orchestrator

Decompose large specifications into atomic tasks with dependencies and acceptance criteria.

4|1|Updated Oct 8, 2025

Search Tags:#AI workflow #task decomposition #quality gates #BDD mapping #DDD co-located #dependency DAG

Ready to run

npx skills add https://github.com/deMGoncalves/documentation-first-approach --skill orchestrator-demgoncalves

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: orchestrator
Source: https://github.com/deMGoncalves/documentation-first-approach/tree/main/.claude/skills/orchestrator
Command: npx skills add https://github.com/deMGoncalves/documentation-first-approach --skill orchestrator-demgoncalves

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires analyst, architect.

What problem does it solve?

This skill enables reliable transformation of large specifications into a set of atomic tasks, minimizing context per task to prevent AI hallucinations and misinterpretations.

Core Features & Use Cases

BDD-driven mapping: Converts given scenarios into domain-driven components and atomic tasks.
Co-located DDD structure: Encourages organized, domain-focused directories per aggregate to keep work cohesive.
Quality gates & context controls: Enforces max task size (<100 LOC) and limited context (~500 lines) to maintain determinism.
Use Case: Given a 5,000-line spec, the orchestrator outputs a complete tasks.md with 8-12 atomic tasks, explicit dependencies, and acceptance criteria.

Quick Start

Start the workflow by invoking the orchestrator to decompose an approved spec into tasks. Use:

@skill orchestrator
/workflow start "Implement authentication flow"

Frequently Asked Questions about orchestrator

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

FAQPage Schema

How do I decompose large specifications into atomic tasks to prevent AI hallucinations?▼

To decompose large specifications into atomic tasks and prevent AI hallucinations, use deterministic task decomposition to break down work into traceable chunks. This enforces strict context limits (~500 lines) and task sizes (<100 LOC) with clear acceptance criteria, minimizing misinterpretations.

What is BDD-to-DDD mapping for AI workflow task generation?▼

BDD-to-DDD mapping for AI workflows converts given scenarios into domain-driven components and atomic tasks. It encourages a co-located DDD directory structure per aggregate, ensuring work remains cohesive and explicitly mapped to behavioral specifications.

How do I establish task dependencies and context limits for a 5,000-line spec?▼

To establish task dependencies and context limits for a 5,000-line spec, apply deterministic task decomposition targeting Phase 3.5. This outputs a tasks.md file with 8-12 atomic tasks, explicit dependency DAGs, and strict context controls (~500 lines per task).

Does the orchestrator skill require an analyst or architect dependency?▼

Yes, the orchestrator skill requires analyst and architect dependencies. It relies on these preceding roles to supply the approved specifications needed to generate atomic tasks, establish dependencies, and enforce quality gates.

What is the best way to enforce quality gates and max task size in AI workflows?▼

The best way to enforce quality gates and max task size in AI workflows is through deterministic task decomposition. This approach enforces strict limits (<100 LOC per task, ~500 lines context) and ensures each task has clear acceptance criteria for reliable implementation.

When should I not use deterministic task decomposition for AI workflows?▼

You should not use deterministic task decomposition for AI workflows when dealing with small, loosely defined specifications that do not require strict context limits or dependency DAGs. It is specifically designed for large specifications needing strict quality gates and traceability.