SPARC development workflow (Specification, Pseudocode, Architecture, Refinement, Completion). Use when: new features, complex implementations, architectural changes. Skip when: simple fixes, documentation, configuration.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add ruvnet/ruflo --skill sparc-methodology --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Sparc Methodology?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ruvnet-sparc-methodology-ac8b34bc)More formats (shields.io, HTML) on the badges page.
---
name: sparc-methodology
description: >
SPARC development workflow (Specification, Pseudocode, Architecture, Refinement, Completion).
Use when: new features, complex implementations, architectural changes.
Skip when: simple fixes, documentation, configuration.
---
# Sparc Methodology Skill
## Purpose
SPARC development workflow (Specification, Pseudocode, Architecture, Refinement, Completion).
## When to Trigger
- new features
- complex implementations
- architectural changes
## When to Skip
- simple fixes
- documentation
- configuration
## Commands
### Specification Phase
Define requirements and acceptance criteria
```bash
npx @claude-flow/cli hooks route --task "specification: [requirements]"
```
### Architecture Phase
Design system structure
```bash
npx @claude-flow/cli hooks route --task "architecture: [design]"
```
## 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
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...