sparc-methodology

Coordinate multi-agent software development across SPARC phases and 17 modes.

1|Updated Nov 13, 2025
One-click install
npx skills add https://github.com/Cornjebus/amair --skill sparc-methodology-cornjebus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sparc-methodology
Source: https://github.com/Cornjebus/amair/tree/main/.claude/skills/sparc-methodology
Command: npx skills add https://github.com/Cornjebus/amair --skill sparc-methodology-cornjebus

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a structured, efficient, and quality-focused development framework that leverages multi-agent AI to overcome the challenges of ad-hoc processes, inconsistent quality, and slow development cycles.

Core Features & Use Cases

  • SPARC Development Phases: Guides through Specification, Pseudocode, Architecture, Refinement (TDD), and Completion phases for systematic development.
  • 17 Specialized Modes: Access modes like coder, architect, tdd, reviewer, researcher, optimizer, debugger, and documenter for every development need.
  • Multi-Agent Orchestration: Utilizes hierarchical, mesh, sequential, parallel, and adaptive patterns for efficient agent coordination.
  • Test-Driven Development (TDD): Integrates a Red-Green-Refactor cycle with comprehensive testing strategies for high code quality.
  • Memory Integration: Ensures persistent knowledge sharing and context preservation across agents and sessions.
  • Use Case: Orchestrate a full-stack feature development, starting with a researcher to gather requirements, an architect to design, a tdd agent to implement with tests, and a reviewer for quality assurance.

Quick Start

Execute a specific SPARC mode for a task: mcp__claude-flow__sparc_mode { mode: "coder", task_description: "implement user authentication with JWT", options: { test_driven: true } } Run a complete TDD workflow for a new feature: npx claude-flow sparc tdd "shopping cart feature with payment integration"

Frequently Asked Questions about sparc-methodology

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

FAQPage Schema
How do I coordinate multiple AI agents for software development?

Multi-agent orchestration using SPARC methodology coordinates specialized agents (architect, coder, tdd, reviewer) across sequential, parallel, and hierarchical patterns. Agents share memory and context to manage Specification, Pseudocode, Architecture, Refinement, and Completion phases end-to-end.

What is test-driven development integration in a multi-agent workflow?

TDD integration in SPARC implements the Red-Green-Refactor cycle with dedicated test agents that write tests before implementation. This ensures comprehensive testing strategies and high code quality across parallel agent collaboration.

Can I use SPARC methodology for full-stack feature development?

Yes. SPARC orchestrates full-stack features through role-based modes: researcher gathers requirements, architect designs systems, tdd agent implements with tests, and reviewer ensures quality assurance across all phases.

How does memory sharing work across SPARC agents in development?

Memory integration ensures persistent knowledge sharing and context preservation between agents and sessions. This enables coordinated decision-making, consistent architecture adherence, and efficient handoffs across the 17 SPARC modes.

What development phases does SPARC structure cover?

SPARC guides through five systematic phases: Specification (requirements), Pseudocode (logic outline), Architecture (design), Refinement (TDD implementation), and Completion (deployment, documentation, monitoring, and API contracts).

Does SPARC include CI/CD integration and deployment management?

Yes. SPARC covers end-to-end lifecycle management including CI/CD integration, deployment orchestration, monitoring setup, and documentation generation as part of the Completion phase.