Token导航 LogoToken导航

Agent Skill · 研究检索

google-chat(Google Chat 搜索)

google-chat 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

google-chat 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证为 MIT,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 4,739。

总安装 30,045周安装 785GitHub Stars 公开资料未说明下载 10,383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

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:google-chat(Google Chat 搜索)
来源仓库:https://github.com/clawdbot/skills
仓库路径:skills/google-chat
安装命令:
npx skills add clawdbot/skills --skill "google-chat"
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 npx skills 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。

AgentSkills.tonpx skills
npx skills add clawdbot/skills --skill "google-chat"

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

google-chat 用于查找、检索和筛选相关信息。适合在需要根据关键词或任务场景快速定位候选结果时使用。可结合来源仓库和原始 README 核验具体用法。google-chat 属于研究检索类 Skill,可作为该场景下的辅助能力补充。安装方式:通过 npx 从 clawdbot/skills 仓库添加技能。

注意:建议确认权限范围、维护状态及是否触发联网或命令执行。

来源仓库内路径:skills/google-chat

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 Codex、Claude、Cursor、Gemini CLI;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 npx skills add clawdbot/skills --skill "google-chat";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

google-chat 怎么安装?

在终端执行 npx skills add clawdbot/skills --skill "google-chat"。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

google-chat 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。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。

google-chat 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。

google-chat 是免费的吗?

来源标注的许可证是 MIT。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。

google-chat 用的人多吗?

公开数据是累计安装 30,045 次,近一周安装 785 次,下载 10,383 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。

google-chat 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 许可证明确为 MIT,商用和分发边界好判断。

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。
  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 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 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

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。
  • 要求有安全扫描结论才肯安装的团队。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
google-chat

Google Chat 搜索 · 本页

30,045—接触敏感数据MIT未收录

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
google-chat
description
Send messages to Google Chat spaces and users via webhooks or OAuth. Use when you need to send notifications, alerts, or messages to Google Chat channels (spaces) or direct messages to specific users. Supports both incoming webhooks (for predefined channels) and OAuth 2.0 (for dynamic messaging to any space or user).

Google Chat Messaging

Send messages to Google Chat using two methods:

  1. Webhooks - Fast, pre-configured channels (messages appear as a bot)
  2. OAuth - Dynamic messaging to any space or user (requires authentication)

Quick Start

Method 1: Webhooks (Recommended for Known Channels)

Send to a pre-configured channel:

python3 scripts/send_webhook.py "$WEBHOOK_URL" "Your message here"

Example with threading:

python3 scripts/send_webhook.py "$WEBHOOK_URL" "Reply message" --thread_key "unique-thread-id"

Configuration: Store webhooks in google-chat-config.json:

{
  "webhooks": {
    "acs_engineering_network": "https://chat.googleapis.com/v1/spaces/...",
    "general": "https://chat.googleapis.com/v1/spaces/..."
  }
}

Read config and send:

WEBHOOK_URL=$(jq -r '.webhooks.acs_engineering_network' google-chat-config.json)
python3 scripts/send_webhook.py "$WEBHOOK_URL" "Deploy completed ✅"

Method 2: OAuth (For Dynamic Messaging)

First-time setup:

  1. Save OAuth credentials to a file (e.g., google-chat-oauth-credentials.json)
  2. Run initial authentication (opens browser, saves token):
python3 scripts/send_oauth.py \
  --credentials google-chat-oauth-credentials.json \
  --token google-chat-token.json \
  --space "General" \
  "Test message"

Send to a space by name:

python3 scripts/send_oauth.py \
  --credentials google-chat-oauth-credentials.json \
  --token google-chat-token.json \
  --space "Engineering Network" \
  "Deploy completed"

Note: OAuth messages automatically include 🤖 emoji prefix. Use --no-emoji to disable this:

python3 scripts/send_oauth.py \
  --credentials google-chat-oauth-credentials.json \
  --token google-chat-token.json \
  --space "Engineering Network" \
  "Message without emoji" \
  --no-emoji

List available spaces:

python3 scripts/send_oauth.py \
  --credentials google-chat-oauth-credentials.json \
  --token google-chat-token.json \
  --list-spaces

Send to a DM (requires existing space ID):

# Note: Google Chat API doesn't support creating new DMs by email
# You need the space ID of an existing DM conversation
python3 scripts/send_oauth.py \
  --credentials google-chat-oauth-credentials.json \
  --token google-chat-token.json \
  --space-id "spaces/xxxxx" \
  "The report is ready"

Send to space by ID (faster):

python3 scripts/send_oauth.py \
  --credentials google-chat-oauth-credentials.json \
  --token google-chat-token.json \
  --space-id "spaces/AAAALtlqgVA" \
  "Direct message to space"

Dependencies

Install required Python packages:

pip install google-auth-oauthlib google-auth-httplib2 google-api-python-client

Required OAuth Scopes:

  • https://www.googleapis.com/auth/chat.messages - Send messages
  • https://www.googleapis.com/auth/chat.spaces - Access space information
  • https://www.googleapis.com/auth/chat.memberships.readonly - List space members (for DM identification)

OAuth Setup Guide

If OAuth credentials don't exist yet:

  1. Go to Google Cloud Console
  2. Select your project or create one
  3. Enable Google Chat API
  4. Go to APIs & Services → Credentials
  5. Create OAuth 2.0 Client ID (Desktop app type)
  6. Download JSON and save as google-chat-oauth-credentials.json

The credentials JSON should look like:

{
  "installed": {
    "client_id": "...apps.googleusercontent.com",
    "client_secret": "GOCSPX-...",
    "redirect_uris": ["http://localhost"],
    ...
  }
}

Webhook Setup Guide

To create a webhook for a Google Chat space:

  1. Open Google Chat in browser
  2. Go to the space
  3. Click space name → Apps & integrations
  4. Click Manage webhooks → Add webhook
  5. Give it a name (e.g., "Agustin Networks")
  6. Copy the webhook URL
  7. Add to google-chat-config.json

Choosing the Right Method

Use Webhooks when:

  • Sending to the same channels repeatedly
  • Messages should appear as a bot/service
  • Speed is important (no OAuth handshake)
  • Configuration is static

Use OAuth when:

  • Sending to different spaces dynamically
  • Messages should appear from your configured Google Chat App
  • Space names are determined at runtime
  • Need to list and discover available spaces

OAuth Limitations:

  • Cannot create new DMs by email address (Google Chat API restriction)
  • To send DMs, you need the space ID of an existing conversation
  • Use --list-spaces to find available DM space IDs

Message Formatting

Both methods support simple text. For advanced formatting (cards, buttons), construct JSON payloads:

Webhook with card:

import json
import urllib.request

payload = {
    "cardsV2": [{
        "cardId": "unique-card-id",
        "card": {
            "header": {"title": "Deploy Status"},
            "sections": [{
                "widgets": [{
                    "textParagraph": {"text": "Production deploy completed successfully"}
                }]
            }]
        }
    }]
}

data = json.dumps(payload).encode("utf-8")
req = urllib.request.Request(webhook_url, data=data, headers={"Content-Type": "application/json"})
urllib.request.urlopen(req)

Troubleshooting

Webhook errors:

  • Verify webhook URL is correct and active
  • Check space still exists and webhook wasn't deleted
  • Ensure message isn't empty

OAuth errors:

  • Run authentication flow again if token expired
  • Verify Google Chat API is enabled in Cloud Console
  • Check user has access to the target space
  • For DMs, ensure user email is correct and in same workspace

Permission errors:

  • Webhooks: Must be member of the space
  • OAuth: Must have access to target space or user
  • Corporate Workspace: Some features may be restricted by admin policies

Examples

Deploy notification to engineering channel:

WEBHOOK=$(jq -r '.webhooks.acs_engineering_network' google-chat-config.json)
python3 scripts/send_webhook.py "$WEBHOOK" "🚀 Production deploy v2.1.0 completed"

Alert specific user about task:

python3 scripts/send_oauth.py \
  --credentials google-chat-oauth-credentials.json \
  --token google-chat-token.json \
  --dm  [email protected]  \
  "Your report is ready for review: https://docs.company.com/report"

Thread multiple messages together (webhook):

WEBHOOK=$(jq -r '.webhooks.general' google-chat-config.json)
THREAD_KEY="deploy-$(date +%s)"

python3 scripts/send_webhook.py "$WEBHOOK" "Starting deploy..." --thread_key "$THREAD_KEY"
# ... deployment happens ...
python3 scripts/send_webhook.py "$WEBHOOK" "Deploy completed ✅" --thread_key "$THREAD_KEY"

平台分布

windsurf

32.77%
按下载量换算3,403

OpenCode

20.96%
按下载量换算2,176

Codex

20.22%
按下载量换算2,099

clawdbot

13.48%
按下载量换算1,400

Cursor

8.07%
按下载量换算838

Claude Code

3.15%
按下载量换算327

安全审计

暂无安全审计结果可展示。

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