What problem does it solve? Coordinating complex software development across specification, architecture, implementation, testing, and review phases is error-prone when done ad hoc. This Skill provides a structured SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) methodology with 17 specialized modes and multi-agent orchestration via Claude Flow. ## Core Features & Use Cases - Phased Development Framework: Five defined phases from specification through completion, each mapped to specialized modes like researcher, architect, coder, tdd, and reviewer. - Multi-Agent Orchestration: Swarm initialization with hierarchical, mesh, ring, or star topologies, parallel agent execution, and cross-agent memory sharing. - TDD Workflows: Red-green-refactor cycles with coverage targets (90%+), supporting Jest, Vitest, Playwright, and Cypress. - Use Case: Building a full-stack feature — run the researcher mode to gather requirements, architect to design the system, coder with test_driven options to implement, then reviewer for security and performance checks, all coordinated through MCP tools or the npx claude-flow CLI. ## Quick Start Ask the AI to run the SPARC pipeline for your feature, for example: use the sparc methodology to design, implement, and test a user authentication feature with JWT.
