Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Google Workspace CLI operations: setup diagnostics, security audit, recipe discovery, and output analysis. Usage: /google-workspace <setup|audit|recipe|analyze> [options]
.claude/skills/alirezarezvani-google-workspace/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 1% | 0% |
Google Workspace CLI administration via the gws CLI. Run setup diagnostics, security audits, browse and execute recipes, and analyze command output.
/google-workspace setup [--json]
/google-workspace audit [--services gmail,drive,calendar] [--json]
/google-workspace recipe list [--persona <role>] [--json]
/google-workspace recipe search <keyword> [--json]
/google-workspace recipe run <name> [--dry-run]
/google-workspace recipe describe <name>
/google-workspace analyze [--filter <field=value>] [--group-by <field>] [--stats <field>] [--format table|csv|json]/google-workspace setup
/google-workspace audit --services gmail,drive --json
/google-workspace recipe list --persona pm
/google-workspace recipe search "email"
/google-workspace recipe run standup-report --dry-run
/google-workspace recipe describe morning-briefing
/google-workspace analyze --filter "mimeType=pdf" --select "name,size" --format tableengineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_doctor.py — Pre-flight diagnosticsengineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/auth_setup_guide.py — Auth setup guideengineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py — Recipe catalog & runnerengineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/workspace_audit.py — Security auditengineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/output_analyzer.py — JSON/NDJSON analyzerRun pre-flight diagnostics and auth validation.
bashpython3 engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_doctor.py [--json] python3 engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/auth_setup_guide.py --validate [--json]
Run security and configuration audit.
bashpython3 engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/workspace_audit.py [--services gmail,drive,calendar] [--json]
Browse, search, and execute the 43 built-in gws recipes.
bashpython3 engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py --list [--persona <role>] [--json] python3 engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py --search <keyword> [--json] python3 engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py --describe <name> python3 engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py --run <name> [--dry-run]
Parse, filter, and aggregate JSON output from any gws command.
bashgws <command> --json | python3 engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/output_analyzer.py [options] python3 engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/output_analyzer.py --demo --format table
-> engineering-team/google-workspace-cli/skills/google-workspace-cli/SKILL.md
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,199 | 10,868 | -43% | 1 | 1 | 0% | 2,223 | 1,639 | -26% | 0 | 0 | — |
case-02 | fail→fail | 8,523 | 5,520 | -35% | 1 | 1 | 0% | 1,422 | 1,334 | -6% | 0 | 0 | — |
case-03 | fail→fail | 8,494 | 4,532 | -47% | 1 | 1 | 0% | 956 | 1,153 | +21% | 0 | 0 | — |
case-04 | fail→pass | 4,986 | 1,931 | -61% | 1 | 1 | 0% | 974 | 1,278 | +31% | 0 | 0 | — |
case-21 | pass→pass | 12,692 | 10,651 | -16% | 1 | 1 | 0% | 2,480 | 3,053 | +23% | 0 | 0 | — |
case-05 | fail→pass | 8,999 | 1,974 | -78% | 1 | 1 | 0% | 1,627 | 1,287 | -21% | 0 | 0 | — |
case-06 | fail→pass | 9,843 | 1,776 | -82% | 1 | 1 | 0% | 1,761 | 1,236 | -30% | 0 | 0 | — |
case-07 | fail→pass | 7,123 | 1,818 | -74% | 1 | 1 | 0% | 1,268 | 1,287 | +1% | 0 | 0 | — |
case-08 | fail→pass | 6,824 | 3,015 | -56% | 1 | 1 | 0% | 1,311 | 1,540 | +17% | 0 | 0 | — |
case-09 | fail→pass | 8,591 | 3,034 | -65% | 1 | 1 | 0% | 1,603 | 1,584 | -1% | 0 | 0 | — |
case-10 | fail→pass | 4,040 | 3,833 | -5% | 1 | 1 | 0% | 670 | 1,222 | +82% | 0 | 0 | — |
case-11 | fail→fail | 8,756 | 1,370 | -84% | 1 | 1 | 0% | 1,562 | 1,109 | -29% | 0 | 0 | — |
case-12 | fail→fail | 8,241 | 3,433 | -58% | 1 | 1 | 0% | 1,618 | 1,205 | -26% | 0 | 0 | — |
case-13 | pass→pass | 3,529 | 1,628 | -54% | 1 | 1 | 0% | 758 | 1,175 | +55% | 0 | 0 | — |
case-14 | fail→pass | 12,269 | 4,003 | -67% | 1 | 1 | 0% | 2,733 | 1,710 | -37% | 0 | 0 | — |
case-15 | fail→pass | 9,912 | 3,379 | -66% | 1 | 1 | 0% | 2,232 | 1,629 | -27% | 0 | 0 | — |
case-16 | fail→fail | 9,146 | 1,103 | -88% | 1 | 1 | 0% | 1,590 | 1,066 | -33% | 0 | 0 | — |
case-17 | fail→pass | 12,271 | 5,776 | -53% | 1 | 1 | 0% | 1,019 | 1,195 | +17% | 0 | 0 | — |
case-18 | fail→pass | 6,918 | 6,891 | -0% | 1 | 1 | 0% | 1,359 | 1,274 | -6% | 0 | 0 | — |
case-19 | fail→pass | 5,876 | 2,686 | -54% | 1 | 1 | 0% | 1,188 | 1,440 | +21% | 0 | 0 | — |
case-20 | pass→pass | 4,257 | 4,512 | +6% | 1 | 1 | 0% | 940 | 1,895 | +102% | 0 | 0 | — |
case-22 | pass→pass | 4,663 | 2,959 | -37% | 1 | 1 | 0% | 817 | 1,427 | +75% | 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. 22 cases were attempted, and 21 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 +59 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
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.