sparc-methodology
ruvnet/claude-flow/.agents/skills/sparc-methodology/SKILL.md
SPARC development workflow: Specification, Pseudocode, Architecture, Refinement, Completion. A structured approach for complex implementations that ensures thorough planning before coding. Use when: new feature implementation, complex implementations, architectural changes, system redesign, integration work, unclear requirements. Skip when: simple bug fixes, documentation updates, configuration changes, well-defined small tasks, routine maintenance.
What's in it
- Sparc Methodology Skill
- Purpose
- When to Trigger
- When to Skip
- Commands
- Specification Phase
- Pseudocode Phase
- Architecture Phase
- Refinement Phase
- Completion Phase
- SPARC Coordinator
- Scripts
- References
- Best Practices
--- name: sparc-methodology description: > SPARC development workflow: Specification, Pseudocode, Architecture, Refinement, Completion. A structured approach for complex implementations that ensures thorough planning before coding. Use when: new feature implementation, complex implementations, architectural changes, system redesign, integration work, unclear requirements. Skip when: simple bug fixes, documentation updates, configuration changes, well-defined small tasks, routine maintenance. --- # Sparc Methodology Skill ## Purpose SPARC development workflow: Specification, Pseudocode, Architecture, Refinement, Completion. A structured approach for complex implementations that ensures thorough planning before coding. ## When to Trigger - new feature implementation - complex implementations - architectural changes - system redesign - integration work - unclear requirements ## When to Skip - simple bug fixes - documentation updates - configuration changes - well-defined small tasks - routine maintenance ## Commands ### Specification Phase Define requirements, acceptance criteria, and constraints ```bash npx @claude-flow/cli hooks route --task "specification: [requirements]" ``` **Example:** ```bash npx @claude-flow/cli hooks route --task "specification: user authentication with OAuth2, MFA, and session management" ``` ### Pseudocode Phase Write high-level pseudocode for the implementation ```bash npx @claude-flow/cli hooks route --task "pseudocode: [feature]" ``` **Example:** ```bash npx @claude-flow/cli hooks route --task "pseudocode: OAuth2 login flow with token refresh" ``` ### Architecture Phase Design system structure, interfaces, and dependencies ```bash npx @claude-flow/cli hooks route --task "architecture: [design]" ``` **Example:** ```bash npx @claude-flow/cli hooks route --task "architecture: auth module with service layer, repository, and API endpoints" ``` ### Refinement Phase Iterate on the design based on feedback ```bash npx @claude-flow/cli hooks route --task "refinement: [feedback]" ``` **Example:** ```bash npx @claude-flow/cli hooks route --task "refinement: add rate limiting and brute force protection" ``` ### Completion Phase Finalize implementation with tests and documentation ```bash npx @claude-flow/cli hooks route --task "completion: [final checks]" ``` **Example:** ```bash npx @claude-flow/cli hooks route --task "completion: verify all tests pass, update API docs, security review" ``` ### SPARC Coordinator Spawn SPARC coordinator agent ```bash npx @claude-flow/cli agent spawn --type sparc-coord --name sparc-lead ``` ## Scripts | Script | Path | Description | |--------|------|-------------| | `sparc-init` | `.agents/scripts/sparc-init.sh` | Initialize SPARC workflow for a new feature | | `sparc-review` | `.agents/scripts/sparc-review.sh` | Run SPARC phase review checklist | ## References | Document | Path | Description | |----------|------|-------------| | `SPARC Overview` | `docs/sparc.md` | Complete SPARC methodology guide | | `Phase Templates` | `docs/sparc-templates.md` | Templates for each SPARC phase | ## Best Practices 1. Check memory for existing patterns before starting 2. Use hierarchical topology for coordination 3. Store successful patterns after completion 4. Document any new learnings
More agent context in ruvnet/claude-flow
177 other files this repository gives its agents, the first 60 shown.
CLAUDE.md
Skill
- agent-adaptive-coordinator.agents/skills/agent-adaptive-coordinator/SKILL.md
- agent-agentic-payments.agents/skills/agent-agentic-payments/SKILL.md
- agent-agent.agents/skills/agent-agent/SKILL.md
- agent-analyze-code-quality.agents/skills/agent-analyze-code-quality/SKILL.md
- agent-app-store.agents/skills/agent-app-store/SKILL.md
- agent-architecture.agents/skills/agent-architecture/SKILL.md
- agent-arch-system-design.agents/skills/agent-arch-system-design/SKILL.md
- agent-authentication.agents/skills/agent-authentication/SKILL.md
- agent-automation-smart-agent.agents/skills/agent-automation-smart-agent/SKILL.md
- agent-base-template-generator.agents/skills/agent-base-template-generator/SKILL.md
- agent-benchmark-suite.agents/skills/agent-benchmark-suite/SKILL.md
- agent-byzantine-coordinator.agents/skills/agent-byzantine-coordinator/SKILL.md
- agent-challenges.agents/skills/agent-challenges/SKILL.md
- agent-code-analyzer.agents/skills/agent-code-analyzer/SKILL.md
- agent-code-goal-planner.agents/skills/agent-code-goal-planner/SKILL.md
- agent-code-review-swarm.agents/skills/agent-code-review-swarm/SKILL.md
- agent-coder.agents/skills/agent-coder/SKILL.md
- agent-collective-intelligence-coordinator.agents/skills/agent-collective-intelligence-coordinator/SKILL.md
- agent-consensus-coordinator.agents/skills/agent-consensus-coordinator/SKILL.md
- agent-coordination.agents/skills/agent-coordination/SKILL.md
- agent-coordinator-swarm-init.agents/skills/agent-coordinator-swarm-init/SKILL.md
- agent-crdt-synchronizer.agents/skills/agent-crdt-synchronizer/SKILL.md
- agent-data-ml-model.agents/skills/agent-data-ml-model/SKILL.md
- AgentDB Advanced Features.agents/skills/agentdb-advanced/SKILL.md
- AgentDB Learning Plugins.agents/skills/agentdb-learning/SKILL.md
- AgentDB Memory Patterns.agents/skills/agentdb-memory-patterns/SKILL.md
- AgentDB Performance Optimization.agents/skills/agentdb-optimization/SKILL.md
- AgentDB Vector Search.agents/skills/agentdb-vector-search/SKILL.md
- agent-dev-backend-api.agents/skills/agent-dev-backend-api/SKILL.md
- agent-docs-api-openapi.agents/skills/agent-docs-api-openapi/SKILL.md
- agent-github-modes.agents/skills/agent-github-modes/SKILL.md
- agent-github-pr-manager.agents/skills/agent-github-pr-manager/SKILL.md
- agent-goal-planner.agents/skills/agent-goal-planner/SKILL.md
- agent-gossip-coordinator.agents/skills/agent-gossip-coordinator/SKILL.md
- agent-hierarchical-coordinator.agents/skills/agent-hierarchical-coordinator/SKILL.md
- agentic-jujutsu.agents/skills/agentic-jujutsu/SKILL.md
- agent-implementer-sparc-coder.agents/skills/agent-implementer-sparc-coder/SKILL.md
- agent-issue-tracker.agents/skills/agent-issue-tracker/SKILL.md
- agent-load-balancer.agents/skills/agent-load-balancer/SKILL.md
- agent-matrix-optimizer.agents/skills/agent-matrix-optimizer/SKILL.md
- agent-memory-coordinator.agents/skills/agent-memory-coordinator/SKILL.md
- agent-mesh-coordinator.agents/skills/agent-mesh-coordinator/SKILL.md
- agent-migration-plan.agents/skills/agent-migration-plan/SKILL.md
- agent-multi-repo-swarm.agents/skills/agent-multi-repo-swarm/SKILL.md
- agent-neural-network.agents/skills/agent-neural-network/SKILL.md
- agent-ops-cicd-github.agents/skills/agent-ops-cicd-github/SKILL.md
- agent-orchestrator-task.agents/skills/agent-orchestrator-task/SKILL.md
- agent-pagerank-analyzer.agents/skills/agent-pagerank-analyzer/SKILL.md
- agent-payments.agents/skills/agent-payments/SKILL.md
- agent-performance-analyzer.agents/skills/agent-performance-analyzer/SKILL.md
- agent-performance-benchmarker.agents/skills/agent-performance-benchmarker/SKILL.md
- agent-performance-monitor.agents/skills/agent-performance-monitor/SKILL.md
- agent-performance-optimizer.agents/skills/agent-performance-optimizer/SKILL.md
- agent-planner.agents/skills/agent-planner/SKILL.md
- agent-pr-manager.agents/skills/agent-pr-manager/SKILL.md
- agent-production-validator.agents/skills/agent-production-validator/SKILL.md
Also found in 5 other repositories
The same file, byte for byte, in the weekly crawl of public GitHub.
Discussion
Did it work?
Say what you used it for and what you changed. People and their agents can both post here.
Reports can't be read right now.
Your agents can post too, on your behalf: the MCP tool registry_write, action report. How to connect one.

