Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

cs-workspace-admin · alirezarezvani | DecimalAI

alirezarezvani/cs-workspace-admin

SkillScore91Maintained

Google Workspace administration agent using the gws CLI. Orchestrates workspace setup, Gmail/Drive/Sheets/Calendar automation, security audits, and recipe execution. Spawn when users need Google Workspace automation, gws CLI help, or workspace administration.

DevOpsby alirezarezvani

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

DevOps & SRE pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/alirezarezvani-cs-workspace-admin/SKILL.md

decimalai skills pull alirezarezvani-cs-workspace-admin --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/alirezarezvani-cs-workspace-admin/SKILL.md https://app.decimal.ai/s/alirezarezvani-cs-workspace-admin/SKILL.md

Raw file: /s/alirezarezvani-cs-workspace-admin/SKILL.md ↗ · machine-readable summary at /s/alirezarezvani-cs-workspace-admin.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 49d ago

—+69% tokens0% turns91% of whole cases pass with skill (20/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-11	✗→✓	▲ Improved	121%	0%
case-02	✗→✓	▲ Improved	99%	0%
case-03	✗→✓	▲ Improved	25%	0%
case-07	✗→✓	▲ Improved	69%	0%
case-08	✗→✓	▲ Improved	79%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

alirezarezvani / claude-skills

.gemini/skills/cs-workspace-admin/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

cs-workspace-admin

Role & Expertise

Google Workspace administration specialist orchestrating the gws CLI for email automation, file management, calendar scheduling, security auditing, and cross-service workflows. Manages setup, authentication, 43 built-in recipes, and 10 persona-based bundles.

Skill Integration

Skill Location

../../engineering-team/google-workspace-cli/

Python Tools

GWS Doctor

Path: ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_doctor.py
Usage: python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_doctor.py [--json]
Purpose: Pre-flight diagnostics — checks installation, auth, and service connectivity

Auth Setup Guide

Path: ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/auth_setup_guide.py
Usage: python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/auth_setup_guide.py --guide oauth
Purpose: Guided auth setup, scope listing, .env generation, validation

Recipe Runner

Path: ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py
Usage: python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py --list
Purpose: Catalog, search, and execute 43 built-in recipes with persona filtering

Workspace Audit

Path: ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/workspace_audit.py
Usage: python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/workspace_audit.py [--json]
Purpose: Security and configuration audit across Workspace services

Output Analyzer

Path: ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/output_analyzer.py
Usage: gws ... --json | python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/output_analyzer.py --count
Purpose: Parse, filter, and aggregate JSON/NDJSON output from any gws command

Knowledge Bases

Command Reference — ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/references/gws-command-reference.md

18 services, 22 helpers, global flags, environment variables

Recipes Cookbook — ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/references/recipes-cookbook.md

43 recipes organized by category with persona mapping

Troubleshooting — ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/references/troubleshooting.md

Common errors, auth issues, platform-specific fixes

Templates

Workspace Config — ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/assets/workspace-config.json

Automation config template with auth, defaults, scheduled tasks

Persona Profiles — ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/assets/persona-profiles.md

10 role-based workflow bundles

Core Workflows

1. Setup & Onboarding

Goal: Get gws CLI installed, authenticated, and verified.

Steps:

Run gws_doctor.py to check installation and existing auth
If not installed, guide through installation (npm/cargo/binary)
Run auth_setup_guide.py --guide oauth for auth instructions
Run auth_setup_guide.py --scopes <services> to identify required scopes
Run auth_setup_guide.py --validate to verify all services
Generate .env template with auth_setup_guide.py --generate-env

Example:

bash
python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_doctor.py
python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/auth_setup_guide.py --guide oauth
python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/auth_setup_guide.py --validate --json

2. Daily Operations

Goal: Execute persona-based daily workflows using recipes.

Steps:

Identify user's role and select persona with gws_recipe_runner.py --personas
List relevant recipes with gws_recipe_runner.py --persona <role> --list
Execute recipes with gws_recipe_runner.py --run <name> (use --dry-run first)
Pipe output through output_analyzer.py for filtering and analysis

Example:

bash
python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py --persona pm --list
python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py --run standup-report --dry-run
gws recipes standup-report --json | python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/output_analyzer.py --format table

3. Security Audit

Goal: Audit Workspace security configuration and remediate findings.

Steps:

Run workspace_audit.py for full security assessment
Review findings, prioritizing FAIL items
Filter findings through output_analyzer.py for actionable items
Execute remediation commands from audit output
Re-run audit to verify fixes

Example:

bash
python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/workspace_audit.py --json
python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/workspace_audit.py --json | \
  python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/output_analyzer.py --filter "status=FAIL"

4. Automation Scripting

Goal: Generate multi-step gws scripts for recurring operations.

Steps:

Identify the workflow from recipe templates
Use gws_recipe_runner.py --describe <name> for command sequences
Customize commands with user-specific parameters
Test with --dry-run flag
Combine into shell scripts or scheduled tasks using workspace-config.json template

Example:

bash
python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/gws_recipe_runner.py --describe morning-briefing
# Customize and test
gws helpers morning-briefing --json | python3 ../../engineering-team/google-workspace-cli/skills/google-workspace-cli/scripts/output_analyzer.py --select "type,summary,time" --format table

Output Standards

Diagnostic reports: structured PASS/WARN/FAIL per check with fixes
Audit reports: scored findings with risk ratings and remediation commands
Recipe output: JSON piped through output_analyzer.py for formatted display
Always use --dry-run before executing bulk or destructive operations

Success Metrics

Setup Time: gws installed and authenticated in under 10 minutes
Audit Coverage: All critical security checks pass (Grade A or B)
Automation: Daily workflows automated via recipes and scheduled tasks
Troubleshooting: Common errors resolved using troubleshooting reference

Related Agents

cs-engineering-lead — Engineering team coordination
cs-senior-engineer — Architecture and CI/CD

References

Skill Documentation
gws CLI Repository

Illustrative Want to see what alirezarezvani/cs-workspace-admin would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/10/2026, 03:50 UTC · 22 cases

Measured on 21 comparable cases — below the 22 needed to publish a lift, so this result is shown here but not on the registry card or leaderboard.

Lift

+77%

91% vs 14%

Agent turns

1.0 vs 1.0

Tokens

+69%

2,942.71 vs 1,743.48

fail → pass · 18pass → pass · 2fail → fail · 1pass → fail · 1

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-06 We are configuring GCP IAM bindings using Terraform for service accounts accessing BigQuery datasets. Can you provide the google_project_iam_binding HCL block?	pass→pass	9,187	7,464	-19%	1	1	0%	1,956	3,517	+80%	0	0	—
case-11 I run a workspace helper command that returns JSON, and I only want to display the type, summary, and time fields formatted as a table. I was thinking of piping into jq and column -t. How should I pipe this JSON using the dedicated workspace output tool?	fail→pass	6,425	4,688	-27%	1	1	0%	1,289	2,851	+121%	0	0	—
case-01 I need to onboard a new workstation for Google Workspace administration. Can you run a diagnostic check on the system's setup and auth state, guide me through obtaining the right OAuth permissions, and output a clean diagnostic report showing pass/fail statuses and next steps?	fail→fail	17,917	5,523	-69%	1	1	0%	4,096	2,327	-43%	0	0	—
case-02 I'm looking for daily automation routines for a product manager role using our Google Workspace tools. Please find the available recipes for my persona, explain how to run a standup report in dry-run mode first, and format the output as a clear summary table.	fail→pass	11,619	11,373	-2%	1	1	0%	2,150	4,282	+99%	0	0	—
case-03 Our security team wants an audit of our Google Workspace configuration. Please analyze our workspace security posture, highlight any items marked as critical or failing, and generate an actionable remediation report with the specific commands needed to fix those issues.	fail→pass	18,325	11,419	-38%	1	1	0%	3,342	4,189	+25%	0	0	—
case-04 We need a Google Apps Script that triggers on edits in Google Sheets to send an email notification using MailApp. Can you write the JavaScript trigger function for installable triggers?	pass→pass	11,053	10,552	-5%	1	1	0%	2,134	4,041	+89%	0	0	—
case-05 I need to perform a full domain user transfer using GAMADV-XTD3 syntax to move user drive files across two distinct Google Workspace tenants. What is the gam command syntax for gam csv users.csv gam user transfer drive?	pass→fail	14,892	10,246	-31%	1	1	0%	2,510	3,817	+52%	0	0	—
case-07 I have completed OAuth authorization and identified my required service scopes. I was about to manually write a new .env file in text edit. What script command should I run instead to generate the baseline environment file template automatically?	fail→pass	8,130	3,067	-62%	1	1	0%	1,515	2,559	+69%	0	0	—
case-08 We need to determine which OAuth scopes are required for managing Gmail and Calendar services before authenticating. I was planning to look up Google's official API scope URLs manually online. Which workspace setup script option lists and identifies these required scopes directly?	fail→pass	8,101	3,751	-54%	1	1	0%	1,511	2,708	+79%	0	0	—
case-09 I am setting up daily tasks for engineering leads and want to see all supported role profiles in our CLI runner catalog. Should I write a custom shell script to parse the assets directory, or which CLI script flag lists all persona profiles?	fail→pass	8,819	3,769	-57%	1	1	0%	1,490	2,785	+87%	0	0	—
case-10 Before running the morning-briefing workflow, I want to inspect its command sequence without executing it. I considered opening the underlying script file in an editor. Which recipe runner option describes the workflow commands directly?	fail→pass	7,925	3,480	-56%	1	1	0%	1,425	2,637	+85%	0	0	—
case-12 Our security pipeline requires raw JSON data from the workspace audit script to ingest into an external SIEM tool. I was thinking of wrapping the audit console output in a custom regex parser. Which native flag produces JSON directly from the audit script?	fail→pass	10,088	3,705	-63%	1	1	0%	1,733	2,623	+51%	0	0	—
case-13 I have a multi-line NDJSON stream from a bulk user query and want a fast count of total returned records. I was going to pipe into wc -l. Which option of the output analyzer script should I use to aggregate record counts?	fail→pass	8,634	3,462	-60%	1	1	0%	1,442	2,571	+78%	0	0	—
case-14 I want to programmatically check the workspace CLI installation and auth state and receive machine-readable JSON results. Should I write a custom Python health check script, or call the workspace doctor script with which flag?	fail→pass	10,924	4,113	-62%	1	1	0%	2,036	2,815	+38%	0	0	—
case-15 I am authoring an automated workflow script using the recipe runner for standup-report. To test it safely without making actual changes, should I comment out execution commands, or pass which standard testing flag to the runner?	fail→pass	6,522	3,348	-49%	1	1	0%	1,100	2,597	+136%	0	0	—
case-16 I need the pre-packaged automation configuration template containing authentication settings, defaults, and scheduled tasks. Should I create a blank config.json from scratch, or which asset file path provides this template?	fail→pass	7,796	2,763	-65%	1	1	0%	1,587	2,520	+59%	0	0	—
case-17 I need to review the definitions for all 10 role-based workflow bundles. Which asset markdown file in the skill package details these persona profiles?	fail→pass	4,717	2,739	-42%	1	1	0%	920	2,542	+176%	0	0	—
case-18 When encountering authentication errors or platform issues, instead of searching general StackOverflow threads, which skill reference document provides common CLI errors and fixes?	fail→pass	9,422	2,283	-76%	1	1	0%	1,695	2,405	+42%	0	0	—
case-19 Where can I find the reference document covering all 18 services, 22 helpers, global flags, and environment variables instead of searching web docs?	fail→pass	10,781	3,857	-64%	1	1	0%	1,748	2,771	+59%	0	0	—
case-20 Which reference document catalogs all 43 built-in recipes organized by category with persona mapping?	fail→pass	8,587	1,948	-77%	1	1	0%	1,450	2,321	+60%	0	0	—
case-21 After executing remediation commands to fix FAIL security findings in Google Workspace, I am tempted to manually spot-check settings in the Google Admin Console. What script execution step should be performed to formally verify remediation?	fail→pass	8,912	4,371	-51%	1	1	0%	1,470	2,740	+86%	0	0	—
case-22 I need an automated check to validate that all configured Workspace authentication services are operational and output JSON. Rather than manually testing endpoints with curl, what command and flag should I execute with the auth setup guide tool?	fail→pass	12,511	2,711	-78%	1	1	0%	2,110	2,506	+19%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

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 +77 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.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 13.6%
Pass rate with the skill: 90.9%
Cases attempted: 22
Cases counted toward lift: 21
Cases that regressed: 1
Skill version measured: v1
Run completed: 8/10/2026, 03:50 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-11

Prompt

I run a workspace helper command that returns JSON, and I only want to display the type, summary, and time fields formatted as a table. I was thinking of piping into jq and column -t. How should I pipe this JSON using the dedicated workspace output tool?

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.

Show both answers

SkillScore blends 4 signals1 of 4 complete

BenchmarkPass rate WITH skill on a verified run91

Live evalNeeds ≥10 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+85% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

Backed by 1 of 4 signals — each added signal makes the score more robust.

Verified on gemini-3.6-flash · re-tested 48 days ago

Other measured skills in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

alirezarezvani/cs-workspace-admin

SkillSafety

Source

cs-workspace-admin

Role & Expertise

Skill Integration

Skill Location

Python Tools

Knowledge Bases

Templates

Core Workflows

1. Setup & Onboarding

2. Daily Operations

3. Security Audit

4. Automation Scripting

Output Standards

Success Metrics

Related Agents

References

How this skill was measured

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-11

Related skills