sparc-methodology

Coordinate SPARC-driven software development across specification, architecture, refinement, and completion.

75|17|Updated Jan 11, 2026
One-click install
npx skills add https://github.com/smith-horn/skillsmith --skill sparc-methodology-smith-horn
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sparc-methodology
Source: https://github.com/smith-horn/skillsmith/tree/main/.claude/skills/sparc-methodology
Command: npx skills add https://github.com/smith-horn/skillsmith --skill sparc-methodology-smith-horn

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

SPARC methodology provides a structured approach to complex software development by coordinating multiple agents and phases, bridging specification through completion, with memory coordination and test-driven workflows to reduce risk and accelerate delivery.

Core Features & Use Cases

  • SPARC modes: 17 specialized modes covering orchestration, development, analysis, and support.
  • Memory integration: cross-agent knowledge persistence for coherent decisions across phases.
  • TDD workflow: test-first development to improve quality and maintainability.
  • Flexible orchestration: supports hierarchical, mesh, and adaptive swarm patterns for large teams and projects.
  • Use Cases: Plan architecture for large systems, run complete development pipelines, research and innovate with multi-agent teams.

Quick Start

Use a mode to initiate the SPARC workflow, for example: mcp__claude-flow__sparc_mode { mode: "researcher", task_description: "gather requirements for SPARC system" }

mcp__claude-flow__sparc_mode { mode: "architect", task_description: "design scalable SPARC-enabled architecture" }

Frequently Asked Questions about sparc-methodology

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

FAQPage Schema
How do I coordinate multi-agent software development across complex project phases?

Multi-agent orchestration for complex software development is managed by the SPARC methodology, which coordinates tasks across specification, architecture, refinement, and completion phases. It supports hierarchical, mesh, and adaptive swarm patterns to structure large teams and maintain cross-agent knowledge persistence.

How does test-driven development integrate with multi-agent orchestration workflows?

Test-driven development integrates into multi-agent orchestration workflows through a test-first approach applied across the development pipeline. This TDD-driven quality assurance ensures that design, testing, and deployment phases are validated by memory-enabled workflows, improving overall software maintainability and reducing delivery risk.

What is the best way to structure architecture for large systems using multiple agents?

Structuring architecture for large systems using multiple agents requires flexible orchestration patterns like hierarchical, mesh, or adaptive swarm configurations. These patterns coordinate specialized modes to plan system architecture, execute development pipelines, and maintain coherent decisions through cross-agent memory persistence.

Can I use adaptive swarm orchestration for complex software architecture design?

Adaptive swarm orchestration can be used for complex software architecture design within a structured methodology framework. It supports large teams by dynamically coordinating specialized modes and memory-enabled workflows, allowing agents to collaborate on system design, refinement, and completion.

When should I use a formal multi-agent development framework over standard development pipelines?

A formal multi-agent development framework should be used when projects require complex orchestration, cross-agent memory coordination, and test-driven quality assurance across multiple phases. It is suited for large systems where bridging specification through completion with specialized modes reduces risk and accelerates delivery.

Why does memory coordination matter for cross-agent decisions in software development?

Memory coordination matters for cross-agent decisions because it provides knowledge persistence across different development phases. This ensures that architectural choices and refinements made by one agent remain coherent and accessible to others, maintaining consistency throughout the specification and completion pipeline.