dtask

Manage task lifecycle states from draft to acceptance via task.json.

4|Updated Feb 21, 2026
One-click install
npx skills add https://github.com/ssdiwu/diwu-workflow --skill dtask
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dtask
Source: https://github.com/ssdiwu/diwu-workflow/tree/main/skills/dtask
Command: npx skills add https://github.com/ssdiwu/diwu-workflow --skill dtask

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a complete framework for managing tasks from initial draft through acceptance, using a state-machine and a standardized task.json to coordinate planning, execution, and verification.

Core Features & Use Cases

  • State machine driven lifecycle with InDraft, InSpec, InProgress, InReview, Done, and Cancelled.
  • Acceptance format based on GWT (Given-When-Then) to ensure verifiable outcomes.
  • Standard task.json structure including id, title, description, acceptance, steps, category, blocked_by, and status.
  • Clear guidance for planning, decomposition, blocking dependencies, and commit messaging to streamline collaboration.
  • Supports multi-agent workflows with guidelines for parallel and serial task execution.

Quick Start

Describe a new feature as a task, draft its acceptance criteria, and initialize a task.json in InDraft.

Frequently Asked Questions about dtask

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

FAQPage Schema
How do I manage task lifecycle from draft to acceptance using a state machine?

Task lifecycle management uses a state machine with statuses like InDraft, InProgress, InReview, and Done to track tasks from creation to acceptance. It enforces structured state transitions and progress tracking via a standardized task.json schema.

How do I write verifiable acceptance criteria for project planning tasks?

Verifiable acceptance criteria are written using the Given-When-Then (GWT) format. This ensures task outcomes are clearly defined and testable, structuring requirements into preconditions, actions, and expected results within the task.json file.

What is the best way to handle task dependencies and blocked_by relationships in workflow planning?

Workflow planning handles task dependencies by defining blocked_by relationships within the task.json structure. This tracks serial and parallel execution prerequisites, ensuring downstream tasks wait for upstream completion during project execution.

Can I use task.json for multi-agent collaboration and parallel execution?

Yes, task.json supports multi-agent collaboration by providing guidelines for parallel and serial task execution. The standardized schema coordinates multiple agents by tracking shared task statuses, blocking dependencies, and progress.

Does task lifecycle management require specific commit messaging formats?

Task lifecycle management provides clear guidance for commit messaging to streamline collaboration. It links code changes directly to structured tasks using the task.json schema, ensuring commits reference tracked workflow states.

What is the task.json schema used for feature decomposition and project execution?

The task.json schema structures feature decomposition by defining id, title, description, acceptance, steps, category, blocked_by, and status. It provides a standardized format for tracking project execution from initial draft to final acceptance.