sparc-methodology

Orchestrates multi-agent software development using the SPARC phased methodology with 17 specialized modes.

Updated May 11, 2026
One-click install
npx skills add https://github.com/Turgunoff/mebellar_app --skill sparc-methodology-turgunoff
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sparc-methodology
Source: https://github.com/Turgunoff/mebellar_app/tree/main/.agents/skills/sparc-methodology
Command: npx skills add https://github.com/Turgunoff/mebellar_app --skill sparc-methodology-turgunoff

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Coordinating complex software development across research, architecture, coding, testing, and review phases is error-prone when done ad hoc. This Skill provides a structured SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) methodology with multi-agent orchestration to run systematic, test-driven development workflows. ## Core Features & Use Cases - 17 Specialized Modes: Includes orchestrator, architect, coder, tdd, reviewer, researcher, analyzer, optimizer, debugger, documenter, and more, each with defined capabilities and usage patterns. - Multiple Orchestration Patterns: Supports hierarchical, mesh, sequential pipeline, parallel, and adaptive swarm topologies for coordinating agents. - TDD Workflows: Built-in red-green-refactor cycles with coverage targets (90%+) and integration with Jest, Playwright, and other test frameworks. - Use Case: To build a new authentication feature, run the researcher mode to gather requirements, architect to design the system, tdd to implement with tests, and reviewer to validate security and performance. ## 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 module with 90% coverage.

Frequently Asked Questions about sparc-methodology

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

FAQPage Schema
How do I run a SPARC mode for a development task?▼

Use the MCP tool mcp__claude-flow__sparc_mode with a mode name and task description, or run npx claude-flow sparc run <mode> "task" from the terminal. Modes include coder, architect, tdd, reviewer, and researcher.

What is the SPARC methodology in software development?▼

SPARC stands for Specification, Pseudocode, Architecture, Refinement, and Completion. It is a phased development methodology that emphasizes specification before code, test-driven implementation, and structured review before deployment.

How do I run a full TDD workflow with SPARC?▼

Run npx claude-flow sparc tdd "feature description" or invoke the tdd mode via MCP with a coverage target. The workflow follows red-green-refactor: write a failing test, implement minimal code to pass, then refactor while keeping tests green.

What swarm topologies does Claude Flow support?▼

Claude Flow supports hierarchical, mesh, ring, and star topologies, initialized via mcp__claude-flow__swarm_init. Hierarchical suits delegated projects, mesh suits peer collaboration, and adaptive strategies adjust to workload changes.

Can SPARC modes run in parallel?▼

Yes, independent modes can execute concurrently using parallel orchestration patterns or batch execution via npx claude-flow sparc batch <modes> "task". The documentation reports 2.8-4.4x speed improvements from parallel agent execution.

What are the limitations of the SPARC pipeline approach?▼

The full pipeline runs all phases sequentially, which may be excessive for small fixes or trivial changes. For simple tasks, invoking a single mode like coder or debugger directly is more appropriate than the complete pipeline.