skills.rest
optimaxin
optimaxinCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

sparc-methodology

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

Updated Jul 16, 2026
Search Tags:#tdd#code review#software development#swarm#sparc#multi-agent orchestration#claude-flow
One-click install
npx skills add https://github.com/optimaxin/Tredev_Gems --skill sparc-methodology-optimaxin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: sparc-methodology
Source: https://github.com/optimaxin/Tredev_Gems/tree/main/.claude/skills/sparc-methodology
Command: npx skills add https://github.com/optimaxin/Tredev_Gems --skill sparc-methodology-optimaxin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Coordinating complex software development across specification, architecture, implementation, testing, and review phases is error-prone and slow 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. - Multi-Agent Orchestration: Supports hierarchical, mesh, ring, and star swarm topologies with parallel execution for 2.8-4.4x speed improvements and cross-agent memory sharing. - TDD Workflows: Built-in red-green-refactor cycles targeting 90%+ test coverage, plus sequential pipelines from research through deployment. - Use Case: To build a full-stack authentication feature, initialize a hierarchical swarm, then run researcher, architect, coder (test-driven), tdd, and reviewer modes in sequence, with memory storing architectural decisions across agents. ## Quick Start Ask the AI to run the SPARC pipeline for your feature, for example: use the sparc-methodology skill to design and implement a JWT authentication API with test-driven development and a security review.

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 with Claude Flow?▼

Run a SPARC mode using the MCP tool mcp__claude-flow__sparc_mode with a mode name and task description, or via CLI with npx claude-flow sparc run <mode> "task". You can list all modes with npx claude-flow sparc modes.

What is the SPARC methodology in software development?▼

SPARC stands for Specification, Pseudocode, Architecture, Refinement, and Completion. It is a systematic development methodology that progresses through requirements definition, system design, test-driven implementation, code review, and deployment phases.

How do I run a full TDD workflow with Claude Flow?▼

Use npx claude-flow sparc tdd "feature description" to execute a test-driven workflow, or chain modes manually: researcher, architect, tdd with a coverage target, then reviewer. The tdd mode follows the red-green-refactor cycle targeting 90% coverage.

Can I use SPARC modes without MCP tools?▼

Yes, use the NPX CLI fallback with commands like npx claude-flow sparc run <mode> "task" or npx claude-flow@alpha for alpha features. A local installation also supports ./claude-flow sparc run <mode> "task".

Which swarm topology should I choose for multi-agent orchestration?▼

Use hierarchical topology for complex projects with clear delegation, mesh for peer-to-peer collaborative tasks, and adaptive strategy for dynamic workloads. Sequential pipelines suit ordered workflows from specification through review.

What are the limitations of parallel agent execution?▼

Parallel execution works best for independent tasks; dependent steps like testing must wait for implementation to finish. Define dependencies explicitly in task orchestration, and use memory integration so agents share architectural decisions and context.

Related Skills

Explore More Software Engineering Skills→
marjorgmarjorg
1

to-spec

Synthesizes conversation context into a structured spec published to the project issue tracker.

Community
Intermediate
treasure-datatreasure-data
21

field-agent-deployment

Manage Field Agent deployment and release workflows across environments.

Official
Advanced
kaiganikaigani
30

producer

Execute multi-step plans by invoking skills sequentially and validating outputs against doneness criteria.

Community
Advanced
sylvandingsylvanding
9

orchestrating-swarms

Coordinate multiple autonomous AI agents for multi-step software engineering workflows.

Community
Advanced