Google Calendar logo

Google Calendar

OrganizationPopular
vellum-ai
google-calendar

View Google Calendar events for any day, create and manage events, and check availability

Overview

Publishervellum-ai
Repositoryvellum-assistant
Skill namegoogle-calendar
Stars
1.3K
Forks
186
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

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

Installation

Install the Google Calendar 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/vellum-ai/vellum-assistant.git /tmp/vellum-assistant
mkdir -p .claude/skills
cp -r /tmp/vellum-assistant/skills/google-calendar .claude/skills/google-calendar
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Calendar 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 Google Calendar 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 Google Calendar 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.

Script Reference

All operations use a single CLI script that returns JSON:

  • Success: { "ok": true, "data": ... }
  • Failure: { "ok": false, "error": "..." }
ScriptSubcommandDescription
scripts/gcal.tslistList events within a date range
scripts/gcal.tsgetGet full details of a specific event
scripts/gcal.tscreateCreate a new event (requires user confirmation)
scripts/gcal.tsavailabilityCheck free/busy times across calendars
scripts/gcal.tsrsvpRespond to an event invitation (accepted, declined, tentative)

Usage Examples

bash
# List events in a date range
bun scripts/gcal.ts list --time-min "2024-01-15T00:00:00Z" --time-max "2024-01-22T00:00:00Z"

# Get full details of a specific event
bun scripts/gcal.ts get --event-id "abc123"

# Create a new event (gates on assistant ui confirm)
bun scripts/gcal.ts create --summary "Team Meeting" --start "2024-01-15T09:00:00-05:00" --end "2024-01-15T10:00:00-05:00" --timezone "America/New_York"

# Check availability for a day
bun scripts/gcal.ts availability --time-min "2024-01-15T00:00:00Z" --time-max "2024-01-15T23:59:59Z"

# RSVP to an event invitation
bun scripts/gcal.ts rsvp --event-id "abc123" --response accepted

# Target a specific connected account (see "Multiple Accounts" below)
bun scripts/gcal.ts list --time-min "2024-01-15T00:00:00Z" --time-max "2024-01-22T00:00:00Z" --account "work@example.com"

Every subcommand accepts --account <email> to select which connected Google account the request runs against. When omitted, the request runs against a single account chosen automatically — safe only when exactly one Google account is connected. Each JSON envelope echoes the queried account in an account field when it is reported by the OAuth layer, so an empty result is self-describing (e.g. No events found in the specified time range for work@example.com.).

Connection Setup

  1. Check connection health first. Run assistant oauth status google. This checks whether the user's Google account is connected and the token is valid. Google Calendar shares the same OAuth connection as Gmail — if the user already connected Gmail, calendar access is included.
    • If the status output shows more than one active connection, you MUST pass --account <email> on every scripts/gcal.ts invocation, matching the calendar the user is asking about. When the user references a calendar by name or company (e.g. "my Acme calendar"), map it to the connected account email before querying. Omitting --account with multiple connections silently queries one arbitrary account — an empty or partial result then looks like a genuinely free calendar when it is really the wrong account. Confirm the account field in each response matches the account you intended.
  2. If no connection is found or the status check fails: Load the vellum-oauth-integrations skill. The skill will evaluate whether managed or your-own mode is appropriate and guide the user accordingly.

Scheduling Playbook

When the user wants to schedule something:

  1. Always check availability first before proposing times. Use bun scripts/gcal.ts availability to find free slots.
  2. Propose 2-3 available time options to the user.
  3. Once the user picks a time, create the event with bun scripts/gcal.ts create.
  4. If adding other attendees, mention that they'll receive an invitation email.

Date & Time Handling

  • Use ISO 8601 format for dates and times (e.g., 2024-01-15T09:00:00-05:00).
  • For all-day events, use date-only format (e.g., 2024-01-15).
  • Always ask the user for their timezone if it's not already known from context or their profile.
  • When listing events, display times in the user's local timezone.

Confidence & Safety

Create and RSVP are medium-risk operations:

  • Create: The create subcommand gates on assistant ui confirm — it presents a confirmation dialog to the user and only proceeds if approved. Pass --skip-confirm when the user has already given explicit confirmation in the conversation.
  • RSVP: The rsvp subcommand gates on assistant ui confirm — it presents a confirmation dialog showing the event, current status, and new response. Pass --skip-confirm when the user has already given explicit confirmation in the conversation.

Error Recovery

When a calendar script fails with a token or authorization error:

  1. Try to reconnect silently. Run assistant oauth ping google. This often resolves expired tokens automatically.
  2. If reconnection fails, go straight to setup. Don't present options, ask which route the user prefers, or explain what went wrong technically. Just tell the user briefly (e.g., "Google Calendar needs to be reconnected - let me set that up") and immediately load the vellum-oauth-integrations skill. The user came to you to get something done, not to troubleshoot - make it seamless.
  3. Never try alternative approaches. Don't use curl, browser automation, or any workaround. If the scripts can't do it, the reconnection flow is the answer.
  4. Never expose error details. The user doesn't need to see error messages about tokens, OAuth, or API failures. Translate errors into plain language.

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 Google Calendar AI skill do?

View Google Calendar events for any day, create and manage events, and check availability

Why use Google Calendar on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vellum-ai/vellum-assistant/tree/main/skills/google-calendar. 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 Google Calendar?

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 Google Calendar?

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

Is the Google Calendar AI skill free?

Yes. It is published on GitHub by vellum-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 👇