task-tracker

Persist hierarchical tasks with dependencies in .claude/tasks/ YAML frontmatter.

1|Updated Aug 1, 2013
One-click install
npx skills add https://github.com/agude/dotfiles --skill task-tracker-agude
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: task-tracker
Source: https://github.com/agude/dotfiles/tree/main/llm/skills/task-tracker
Command: npx skills add https://github.com/agude/dotfiles --skill task-tracker-agude

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

Track tasks and subtasks in .claude/tasks/ for context preservation. Use when planning multi-step work, tracking progress, or resuming interrupted sessions.

Core Features & Use Cases

  • Hierarchical task storage with leaf and parent differentiation, supporting subtasks.
  • Dependency tracking and progress updates across multi-step workflows.
  • Persistent notes and progress rendering for long-running AI-assisted projects.

Quick Start

Initialize the tracker with the task.py script, and start adding tasks with the available commands.

Frequently Asked Questions about task-tracker

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

FAQPage Schema
How do I persist task state across LLM sessions?

Persist task state across LLM sessions by storing tasks in the .claude/tasks/ directory. This preserves context, allowing you to resume interrupted multi-step workflows.

Can I track dependencies and hierarchical subtasks for multi-step work?

Yes, you can track dependencies and hierarchical subtasks. The system differentiates leaf and parent tasks, supporting subtask promotion and demotion for complex workflows.

How does the task tracker format data for machine consumption?

The task tracker formats data for machine consumption by rendering progress and notes in a JSON-friendly form. Task files meet a YAML frontmatter schema with name and description.

Do I need any external dependencies to manage markdown tasks?

No external dependencies are required to manage markdown tasks. You can initialize the tracker with the included task.py script and start adding tasks immediately.

What is the best way to resume an interrupted AI-assisted project?

Resume an interrupted AI-assisted project by utilizing persistent notes and progress rendering. The tracker stores state locally, enabling seamless continuation of long-running workflows.