compose

Coordinates an AI agent ensemble to plan, test, implement and review software projects with TDD and SOLID principles.

Updated Apr 30, 2026
One-click install
npx skills add https://github.com/PFigs/compose --skill compose-pfigs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: compose
Source: https://github.com/PFigs/compose/tree/main
Command: npx skills add https://github.com/PFigs/compose --skill compose-pfigs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Planning and executing software work end-to-end by coordinating a Jazz-era ensemble of named agents (Ella, Bird, Duke, Monk, Hawk, Django, Billie, Count) to drive structured planning, testing, implementation, and review with TDD and SOLID disciplines.

Core Features & Use Cases

  • End-to-end orchestration of planning, testing, implementation, and review across phases.
  • Dynamic, session-wide discovery and wiring of available skills at session start.
  • Adherence to TDD, SOLID + KISS / DRY / YAGNI across all phases.

Quick Start

Trigger a /compose session to initialize the ensemble and begin Phase 0 exploration.

Frequently Asked Questions about compose

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

FAQPage Schema
How do I coordinate end-to-end software planning and execution with AI agents?

The Skill manages agent orchestration by dynamically discovering and wiring available skills at session start, then coordinating the ensemble to apply TDD and SOLID principles for reliable software delivery.

Does this automated workflow enforce TDD and SOLID principles during implementation?

Yes, the automated workflow enforces TDD and SOLID principles across all phases, while also adhering to KISS, DRY, and YAGNI disciplines to ensure structured and reliable code delivery.

What's the best way to start a phased software planning session?

The best way to start a phased software planning session is to trigger the /compose command, which initializes the agent ensemble and begins Phase 0 exploration for your project.

Can I use agent orchestration for projects requiring automated decision-making and tool integrations?

Yes, you can use this agent orchestration for projects requiring phased governance and automated decision-making, as it dynamically wires available skills and applies tool integrations throughout the workflow.

What are the limitations of using a multi-agent ensemble for software workflow automation?

A limitation of this multi-agent ensemble is that it requires dynamic, session-wide discovery and wiring of available skills at startup, meaning your environment must support this initialization phase before execution begins.