Google Tasks logo

Google Tasks

Community
win4r
google_tasks

Manage the user's Google Tasks: lists, task details, creation, updates, and completion.

Overview

Publisherwin4r
RepositoryMuseAI-Skills
Skill namegoogle_tasks
Stars
382
Forks
116
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by win4r on GitHub. Read the source before you install it.

Installation

Install the Google Tasks 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/win4r/MuseAI-Skills/tree/main/opt/hatch/skills/google-tasks
  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/win4r/MuseAI-Skills.git /tmp/MuseAI-Skills
mkdir -p .claude/skills
cp -r /tmp/MuseAI-Skills/opt/hatch/skills/google-tasks .claude/skills/google_tasks
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Tasks 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 Tasks 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 Tasks 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 Tasks

Everything runs through hatch_gws_cli tasks <resource> <method>. The two resources are tasklists and tasks, so a task command names tasks twice — hatch_gws_cli tasks tasks list (service tasks, resource tasks, method list). Parameters go in a --params JSON object, and creates and edits add a --json request body. The flows below give the exact command for each job, so use them verbatim; run hatch_gws_cli tasks <resource> --help for a command's flags, and hatch_gws_cli schema tasks.tasks.insert (and so on) for a method's --params/--json shape.

A task's due is a date given as an RFC3339 timestamp like 2026-04-16T00:00:00Z, but Google Tasks uses only the date — there is no time of day and no reminders. The default task list is @default.

Connecting

Tasks needs a one-time connect before commands return data. Run hatch_gws_cli tasks status. If it is not connected, post the exact connect_url it returns as [Connect Google Tasks](<connect_url>) and wait for the user to tap it. Don't invent a URL, send the user to Settings, or ask for credentials.

To disconnect, run hatch_gws_cli tasks disconnect and post its disconnect_url as [Disconnect Google Tasks](<disconnect_url>).

If a command reports an auth failure or not-connected, rerun status and follow the link it returns. If status is unavailable, say Google Tasks isn't available on this device and stop. Auth flows only through status and disconnect, with no hand-authored credential files or raw gws auth.

Common flows

See your lists and tasks

  • Your to-do lists: hatch_gws_cli tasks tasklists list. Use when the user asks what lists they have or wants to target one by name.
  • Open tasks on a list: hatch_gws_cli tasks tasks list --params '{"tasklist":"@default","showCompleted":false}'. Use @default unless the user named a list (resolve its ID with hatch_gws_cli tasks tasklists list first). To include finished tasks, set "showCompleted":true,"showHidden":true (completed tasks drop off the default view over time).
  • Tasks due in a window: hatch_gws_cli tasks tasks list --params '{"tasklist":"@default","dueMin":"<start>","dueMax":"<end>"}' (RFC3339) — use for "what's due this week".
  • One task's full detail or its ID before editing: hatch_gws_cli tasks tasks get --params '{"tasklist":"@default","task":"<id>"}'.

Add a task

hatch_gws_cli tasks tasks insert --params '{"tasklist":"@default"}' --json '{"title":"Buy groceries","notes":"Milk, eggs","due":"<date>"}'. Only title is required; add notes and a due date when the user gives them.

Complete or reopen a task

  • Mark done: hatch_gws_cli tasks tasks patch --params '{"tasklist":"@default","task":"<id>"}' --json '{"status":"completed"}'.
  • Reopen: the same with '{"status":"needsAction"}'.

Edit or reschedule a task

hatch_gws_cli tasks tasks patch --params '{"tasklist":"@default","task":"<id>"}' --json '{"title":"...","due":"<date>"}'. Patch only the fields that change.

Organize

  • Move, nest as a subtask, or reorder: hatch_gws_cli tasks tasks move --params '{"tasklist":"@default","task":"<id>","parent":"<parent-id>","previous":"<sibling-id>"}' — omit parent for top level, omit previous to move to the top.
  • Manage lists: hatch_gws_cli tasks tasklists insert --json '{"title":"Work"}', hatch_gws_cli tasks tasklists patch --params '{"tasklist":"<id>"}' --json '{"title":"..."}', hatch_gws_cli tasks tasklists delete --params '{"tasklist":"<id>"}'.

Delete or clear

  • Delete one task: hatch_gws_cli tasks tasks delete --params '{"tasklist":"@default","task":"<id>"}'.
  • Hide completed tasks from a list's normal view (they stay retrievable with showHidden, not deleted): hatch_gws_cli tasks tasks clear --params '{"tasklist":"@default"}'.

Carry the tasklist ID and task ID from the read that found the item straight through the write, and use them exactly. @default is only the default when the user has not pointed at a specific list; once a read locates a task on some list, target that same list for the update, complete, move, or delete — never fall back to @default. Never invent or rewrite a task or list ID.

Rules

  • Task and task-list writes may proceed from a clear, unambiguous user request without an additional confirmation. Resolve the exact task and list before editing, moving, completing, or deleting.
  • Talk to the user in plain language only. The commands and their JSON output are for you, not the user: keep them out of your replies — no command or flag (hatch_gws_cli, --params), no status word (not_connected, unavailable), no task or list id, no API field (etag, updated, page tokens), and no raw JSON. Say "your to-do list" or name a task by its title. A task's own content is not an id: its title, notes, and due date are what the user asked for, so keep those in your reply.
  • Get due dates right against the current date and the user's timezone; report them as plain dates.
  • due remains a date-only value. For actual instants, prefer the added task_record_updated_at and task_completed_at UTC/user-local fields.
  • Never print tokens, secrets, or credential material. Redact them if they appear in tool output.

Limits

  • Tasks are date-based only: a due date carries no time of day, and Google Tasks sends no reminders or notifications — don't promise a specific time or an alert. If the user wants a timed reminder, suggest Google Calendar instead.
  • Tasks are personal to the connected account: no sharing a list, no assigning a task to someone else, no attachments.

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 Tasks AI skill do?

Manage the user's Google Tasks: lists, task details, creation, updates, and completion.

Why use Google Tasks on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/win4r/MuseAI-Skills/tree/main/opt/hatch/skills/google-tasks. 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 Tasks?

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 Tasks?

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

Is the Google Tasks AI skill free?

It is published on GitHub by win4r. Check the repository for licensing terms. 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 👇