grok models. Supports text and vision.

Setup

INSTALLATION AND USE INSTRUCTIONS

export XAI_API_KEY="xai-YOUR-KEY"

Get your API key at: https://console.x.ai

Commands

Chat with Grok

node {baseDir}/scripts/chat.js "What is the meaning of life?"

Use a specific model

node {baseDir}/scripts/chat.js --model grok-3-mini "Quick question: 2+2?"

Vision (analyze images)

node {baseDir}/scripts/chat.js --image /path/to/image.jpg "What's in this image?"

🔍 Search X/Twitter (Real-time!)

node {baseDir}/scripts/search-x.js "Remotion video framework"
node {baseDir}/scripts/search-x.js --days 7 "Claude AI tips"
node {baseDir}/scripts/search-x.js --handles @remotion_dev "updates"

Uses xAI Responses API with x_search tool for real X posts with citations.

List available models

node {baseDir}/scripts/models.js

Available Models

  • grok-3 - Most capable, best for complex tasks
  • grok-3-mini - Fast and efficient
  • grok-3-fast - Optimized for speed
  • grok-2-vision-1212 - Vision model for image understanding

Example Usage

User: "Ask Grok what it thinks about AI safety" Action: Run chat.js with the prompt

User: "Use Grok to analyze this image" (with attached image) Action: Run chat.js with --image flag

User: "What Grok models are available?" Action: Run models.js

API Reference

xAI API Docs: https://docs.x.ai/api

Environment Variables

  • XAI_API_KEY - Your xAI API key (required)
  • XAI_MODEL - Default model (optional, defaults to grok-3)

Security & Permissions

What this skill does:

  • Sends chat prompts to xAI's API at api.x.ai
  • Vision mode sends images to xAI for analysis
  • scripts/models.js lists available models (read-only)

What this skill does NOT do:

  • Does not read arbitrary local files — --image only accepts files with image extensions (.jpg, .jpeg, .png, .gif, .webp)
  • Does not read config files or access the filesystem beyond the specified image path
  • Does not store conversation history or logs
  • Does not send credentials to any endpoint other than api.x.ai
  • Cannot be invoked autonomously by the agent (disable-model-invocation: true)

Bundled scripts: scripts/chat.js (chat), scripts/models.js (list models), scripts/search-x.js (X search)

Review scripts before first use to verify behavior.

数据来源:ClawHub ↗ · 中文优化:龙虾技能库
OpenClaw 技能定制 / 插件定制 / 私有工作流定制

免费技能或插件可能存在安全风险,如需更匹配、更安全的方案,建议联系付费定制

了解定制服务