sparc-methodology

Coordinate multi-agent software development across specification, design, implementation, testing, and deployment phases.

Updated Sep 21, 2025
One-click install
npx skills add https://github.com/Filipcsupka/cv-web --skill sparc-methodology-filipcsupka
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sparc-methodology
Source: https://github.com/Filipcsupka/cv-web/tree/main/.agents/skills/sparc-methodology
Command: npx skills add https://github.com/Filipcsupka/cv-web --skill sparc-methodology-filipcsupka

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) is a comprehensive development methodology designed to coordinate multi-agent workflows across the software lifecycle, enabling systematic planning, parallel execution, and memory-backed collaboration.

Core Features & Use Cases

  • 17 specialized modes for end-to-end software development, including researcher, architect, coder, tdd, reviewer, and memory-manager
  • Structured phases: Specification, Architecture, Refinement, Review, and Completion with guidance on best practices
  • Cross-agent orchestration patterns and memory integration to share decisions, design notes, and validation results across sessions

Quick Start

Begin a SPARC sprint by initializing a hierarchical swarm and assigning the core modes (researcher, architect, coder, tdd, reviewer) to coordinate a feature from specification to completion.

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 workflows for end-to-end software development?

The SPARC methodology coordinates multi-agent software development through five phases: Specification, Pseudocode, Architecture, Refinement, and Completion, using 17 specialized modes to ensure rigorous phase-based planning.

How do I share memory and design decisions across multiple AI agents during a project?

You share memory across multiple AI agents using cross-agent orchestration patterns and memory integration, which propagate design notes, decisions, and validation results across different specialized modes and sessions.

What is the best way to structure test-driven development within a multi-agent architecture?

Structuring TDD within a multi-agent architecture involves assigning dedicated TDD and reviewer modes to execute tests and perform quality-focused reviews, ensuring validation occurs during the refinement phase.

Does multi-agent orchestration work for software projects requiring parallel execution and rigorous planning?

Yes, multi-agent orchestration supports software projects requiring parallel execution by deploying a hierarchical swarm that enables parallel execution, allowing specialized agents to handle architecture and implementation simultaneously.

When do I need a structured phase-based development methodology for my software project?

You need a structured phase-based development methodology when your software project requires systematic planning from specification to deployment, rigorous quality-focused reviews, and coordinated parallel execution across multiple agents.