Google Chat Messages logo

Google Chat Messages

CommunityPopular
jezweb
google-chat-messages

Send Google Chat messages via incoming webhooks — text, rich cards (cardsV2), threaded replies. TypeScript types, card builder utility, widget reference inline. Use whenever the user wants to post to Google Chat from a script, build a chatbot reply, send a notification card, build a Google Chat webhook integration, or troubleshoot card / threading issues.

Overview

Publisherjezweb
Repositoryclaude-skills
Skill namegoogle-chat-messages
Stars
1K
Forks
102
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jezweb on GitHub. Read the source before you install it.

Installation

Install the Google Chat Messages AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jezweb/claude-skills.git /tmp/claude-skills
mkdir -p .claude/skills
cp -r /tmp/claude-skills/plugins/integrations/skills/google-chat-messages .claude/skills/google-chat-messages
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Chat Messages in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Google Chat Messages on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Google Chat Messages is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Google Chat Messages

Send messages to Google Chat spaces via incoming webhooks. Produces text messages, rich cards (cardsV2), and threaded replies.

What You Produce

  • Text messages with Google Chat formatting
  • Rich card messages (cardsV2) with headers, sections, widgets
  • Threaded conversations
  • Reusable webhook sender utility

Workflow

Step 1: Get Webhook URL

In Google Chat:

  1. Open a Space > click space name > Manage webhooks
  2. Create webhook (name it, optionally add avatar URL)
  3. Copy the webhook URL

Store the URL as an environment variable or in your secrets manager — never hardcode.

Step 2: Choose Message Type

NeedTypeComplexity
Simple notificationText messageLow
Structured info (status, digest)Card message (cardsV2)Medium
Ongoing updatesThreaded repliesMedium
Action buttons (open URL)Card with buttonListMedium

Step 3: Send the Message

Use assets/webhook-sender.ts for the sender utility. Use assets/card-builder.ts for structured card construction.

Text Formatting

Google Chat does NOT use standard Markdown.

FormatSyntaxExample
Bold*text**important*
Italic_text__emphasis_
Strikethrough~text~~removed~
Monospace`text``code`
Code block```text```Multi-line code
Link<url|text><https://example.com|Click here>
Mention user<users/USER_ID><users/123456>
Mention all<users/all><users/all>

Not supported: **double asterisks**, headings (###), blockquotes, tables, images inline.

Text Message Example

typescript
await sendText(webhookUrl, '*Build Complete*\n\nBranch: `main`\nStatus: Passed\n<https://ci.example.com/123|View Build>');

cardsV2 Structure

Cards use the cardsV2 format (recommended over legacy cards).

typescript
const message = {
  cardsV2: [{
    cardId: 'unique-id',
    card: {
      header: {
        title: 'Card Title',
        subtitle: 'Optional subtitle',
        imageUrl: 'https://example.com/icon.png',
        imageType: 'CIRCLE'  // or 'SQUARE'
      },
      sections: [{
        header: 'Section Title',  // optional
        widgets: [
          // widgets go here
        ]
      }]
    }
  }]
};

Widget Reference

All widget types available in cardsV2 sections.

textParagraph

Formatted text block. Supports Google Chat formatting (*bold*, _italic_, <url|text>).

typescript
{
  textParagraph: {
    text: '*Status*: All systems operational\n_Last checked_: 5 minutes ago'
  }
}

decoratedText

Labelled value with optional icons. Most versatile widget for key-value data.

Basic:

typescript
{
  decoratedText: {
    topLabel: 'Environment',
    text: 'Production',
    bottomLabel: 'Last deployed 2h ago'
  }
}

With start icon:

typescript
{
  decoratedText: {
    topLabel: 'Status',
    text: 'Healthy',
    startIcon: { knownIcon: 'STAR' }
  }
}

With custom icon URL:

typescript
{
  decoratedText: {
    topLabel: 'GitHub',
    text: 'PR #142 merged',
    startIcon: {
      iconUrl: 'https://github.githubassets.com/favicons/favicon.svg',
      altText: 'GitHub'
    }
  }
}

With button:

typescript
{
  decoratedText: {
    topLabel: 'Alert',
    text: 'CPU at 95%',
    button: {
      text: 'View',
      onClick: { openLink: { url: 'https://monitoring.example.com' } }
    }
  }
}

Clickable (whole widget):

typescript
{
  decoratedText: {
    text: 'View full report',
    wrapText: true,
    onClick: { openLink: { url: 'https://reports.example.com' } }
  }
}

With wrap text:

typescript
{
  decoratedText: {
    topLabel: 'Description',
    text: 'This is a longer description that should wrap to multiple lines instead of being truncated',
    wrapText: true
  }
}

buttonList

One or more action buttons. Buttons open URLs or trigger actions.

Single button:

typescript
{
  buttonList: {
    buttons: [{
      text: 'Open Dashboard',
      onClick: { openLink: { url: 'https://dashboard.example.com' } }
    }]
  }
}

Multiple buttons:

typescript
{
  buttonList: {
    buttons: [
      {
        text: 'Approve',
        onClick: { openLink: { url: 'https://app.example.com/approve/123' } },
        color: { red: 0, green: 0.5, blue: 0, alpha: 1 }
      },
      {
        text: 'Reject',
        onClick: { openLink: { url: 'https://app.example.com/reject/123' } }
      }
    ]
  }
}

Button with icon:

typescript
{
  buttonList: {
    buttons: [{
      text: 'View on GitHub',
      icon: { knownIcon: 'BOOKMARK' },
      onClick: { openLink: { url: 'https://github.com/org/repo/pull/42' } }
    }]
  }
}

image

Standalone image widget.

typescript
{
  image: {
    imageUrl: 'https://example.com/chart.png',
    altText: 'Monthly usage chart'
  }
}

divider

Horizontal line separator between widgets.

typescript
{ divider: {} }

Collapsible Sections

Sections can be collapsed with only the first N widgets visible:

typescript
{
  header: 'Details',
  collapsible: true,
  uncollapsibleWidgetsCount: 2,  // Show first 2, collapse rest
  widgets: [
    { decoratedText: { topLabel: 'Status', text: 'Active' } },
    { decoratedText: { topLabel: 'Region', text: 'AU' } },
    // These start collapsed
    { decoratedText: { topLabel: 'Instance', text: 'prod-01' } },
    { decoratedText: { topLabel: 'Memory', text: '2.1 GB' } },
    { decoratedText: { topLabel: 'CPU', text: '45%' } }
  ]
}

Known Icons

Icons available via knownIcon in decoratedText and button widgets.

typescript
{ startIcon: { knownIcon: 'STAR' } }
// or
{ icon: { knownIcon: 'EMAIL' } }
Icon NameUse For
AIRPLANETravel, flights
BOOKMARKSave, reference, links
BUSTransport, transit
CARDriving, transport
CLOCKTime, duration, schedule
CONFIRMATION_NUMBER_ICONTickets, bookings
DESCRIPTIONDocuments, files
DOLLARMoney, pricing, cost
EMAILEmail, messages
INVITEInvitations
MAP_PINLocation, address
MEMBERSHIPMembers, users
MULTIPLE_PEOPLETeams, groups
OFFERDeals, promotions
PERSONIndividual user
PHONEPhone number, calls
SHOPPING_CARTCommerce, purchases
STARRating, favourite, important
STOREShop, retail
TICKETTickets, events
VIDEO_CAMERAVideo, meetings

For icons not in the list, use iconUrl with any publicly accessible image (square, ideally 24x24 or 48x48 pixels).

Threading

Thread messages together using threadKey:

typescript
// First message — creates thread
const response = await sendCard(webhookUrl, card, {
  threadKey: 'deploy-2026-02-16'
});

// Reply to thread — append &messageReplyOption=REPLY_MESSAGE_FALLBACK_TO_NEW_THREAD
const threadUrl = `${webhookUrl}&messageReplyOption=REPLY_MESSAGE_FALLBACK_TO_NEW_THREAD`;
await sendCard(threadUrl, replyCard, {
  threadKey: 'deploy-2026-02-16'
});

The threadKey is a client-assigned string. Use consistent keys for related messages (e.g., deploy-{date}, alert-{id}).

Common Patterns

Notification Card

typescript
import { buildCard, sendCard } from './assets/card-builder';
import { sendWebhook } from './assets/webhook-sender';

const card = buildCard({
  cardId: 'deploy-notification',
  title: 'Deployment Complete',
  subtitle: 'production - v2.1.0',
  imageUrl: 'https://example.com/your-icon.png',
  sections: [{
    widgets: [
      { decoratedText: { topLabel: 'Environment', text: 'Production' } },
      { decoratedText: { topLabel: 'Version', text: 'v2.1.0' } },
      { decoratedText: { topLabel: 'Status', text: '*Healthy*', startIcon: { knownIcon: 'STAR' } } },
      { buttonList: { buttons: [{ text: 'View Deployment', onClick: { openLink: { url: 'https://dash.example.com' } } }] } }
    ]
  }]
});

Digest Card (Weekly Summary)

typescript
const digest = buildCard({
  cardId: 'weekly-digest',
  title: 'Weekly Summary',
  subtitle: `${count} updates this week`,
  sections: [
    {
      header: 'Highlights',
      widgets: items.map(item => ({
        decoratedText: { text: item.title, bottomLabel: item.date }
      }))
    },
    {
      widgets: [{
        buttonList: {
          buttons: [{ text: 'View All', onClick: { openLink: { url: dashboardUrl } } }]
        }
      }]
    }
  ]
});

Error Prevention

MistakeFix
**bold** in textUse *bold* (single asterisks)
[text](url) linksUse <url|text> format
Missing cardsV2 wrapperWrap card in { cardsV2: [{ cardId, card }] }
Thread replies not threadingAppend &messageReplyOption=REPLY_MESSAGE_FALLBACK_TO_NEW_THREAD to webhook URL
Webhook returns 400Check JSON structure — common issue is missing text or cardsV2 at top level
Card not showingEnsure sections has at least one widget

Asset Files

FilePurpose
assets/types.tsTypeScript type definitions for cardsV2
assets/card-builder.tsUtility to build card messages
assets/webhook-sender.tsPOST to webhook with error handling

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Google Chat Messages AI skill do?

Send Google Chat messages via incoming webhooks — text, rich cards (cardsV2), threaded replies. TypeScript types, card builder utility, widget reference inline. Use whenever the user wants to post to Google Chat from a script, build a chatbot reply, send a notification card, build a Google Chat webhook integration, or troubleshoot card / threading issues.

Why use Google Chat Messages on TypingMind?

Because you install it once and use it with any model. Google Chat Messages is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Google Chat Messages in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jezweb/claude-skills/tree/main/plugins/integrations/skills/google-chat-messages. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Google Chat Messages?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Google Chat Messages?

As many as you like. As long as a model supports skills, you can use Google Chat Messages with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Google Chat Messages AI skill free?

Yes. It is published on GitHub by jezweb under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇