task-tree

Creates browsable task trees for tracking progress in AI-assisted projects.

8|2|Updated Apr 9, 2026
One-click install
npx skills add https://github.com/FuZhiyu/superRA --skill task-tree-fuzhiyu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: task-tree
Source: https://github.com/FuZhiyu/superRA/tree/main/skills/task-tree
Command: npx skills add https://github.com/FuZhiyu/superRA --skill task-tree-fuzhiyu

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill prevents AI-assisted projects from losing context, drifting from objectives, or accumulating unreviewed work by storing project state in a durable, structured task tree.

Core Features & Use Cases

  • Task Tree Operations: Query frontier, tree, and dependency DAG views, then create, move, rename, link, and restructure tasks.
  • Workflow State Management: Update task statuses, propagate parent rollups, validate dependencies, manage review comments, and append results.
  • Dashboard and Migration: Serve or export live task-tree dashboards and migrate legacy PLAN.md and RESULTS.md workflows.
  • Use Case: Give an AI coding agent a multi-stage research or implementation project, then use the task tree to dispatch ready tasks, preserve findings and review notes, and hand unfinished work to another agent without losing project context.

Quick Start

Use the task-tree skill to inspect the current task frontier, implement the next dispatchable task, record its results, and update its status for review.

Frequently Asked Questions about task-tree

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

FAQPage Schema
How do I maintain AI agent project context without losing track of unreviewed work?

Task tree management stores AI-assisted project state in a durable, structured task tree instead of transient agent context. It tracks task statuses, validates dependencies, and preserves review comments to prevent projects from drifting from objectives.

How do I migrate legacy plan files into a structured task tree workflow?

Migrating legacy plan files involves importing existing PLAN.md and RESULTS.md workflows into a YAML-backed task tree. This conversion establishes durable task metadata, enabling dashboard export, dependency validation, and DAG queries for ongoing project orchestration.

Can I query the task dependency DAG to find dispatchable tasks for my AI agents?

Yes, you can query the task dependency DAG and frontier views to identify dispatchable tasks. The Python CLI provides DAG and frontier queries, sibling dependency validation, and atomic task updates to orchestrate multi-stage execution.

Does task tree orchestration work for multi-stage research workflows and coding projects?

Task tree orchestration applies to coding projects, research workflows, and multi-stage analysis. It dispatches ready tasks to AI agents, preserves findings in comment sidecars, and allows handing unfinished work to another agent without losing context.

Do I need Python and pyyaml to use this task tree management system?

Yes, task tree management requires a Python environment with the pyyaml dependency installed. The system operates through a Python CLI that handles status rollups, worktree discovery, and YAML-backed task metadata storage.

What is the best way to monitor task status rollups across a complex project?

Monitoring task status rollups is best handled by exporting or serving a live task-tree dashboard. The system propagates parent rollups from child task statuses, providing a dashboard export feature to visualize project progress and review queued work.