workflow-decompose

Decompose approved requirement specs into atomic traceable tasks with dependency DAGs.

1|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/NestorMonroy/thyrox --skill workflow-decompose-nestormonroy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: workflow-decompose
Source: https://github.com/NestorMonroy/thyrox/tree/main/.claude/skills/workflow-decompose
Command: npx skills add https://github.com/NestorMonroy/thyrox --skill workflow-decompose-nestormonroy

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Turning an approved requirements specification into executable work often produces vague, oversized tasks with no traceability, causing duplicated or lost work during implementation. This Skill converts specs into atomic T-NNN tasks with dependency graphs and full SPEC-to-task traceability. ## Core Features & Use Cases - Atomic Task Decomposition: Generates task-plan.md files with checkbox tasks (T-NNN) where each task touches exactly one location and can be committed independently. - Dependency DAG & Traceability: Documents a Mermaid dependency graph, execution phases, and a reverse SPEC-to-task coverage table so orphan tasks and scope creep are detected. - Parallel Execution Marking: Flags parallelizable tasks with [P] markers and supports task claiming conventions for multi-agent execution. - Use Case: After finishing a requirements spec for a new feature, run this Skill to produce a task plan with 20 atomic tasks, a Mermaid DAG showing the critical path, and a coverage table proving every requirement maps to at least one task before any code is written. ## Quick Start Ask the assistant to decompose the active work package's requirements spec into an atomic task plan with dependency DAG and SPEC traceability.

Frequently Asked Questions about workflow-decompose

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

FAQPage Schema
How do I break down a requirements spec into executable tasks?▼

Read the requirements spec for the active work package, then create a task-plan.md listing atomic tasks as checkboxes with unique T-NNN IDs, each referencing its source requirement (SPEC-N). Include a Mermaid dependency DAG and a SPEC-to-task coverage table.

What makes a task atomic in project planning?▼

A task is atomic if it touches exactly one location (one file or one section), contains no 'and' connecting two distinct operations, and can be committed and checked off independently. Tasks failing these checks must be decomposed further before proceeding.

How do I mark tasks for parallel execution in a task plan?▼

Mark parallelizable tasks with a [P] flag in the task list, for example '- [ ] [T-003] [P] Task description (SPEC-2)'. During parallel execution, use [~] to claim a task before working on it to prevent duplicate work.

When should I categorize issues before task decomposition?▼

Categorize first when the work involves more than 50 issues. Use the categorization plan template to group issues into prioritized batches by type, severity, or module before decomposing each batch into atomic tasks.

Why does task decomposition require a human approval gate?▼

The gate exists because the next phase modifies the repository directly. The complete task plan with all tasks listed must be presented and explicitly approved by the user before execution begins, with no exceptions.