Install any skill in seconds. Free to start, no credit card required.
Get Started Free →name: gogcli
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-08 | ✗→✓ | ▲ Improved | — | — |
| case-17 | ✗→✓ | ▲ Improved | — | — |
| case-13 | ✗→✓ | ▲ Improved | — | — |
| case-10 | ✗→✓ | ▲ Improved | — | — |
name: gogcli description: Google Workspace CLI for Gmail, Calendar, Drive, Sheets, Docs, Slides, Contacts, Tasks, People, Groups, Keep. Use when user asks to interact with Google services.
gogcli is a CLI tool for managing Google Workspace services from the terminal. Supports Gmail, Calendar, Drive, Sheets, Docs, Slides, Contacts, Tasks, People, Groups, and Keep.
bashbrew install steipete/tap/gogcli
bash# 1. Clone repository git clone https://github.com/steipete/gogcli.git # 2. Navigate to directory cd gogcli # 3. Build make # 4. (Optional) Make available globally sudo make install
Before using gogcli, set up OAuth credentials:
Step 1: Get OAuth Client Credentials
http://localhost:8085/callback~/Downloads/Step 2: Authorize Your Account
bashcd gogcli ./bin/gog auth add you@gmail.com ~/Downloads/client_secret_....json
Step 3: Verify
bash./bin/gog auth list ./bin/gog gmail search 'is:unread' --max 5
bash# Search ./bin/gog gmail search 'query' --max 20 # Send ./bin/gog gmail send 'recipient@gmail.com' --subject 'Hello' --body 'Message' # Labels ./bin/gog gmail labels list
bash# List events ./bin/gog calendar events list --max 50 # Create event ./bin/gog calendar events create 'Meeting' --start '2026-01-30T10:00'
bash# List files ./bin/gog drive ls --query 'pdf' --max 20 # Upload file ./bin/gog drive upload ~/Documents/file.pdf
bash# List sheets ./bin/gog sheets list # Export sheet ./bin/gog sheets export <spreadsheet-id> --format pdf
bash./bin/gog contacts search 'John Doe'
bash# List tasklists ./bin/gog tasks list # Add task ./bin/gog tasks add --title 'Task' --due '2026-01-30'
--json flag for scripting~/.config/gog/gog auth list to check authentication status| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
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. 23 cases were attempted. The headline lift of +52 percentage points is the difference between those two pass rates over the 23 comparable cases.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.