Gcloud Skill logo

Gcloud Skill

Community
zeenie-ai
gcloud-skill

Work with Google Cloud via the official gcloud CLI — check auth/config, list and switch projects, manage Compute Engine instances, deploy and inspect Cloud Run services, work with Cloud Storage, and run any other gcloud command. Output is parsed JSON.

Overview

Publisherzeenie-ai
RepositoryOpenCompany
Skill namegcloud-skill
Stars
912
Forks
137
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zeenie-ai on GitHub. Read the source before you install it.

Installation

Install the Gcloud Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zeenie-ai/OpenCompany.git /tmp/OpenCompany
mkdir -p .claude/skills
cp -r /tmp/OpenCompany/server/skills/gcloud/gcloud-skill .claude/skills/gcloud-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gcloud Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gcloud Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gcloud Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Google Cloud Skill

Wrapper over the official Google Cloud CLI (gcloud). Typed operations for the core flows plus a custom passthrough that covers the entire gcloud surface. JSON-capable operations run with --format=json, so results come back parsed in result.

Each call starts a fresh gcloud process — a few seconds of startup latency per call is normal; don't retry a slow call.

Tool: gcloud

Operations

OperationPurposeKey fields
auth_listCredentialed accounts + which is active
config_listCurrent configuration (account, project, region defaults)
projects_listProjects the account can access (parsed JSON)limit (default 50)
set_projectSet the configuration's default projectproject_id (required)
compute_instances_listCompute Engine instances (parsed JSON)zone (optional filter), project
compute_instance_startStart an instanceinstance, zone (both required), project
compute_instance_stopStop an instanceinstance, zone (both required), project
compute_instance_describeFull instance detailsinstance, zone (both required), project
run_deployDeploy a Cloud Run serviceservice, region (required), exactly one of source / image, allow_unauthenticated, project
run_services_listCloud Run services (all regions unless filtered)region (optional), project
run_service_describeCloud Run service details (URL, revisions)service, region (both required), project
storage_lsList buckets or objectsurl (optional gs:// URL; omit to list buckets), project
storage_cpCopy files local <-> gs://src, dst (required), recursive, path (working dir)
storage_rmDelete objectsurl (required gs:// URL), recursive
customAny other gcloud commandcommand — exactly what you would type after gcloud

The project / zone / region fields map to --project / --zone / --region. When project is empty, gcloud falls back to the configured default — run set_project once instead of repeating project on every call.

Response

json
{
  "operation": "projects_list",
  "success": true,
  "result": [{ "projectId": "my-project-123", "name": "My Project", "lifecycleState": "ACTIVE" }]
}

Parsed JSON lands in result; plain text (set_project, storage_cp progress) lands in stdout. On failure the tool raises an error carrying gcloud's own message — surface it verbatim; gcloud's errors are precise (including "You do not currently have an active account selected", which means the user needs to log in via Credentials -> Google Cloud).

Typical flows

Orient first when state is unknown:

json
{ "operation": "auth_list" }
{ "operation": "config_list" }
{ "operation": "projects_list" }
{ "operation": "set_project", "project_id": "my-project-123" }

Compute Engine — zone is required for single-instance operations (get it from the list output's zone field):

json
{ "operation": "compute_instances_list" }
{ "operation": "compute_instance_stop", "instance": "my-vm", "zone": "us-central1-a" }

Cloud Run — deploy from a container image, or from source (source deploys run Cloud Build and can take minutes; the 15-minute timeout accommodates that):

json
{ "operation": "run_deploy", "service": "my-api", "region": "us-central1", "image": "gcr.io/my-project/my-api:latest", "allow_unauthenticated": true }
{ "operation": "run_deploy", "service": "my-api", "region": "us-central1", "source": ".", "path": "app" }
{ "operation": "run_service_describe", "service": "my-api", "region": "us-central1" }

The deployed URL is in the describe/deploy result under status.url.

Cloud Storage — local paths resolve against the workflow workspace:

json
{ "operation": "storage_ls", "url": "gs://my-bucket/reports/" }
{ "operation": "storage_cp", "src": "gs://my-bucket/reports/latest.csv", "dst": "./downloads/" }
{ "operation": "storage_cp", "src": "./build", "dst": "gs://my-bucket/site/", "recursive": true }

The full gcloud surface via custom

json
{ "operation": "custom", "command": "iam service-accounts list" }
{ "operation": "custom", "command": "sql instances list" }
{ "operation": "custom", "command": "functions deploy my-fn --runtime python312 --trigger-http --region us-central1" }
{ "operation": "custom", "command": "container clusters list" }
{ "operation": "custom", "command": "logging read \"severity>=ERROR\" --limit 20 --format=json" }
{ "operation": "custom", "command": "services enable run.googleapis.com" }

Notes for custom:

  • Add --format=json yourself when you want parsed output — it is not injected for you.
  • command is parsed with shlex.split — wrap filter expressions and JSON in quotes as you would in a shell.
  • Long-running commands get a 10-minute timeout; for very long operations prefer the --async flag and poll.
  • auth application-default login mints Application Default Credentials for client-library code (stored isolated under OpenCompany's data directory). gcloud CLI commands themselves never need ADC.

Authentication

Auth is owned by the gcloud CLI itself, isolated under OpenCompany's data directory (a login you did in your own terminal is NOT visible here):

  • Credentials Modal -> Google Cloud -> Login — gcloud opens the browser itself for Google sign-in (localhost callback, so the browser must be on the server's machine). First use auto-installs the CLI (~100 MB; allow a few minutes).

If a command fails with an auth error, point the user at the Login button; don't ask them to paste credentials in chat. If it fails with "API not enabled", enable it via { "operation": "custom", "command": "services enable <api>.googleapis.com" }.

Best practices

  1. Run config_list first when state is unknown — it shows the active account and default project without side effects.
  2. Set the project once (set_project) instead of repeating the project field.
  3. Destructive operations (instance stop, storage_rm, deletes via custom) — confirm with the user before running unless they explicitly asked.
  4. Surface gcloud error messages verbatim — don't paraphrase; they name the exact flag, permission, or API to fix.
  5. Costs are real — starting instances and deploying services incurs billing; mention it when the user's intent is exploratory.

Frequently asked questions

What does the Gcloud Skill AI skill do?

Work with Google Cloud via the official gcloud CLI — check auth/config, list and switch projects, manage Compute Engine instances, deploy and inspect Cloud Run services, work with Cloud Storage, and run any other gcloud command. Output is parsed JSON.

Why use Gcloud Skill on TypingMind?

Because you install it once and use it with any model. Gcloud Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gcloud Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zeenie-ai/OpenCompany/tree/main/server/skills/gcloud/gcloud-skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Gcloud Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gcloud Skill?

As many as you like. As long as a model supports skills, you can use Gcloud Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gcloud Skill AI skill free?

Yes. It is published on GitHub by zeenie-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇