Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Interact with Google Chat - list spaces, send messages, read conversations, and manage DMs. Use when user asks to: send a message on Google Chat, read chat messages, list chat spaces, find a chat room, send a DM, or create a new chat space. Lightweight alternative to full Google Workspace MCP server with standalone OAuth authentication.
.claude/skills/sanjay3290-google-chat/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -52% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -45% | 0% |
Lightweight Google Chat integration with standalone OAuth authentication. No MCP server required.
> ⚠️ Requires Google Workspace account. Personal Gmail accounts are not supported.
Authenticate with Google (opens browser):
bashpython scripts/auth.py login
Check authentication status:
bashpython scripts/auth.py status
Logout when needed:
bashpython scripts/auth.py logout
All operations via scripts/chat.py. Auto-authenticates on first use if not logged in.
bash# List all spaces you're a member of python scripts/chat.py list-spaces # Find a space by name python scripts/chat.py find-space "Project Alpha" # Get messages from a space python scripts/chat.py get-messages spaces/AAAA123 --limit 10 # Send a message to a space python scripts/chat.py send-message spaces/AAAA123 "Hello team!" # Send a message with file attachment python scripts/chat.py send-message spaces/AAAA123 "Here's the report" --attachment /path/to/file.pdf # Send a direct message python scripts/chat.py send-dm user@example.com "Hey, quick question..." # Send a DM with file attachment python scripts/chat.py send-dm user@example.com "Please review" --attachment /path/to/file.pdf # Find or create DM space with someone python scripts/chat.py find-dm user@example.com # List threads in a space python scripts/chat.py list-threads spaces/AAAA123 # Create a new space with members python scripts/chat.py setup-space "New Project" user1@example.com user2@example.com
Google Chat uses spaces/AAAA123 format. Get space names from list-spaces or find-space.
Tokens stored securely using the system keyring:
Service name: google-chat-skill-oauth
Automatically refreshes expired tokens using Google's cloud function.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 3,890 | 19,694 | +406% | 1 | 1 | 0% | 558 | 1,324 | +137% | 0 | 0 | — |
case-02 | fail→pass | 2,855 | 1,608 | -44% | 1 | 1 | 0% | 507 | 728 | +44% | 0 | 0 | — |
case-03 | fail→pass | 6,819 | 1,342 | -80% | 1 | 1 | 0% | 1,097 | 708 | -35% | 0 | 0 | — |
case-04 | fail→pass | 8,020 | 1,222 | -85% | 1 | 1 | 0% | 1,431 | 680 | -52% | 0 | 0 | — |
case-09 | fail→pass | 11,419 | 1,709 | -85% | 1 | 1 | 0% | 2,022 | 816 | -60% | 0 | 0 | — |
case-05 | fail→pass | 8,904 | 1,600 | -82% | 1 | 1 | 0% | 1,418 | 780 | -45% | 0 | 0 | — |
case-06 | fail→pass | 10,009 | 1,184 | -88% | 1 | 1 | 0% | 1,730 | 661 | -62% | 0 | 0 | — |
case-07 | fail→pass | 12,064 | 1,294 | -89% | 1 | 1 | 0% | 2,386 | 685 | -71% | 0 | 0 | — |
case-08 | fail→pass | 9,193 | 1,706 | -81% | 1 | 1 | 0% | 1,726 | 810 | -53% | 0 | 0 | — |
case-10 | fail→pass | 8,753 | 2,061 | -76% | 1 | 1 | 0% | 1,710 | 836 | -51% | 0 | 0 | — |
case-11 | fail→pass | 7,277 | 1,058 | -85% | 1 | 1 | 0% | 1,286 | 699 | -46% | 0 | 0 | — |
case-12 | fail→pass | 9,512 | 2,944 | -69% | 1 | 1 | 0% | 1,651 | 985 | -40% | 0 | 0 | — |
case-13 | fail→pass | 11,097 | 1,772 | -84% | 1 | 1 | 0% | 1,855 | 714 | -62% | 0 | 0 | — |
case-14 | pass→pass | 9,409 | 1,135 | -88% | 1 | 1 | 0% | 1,663 | 701 | -58% | 0 | 0 | — |
case-15 | fail→pass | 8,417 | 1,787 | -79% | 1 | 1 | 0% | 1,564 | 809 | -48% | 0 | 0 | — |
case-16 | fail→pass | 11,250 | 1,795 | -84% | 1 | 1 | 0% | 2,062 | 796 | -61% | 0 | 0 | — |
case-17 | fail→pass | 7,019 | 1,253 | -82% | 1 | 1 | 0% | 1,380 | 761 | -45% | 0 | 0 | — |
case-18 | fail→pass | 9,391 | 1,751 | -81% | 1 | 1 | 0% | 1,652 | 851 | -48% | 0 | 0 | — |
case-19 | pass→pass | 13,007 | 11,015 | -15% | 1 | 1 | 0% | 2,394 | 2,680 | +12% | 0 | 0 | — |
case-20 | pass→pass | 6,432 | 5,587 | -13% | 1 | 1 | 0% | 1,189 | 1,507 | +27% | 0 | 0 | — |
case-21 | pass→pass | 7,866 | 5,138 | -35% | 1 | 1 | 0% | 1,406 | 1,481 | +5% | 0 | 0 | — |
case-22 | fail→pass | 12,847 | 3,695 | -71% | 1 | 1 | 0% | 2,237 | 1,120 | -50% | 0 | 0 | — |
case-23 | pass→pass | 7,907 | 2,258 | -71% | 1 | 1 | 0% | 1,158 | 876 | -24% | 0 | 0 | — |
case-24 | pass→pass | 4,857 | 2,058 | -58% | 1 | 1 | 0% | 801 | 773 | -3% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +71 percentage points is the difference between those two pass rates over the 23 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.