Admin logo

Admin

Organization
grafana
admin

Manage Grafana Cloud accounts — organizations, stacks, RBAC roles and assignments, SSO/SAML/OAuth/GitHub auth, service accounts for CI/CD, user invites, team membership, and API-driven provisioning. Creates stacks via the Cloud API, mints service-account tokens, applies role assignments, configures SSO providers, and provisions teams/folders/dashboards via Terraform. Use when managing Grafana Cloud access, configuring SSO/SAML/OAuth, setting up service accounts for Terraform/CI/CD, assigning RBAC roles, inviting users, managing multiple stacks or organizations, provisioning cloud resources via API or Terraform, or auditing admin actions — even when the user says "set up SSO", "create a stack", "make a service account", or "onboard a team" without explicitly saying "admin".

Overview

Publishergrafana
Repositoryskills
Skill nameadmin
Stars
289
Forks
27
Bundled files
3
LicenseApache-2.0
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.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by grafana on GitHub. Read the source before you install it.

Installation

Install the Admin 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.
    https://github.com/grafana/skills/tree/main/skills/grafana-cloud/admin
  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/grafana/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/grafana-cloud/admin .claude/skills/admin
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Admin 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 Admin 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 Admin 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.

Grafana Cloud Admin

Docs: https://grafana.com/docs/grafana-cloud/account-management.md

Common Workflows

Setting up a new stack

bash
# 1. Create the stack via Cloud API
curl -X POST https://grafana.com/api/instances \
  -H "Authorization: Bearer <grafana-com-api-key>" \
  -H "Content-Type: application/json" \
  -d '{"name": "my-new-stack", "slug": "my-new-stack", "region": "us-east-0", "plan": "grafana-cloud-free"}'

# 2. Verify the stack is reachable (poll until 200)
until curl -fs https://my-new-stack.grafana.net/api/health > /dev/null; do sleep 2; done

# 3. Mint an admin service-account token (see § Service Accounts below)

# 4. Test the token
curl https://my-new-stack.grafana.net/api/org -H "Authorization: Bearer <token>"
# Returns 200 + org JSON → token works

Onboarding a team

  1. Invite users via POST /api/org/invites (one curl per user — see references/api-reference.md § Stack API)
  2. Create the team via POST /api/teams
  3. Add each user via POST /api/teams/{teamId}/members
  4. Assign an RBAC role to the team (see § RBAC below)
  5. Verify: GET /api/teams/{teamId}/members returns the expected user list

Configuring SSO (Okta / SAML / GitHub)

  1. Pick the provider config from references/sso.md and drop into grafana.ini
  2. Restart Grafana
  3. Always validate in an incognito window before announcing: see references/sso.md § Verifying SSO for the 5-step verification + role-mapping debug pattern

Deleting a stack (destructive)

bash
# 1. Delete via Cloud API
curl -X DELETE https://grafana.com/api/instances/{id} \
  -H "Authorization: Bearer <grafana-com-api-key>"

# 2. Verify the stack is gone (must return 404)
curl https://grafana.com/api/instances/{id} \
  -H "Authorization: Bearer <grafana-com-api-key>"

If the GET still returns 200 after a few seconds, the delete didn't apply — re-check the stack ID and Cloud API key.

Organization and Stack Structure

Grafana Cloud Account
└── Organization (billing unit)
    ├── Stack 1 (prod)   → dedicated Grafana, Prometheus, Loki, Tempo URLs
    ├── Stack 2 (staging)
    └── Stack 3 (dev)
  • Organization: top-level account with billing, users, API keys, stacks
  • Stack: dedicated Grafana + LGTM instance with its own URLs and credentials

User Roles

RoleScopePermissions
Org AdminOrganizationManage stacks, users, billing, API keys
AdminStackData sources, plugins, users, provisioning
EditorStackCreate/edit dashboards, alerts
ViewerStackRead-only dashboards

RBAC

Define a custom role + assignment in provisioning YAML:

yaml
# provisioning/access-control/roles.yaml
apiVersion: 1
roles:
  - name: TeamDashboardEditor
    description: Edit dashboards within team folder
    permissions:
      - action: dashboards:read
        scope: folders:UID:team-folder
      - action: dashboards:write
        scope: folders:UID:team-folder
      - action: dashboards:create
        scope: folders:UID:team-folder
yaml
# provisioning/access-control/assignments.yaml
apiVersion: 1
roleAssignments:
  - roleName: TeamDashboardEditor
    users:
      - alice@example.com
      - bob@example.com
    teams:
      - platform-team

After committing the YAML and restarting Grafana, verify the role applied: GET /api/access-control/roles | jq '.[] | select(.name=="TeamDashboardEditor")'.

Service Accounts

Service accounts are the recommended way for programmatic access (CI/CD, Terraform, agents).

bash
# 1. Create the service account
curl -X POST https://yourstack.grafana.net/api/serviceaccounts \
  -H "Authorization: Bearer <admin-token>" \
  -H "Content-Type: application/json" \
  -d '{"name": "terraform-provisioner", "role": "Admin", "isDisabled": false}'

# 2. Mint a token for it
curl -X POST https://yourstack.grafana.net/api/serviceaccounts/{id}/tokens \
  -H "Authorization: Bearer <admin-token>" \
  -H "Content-Type: application/json" \
  -d '{"name": "ci-token", "secondsToLive": 0}'

# 3. Verify the token works (test on a harmless endpoint)
curl https://yourstack.grafana.net/api/org \
  -H "Authorization: Bearer <new-token>"
# 200 + org JSON → token works. Anything else → re-check role assignment in step 1.

Provisioning equivalent (YAML, declarative):

yaml
# provisioning/access-control/service_accounts.yaml
apiVersion: 1
serviceAccounts:
  - name: alloy-writer
    orgId: 1
    role: Editor
    tokens:
      - name: alloy-token

References

  • references/sso.md — OAuth / SAML / GitHub OAuth config + the 5-step SSO verification pattern + common failure modes
  • references/terraform.md — Terraform provider config + common resource patterns (teams, users, folders, dashboards) + drift troubleshooting
  • references/api-reference.md — full Cloud API + Stack API endpoint reference + audit-log queries

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Admin AI skill do?

Manage Grafana Cloud accounts — organizations, stacks, RBAC roles and assignments, SSO/SAML/OAuth/GitHub auth, service accounts for CI/CD, user invites, team membership, and API-driven provisioning. Creates stacks via the Cloud API, mints service-account tokens, applies role assignments, configures SSO providers, and provisions teams/folders/dashboards via Terraform. Use when managing Grafana Cloud access, configuring SSO/SAML/OAuth, setting up service accounts for Terraform/CI/CD, assigning RBAC roles, inviting users, managing multiple stacks or organizations, provisioning cloud resources...

Why use Admin on TypingMind?

Because you install it once and use it with any model. Admin 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 Admin in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/grafana/skills/tree/main/skills/grafana-cloud/admin. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Admin?

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 Admin?

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

Is the Admin AI skill free?

Yes. It is published on GitHub by grafana under the Apache-2.0 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 👇