mcpField
S
sparc-methodology

sparc-methodology

github.com/ruvnetDevelopment80.0k1.2k installsUpdated today
Repository

About sparc-methodology

sparc-methodology is a Claude Flow skill that structures complex development work into Specification, Pseudocode, Architecture, Refinement, and Completion. It is intended for feature, integration, and redesign tasks that benefit from planning before implementation.

Key features

  1. 01Structure work into five SPARC phases
  2. 02Define requirements and acceptance criteria
  3. 03Plan implementation with pseudocode and architecture
  4. 04Refine designs using feedback
  5. 05Complete work with tests and documentation

Use cases

  1. 01Plan a complex new feature before coding
  2. 02Structure architectural changes or system redesign
  3. 03Coordinate integration work with unclear requirements

MCP support

The skill routes SPARC phase tasks through the Claude Flow CLI and can spawn a SPARC coordinator agent; it does not specify MCP server capabilities.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/ruvnet/ruflo --skill sparc-methodology

After installing, type/sparc-methodologyin Claude Code to confirm it loaded.

Bundled filesscripts/sparc-init.shscripts/sparc-review.sh

Details

From the project README

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

npx @claude-flow/cli hooks route --task "specification: [requirements]"

Example:

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

npx @claude-flow/cli hooks route --task "pseudocode: [feature]"

Example:

npx @claude-flow/cli hooks route --task "pseudocode: OAuth2 login flow with token refresh"
Architecture Phase

Design system structure, interfaces, and dependencies

npx @claude-flow/cli hooks route --task "architecture: [design]"

Example:

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

npx @claude-flow/cli hooks route --task "refinement: [feedback]"

Example:

npx @claude-flow/cli hooks route --task "refinement: add rate limiting and brute force protection"
Completion Phase

Finalize implementation with tests and documentation

npx @claude-flow/cli hooks route --task "completion: [final checks]"

Example:

npx @claude-flow/cli hooks route --task "completion: verify all tests pass, update API docs, security review"
SPARC Coordinator

Spawn SPARC coordinator agent

npx @claude-flow/cli agent spawn --type sparc-coord --name sparc-lead

Scripts

ScriptPathDescription
sparc-init.agents/scripts/sparc-init.shInitialize SPARC workflow for a new feature
sparc-review.agents/scripts/sparc-review.shRun SPARC phase review checklist

References

DocumentPathDescription
SPARC Overviewdocs/sparc.mdComplete SPARC methodology guide
Phase Templatesdocs/sparc-templates.mdTemplates 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

Comments

Markdown supported