Skip to content
Get packs

Google Chat Channel Setup

Connects NanoClaw to Google Chat by installing and registering a Chat SDK adapter.

Source Download skill
Repository
nanocoai/nanoclaw
Stars
31,072
Licence
MIT
Files
3 files

What it does

This skill teaches an agent to add Google Chat as a messaging channel for NanoClaw, a personal AI assistant framework. The agent copies a Google Chat adapter file from the project's channels branch, registers it, installs a pinned adapter package, builds the project and runs one test. It then walks the user through Google Cloud Console setup and stores the service account key and endpoint settings in the local .env file.

Great for

  • Developers running NanoClaw who want their assistant to answer in Google Chat spaces or direct messages
  • Teams with a Google Workspace domain who want a Chat app that only their own staff can use

Skip it if

  • Users who do not run NanoClaw or a compatible agent setup, since the steps assume its build, test and .env conventions
  • Anyone unwilling to create a Google Cloud project and service account key, because the setup cannot be completed without them
  • Shared or unmanaged machines, because the service account JSON key is stored in plain text in .env

Try asking

  • “Add Google Chat support to my NanoClaw install”
  • “Set up the Google Chat channel and walk me through the Google Cloud Console steps”
  • “Re-run the Google Chat integration after I changed my tunnel URL”
Step-by-step guide: how to use Google Chat Channel SetupInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 3 original files, the MIT licence and an attribution note.

    add-gchat.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip add-gchat.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip add-gchat.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Keep the service account key out of shared logs and version control, since it is stored in .env as a single-line string
  • Use a tunnel such as ngrok for local testing and make sure the endpoint URL in Google Cloud matches .env exactly, or every webhook will be rejected
  • Read the Google Cloud steps before starting, since the Convert to add-on step for an existing Chat app cannot be undone

What's inside

  • apply-fixtures.json
  • REMOVE.md
  • SKILL.md

Redistributed unmodified from nanocoai/nanoclaw under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.