Post team updates to Google Chat Spaces via webhook. Deployment notifications, bug fixes, feature announcements, questions. Reads config from .claude/settings.json, includes git context. Use when: "post to team", "notify team", after deployments, completing features, fixing bugs, asking team questions.
/plugin marketplace add jezweb/claude-skills/plugin install jezweb-tooling-skills@jezweb/claude-skillsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
README.mdtemplates/bugfix.mdtemplates/custom.mdtemplates/deployment.mdtemplates/feature.mdtemplates/question.mdtemplates/settings-template.jsonStatus: Production Ready Last Updated: 2026-01-09
Post updates to a team Google Chat Space via webhook.
Run /google-spaces-updates setup or manually create .claude/settings.json:
{
"project": {
"name": "my-project",
"repo": "github.com/org/my-project"
},
"team": {
"chat_webhook": "https://chat.googleapis.com/v1/spaces/SPACE_ID/messages?key=KEY&token=TOKEN",
"members": ["Deepinder", "Joshua", "Raquel"]
}
}
"Post deployment update to team"
"Tell the team about the new feature"
"Ask the team about the auth approach"
Look for .claude/settings.json in the current project directory:
cat .claude/settings.json 2>/dev/null || echo "NOT_FOUND"
If NOT_FOUND, ask the user:
"This project doesn't have Google Spaces configured. Would you like me to set it up? I'll need the webhook URL for your team's Google Space."
Then create the file using the template in templates/settings-template.json.
Based on the command or context, determine the update type:
| Type | When to use |
|---|---|
deployment | After pushing to production/staging, deploying to Vercel/etc |
bugfix | After fixing a bug, especially one reported by team |
feature | After completing a feature that's ready for review/use |
question | When blocked or need team input on a decision |
custom | For anything else |
Collect relevant information to include:
# Recent commits (for context)
git log --oneline -3 2>/dev/null
# Current branch
git branch --show-current 2>/dev/null
# Changed files (if recent changes)
git diff --name-only HEAD~1 2>/dev/null | head -10
Also use context from the conversation:
Use the appropriate template from templates/ directory.
Key formatting rules for Google Chat:
*bold* for emphasis (not markdown bold)_italic_ for secondary textcurl -X POST "WEBHOOK_URL" \
-H "Content-Type: application/json" \
-d '{"text": "MESSAGE_HERE"}'
Replace:
WEBHOOK_URL with value from .claude/settings.json ā team.chat_webhookMESSAGE_HERE with the formatted message (escape quotes properly)After posting, tell the user:
"Posted update to team chat: [brief summary of what was posted]"
š *Deployed: [PROJECT_NAME]*
[WHAT_CHANGED - 1-2 sentences]
⢠Branch: `[BRANCH]`
⢠Commit: `[COMMIT_HASH]`
[⢠Preview: URL (if applicable)]
[⢠Production: URL (if applicable)]
_Posted by [USER] via Claude Code_
š *Bug Fixed: [PROJECT_NAME]*
*Problem:* [What was broken]
*Solution:* [How it was fixed]
*Files:* [Key files changed]
[⢠Commit: `[COMMIT_HASH]`]
_Please verify if you reported this issue._
⨠*Feature Complete: [PROJECT_NAME]*
*[FEATURE_NAME]*
[DESCRIPTION - what it does, 1-2 sentences]
[⢠Demo: URL]
[⢠Files: key files]
_Ready for review/testing._
ā *Question: [PROJECT_NAME]*
[QUESTION - clear and specific]
*Context:*
[Relevant background - what you're working on, what you've tried]
*Options considered:*
1. [Option A]
2. [Option B]
_@[PERSON] - would appreciate your input_
š¢ *Update: [PROJECT_NAME]*
[MESSAGE]
_Posted by [USER] via Claude Code_
When user runs /google-spaces-updates setup:
.claude/settings.json using the template.claude/ to .gitignore if not already thereSuggest posting an update when:
git push to main/master/productionAsk: "Would you like me to post an update to the team about this?"
The URL format: https://chat.googleapis.com/v1/spaces/SPACE_ID/messages?key=KEY&token=TOKEN
Security: Keep webhook URLs private. Add .claude/settings.json to .gitignore.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.