td-task-management

Coordinate AI agents' task management across context windows with structured handoffs.

3|1|Updated Dec 23, 2025
One-click install
npx skills add https://github.com/marcus/marcus-skills --skill td-task-management
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: td-task-management
Source: https://github.com/marcus/marcus-skills/tree/main/skills/td-task-management
Command: npx skills add https://github.com/marcus/marcus-skills --skill td-task-management

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Task management for AI agents across context windows, enabling tracking of work, logging progress, and structured handoffs between sessions.

Core Features & Use Cases

  • Session continuity across context windows by recording active work and decisions
  • Structured handoffs using fields like done, remaining, decisions, and uncertain
  • Multi-workflow support for single-issue focus and multi-issue sessions

Quick Start

Initialize a td task-management workflow and start a new session to begin tracking work.

Frequently Asked Questions about td-task-management

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I persist AI agent context across multiple sessions?

To persist AI agent context across sessions, you need structured task handoffs that record active work, decisions, and remaining items. This ensures reliable continuity by enforcing a standardized handoff format between context windows.

What is the best way to manage task handoffs for AI agents?

The best way to manage task handoffs for AI agents is to use a structured format tracking done, remaining, decisions, and uncertain items. This enforces reliable continuity and review across single-issue and multi-issue workflows.

How do I track AI agent workflows across context windows?

You can track AI agent workflows across context windows by initializing a task management workflow that records progress and logs decisions. This supports both single-issue focus and multi-issue sessions seamlessly.

Can I use structured handoffs for multi-issue AI agent workflows?

Yes, structured handoffs support multi-issue AI agent workflows by maintaining session continuity. The system records active work and decisions, allowing you to manage multiple issues simultaneously across different context windows.

Why do AI agents lose context between sessions and how do I fix it?

AI agents lose context between sessions because context windows reset, discarding active work. You fix this by applying structured task management to enforce handoffs with done, remaining, decisions, and uncertain fields for reliable continuity.