Unitask Task Agent for Openclaw

A sophisticated AI agent skill for managing Unitask accounts through secure API tokens, specializing in task lifecycle management and intelligent daily time-blocking.

mfaiz-007
v0.13.3
Feb 8, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install unitask-task-agent

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install unitask-task-agent using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Unitask Task Agent?

The Unitask Task Agent is a developer-centric tool designed to integrate seamlessly with the unitask.app platform. By utilizing this skill within the Openclaw Skills ecosystem, users can delegate complex task management operations to an AI agent. It supports everything from simple list retrieval to the creation of intricate subtask hierarchies, all while maintaining a high security standard through scoped API tokens and a hosted Model Context Protocol (MCP) endpoint.

This skill is particularly valuable for users who want to bridge the gap between their planning software and their AI-driven workflows. It allows for natural language interaction with task lists, ensuring that productivity remains high without the need for manual data entry. Whether you are managing a personal to-do list or coordinating professional projects, this integration provides a robust framework for agentic task handling.

Unitask Task Agent Use Cases

  • Retrieving a summary of daily tasks and checking current progress through natural language queries.
  • Creating and organizing complex projects by nesting subtasks under parent identifiers.
  • Automating the transition of task statuses from todo to done based on project milestones.
  • Generating optimized daily schedules using the advanced time-blocking preview and apply features.

How Unitask Task Agent Works

  1. The AI agent authenticates with the hosted unitask.app API using a user-provided scoped token.
  2. The user provides a command, such as requesting a list of tasks or scheduling a work block.
  3. The skill invokes the appropriate MCP tool, such as list_tasks or plan_day_timeblocks, to interact with the Unitask backend.
  4. For scheduling actions, the agent provides a preview to the user to ensure the proposed time blocks align with their availability.
  5. Upon confirmation, the agent updates the user's Unitask account, reflecting the new tasks, status changes, or scheduled blocks in real-time.

Unitask Task Agent Setup

  1. Generate a Unitask API token by navigating to Dashboard -> Settings -> API within your Unitask account.
  2. Store the token securely as an environment variable in your agent's configuration:
export UNITASK_API_KEY='your_scoped_token_here'
  1. Connect your agent to the hosted MCP endpoint located at https://unitask.app/api/mcp.
  2. Verify that your token has the necessary scopes (read, write, or delete) required for your specific Openclaw Skills implementation.

Unitask Task Agent Data Schema & Taxonomy

The skill manages data through a structured schema focused on task attributes and user preferences:

Attribute Description
title The primary name of the task (Required)
status Current state: todo, done, or archived
parent_id Used to create hierarchical subtasks
priority Numerical or categorical importance level
scheduled_start ISO timestamp for time-block initiation
duration_minutes The length of the allocated time block

Metadata such as user settings and quiz preferences are also accessible to tailor the agent's behavior to individual productivity styles.

Unitask Task Agent Advanced Features

  • Hosted MCP integration allowing for cloud-to-cloud communication without local infrastructure, a key benefit of modern Openclaw Skills.
  • Recursive subtask management that maintains relationships between parent and child tasks during updates or deletions.
  • Two-phase time-blocking execution (preview then apply) to ensure human-in-the-loop safety for calendar management.
  • Granular security model supporting read-only, write, and delete scopes to enforce the principle of least privilege.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*