メニュー
SPARC development methodology for systematic test-driven development
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation.
Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing.
Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern.
Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.
MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring for sub-100ms response times.
Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).
| name | sparc-methodology |
| description | SPARC development methodology for systematic test-driven development |
| version | 1.0.0 |
| invocable | true |
| author | agentic-flow |
| capabilities | ["specification","pseudocode","architecture","refinement","completion"] |
Systematic Test-Driven Development using SPARC (Specification, Pseudocode, Architecture, Refinement, Completion).
# Run complete TDD workflow
npx agentic-flow@alpha sparc tdd "implement user authentication"
# Run specific phase
npx agentic-flow@alpha sparc run specification "auth system"
npx agentic-flow@alpha sparc run pseudocode "auth system"
npx agentic-flow@alpha sparc run architect "auth system"
npx agentic-flow@alpha sparc run refinement "auth system"
npx agentic-flow@alpha sparc run completion "auth system"
# Batch execution
npx agentic-flow@alpha sparc batch "spec-pseudocode,architect" "feature X"
Define requirements and acceptance criteria.
Agent: specification
Output: Requirements doc, test cases
Command:
npx agentic-flow@alpha sparc run spec "user login feature"
Design algorithms and logic flow.
Agent: pseudocode
Output: Algorithm design, flow diagrams
Command:
npx agentic-flow@alpha sparc run pseudo "auth flow"
System design and component structure.
Agent: architecture
Output: Component diagram, API design
Command:
npx agentic-flow@alpha sparc run arch "microservices layout"
Iterative TDD implementation.
Agent: refinement
Output: Tests + Implementation
Command:
npx agentic-flow@alpha sparc run refine "auth module"
Integration and deployment.
Agent: completion
Output: Integrated system, docs
Command:
npx agentic-flow@alpha sparc run complete "auth system"
Additional specialized modes:
| Mode | Description |
|---|---|
dev | General development |
api | API design |
ui | UI/UX development |
test | Testing focus |
refactor | Code improvement |
debug | Bug investigation |
security | Security review |
devops | CI/CD setup |
# Full TDD cycle
npx agentic-flow@alpha sparc tdd "implement OAuth2"
# This runs:
# 1. Specification: Define requirements
# 2. Pseudocode: Design algorithm
# 3. Architecture: Plan structure
# 4. Refinement: Write tests first, then implement
# 5. Completion: Integrate and document
SPARC uses specialized agents:
// Via Claude Code Task tool
Task("Specification agent", "Define requirements for OAuth", "specification")
Task("Architecture agent", "Design OAuth architecture", "architecture")
Task("Coder agent", "Implement OAuth with TDD", "sparc-coder")
Task("Tester agent", "Verify OAuth implementation", "tester")
Task("Reviewer agent", "Review OAuth code quality", "reviewer")