Sparc Methodology
- 1k installs
- 67k repo stars
- Updated August 4, 2026
- ruvnet/ruflo
sparc-methodology is an agent skill that enforces a repeatable five-phase SPARC workflow—specification, pseudocode, architecture, refinement, and completion—before and during feature implementation.
About
sparc-methodology is a ruflo skill backed by bash init and review scripts that scaffold a five-phase SPARC workflow for every new feature. Running the init script with a feature name creates ./docs/sparc/$FEATURE_NAME/ and five phase files: 1-specification.md, 2-pseudocode.md, 3-architecture.md, 4-refinement.md, and 5-completion.md. A companion review script runs phase checklist reviews. Developers reach for sparc-methodology when agents tend to jump straight to code and need enforced thinking steps—spec first, pseudocode second, architecture third—documented on disk. The methodology suits greenfield features or large refactors where traceable phase artifacts matter more than speed on tiny patches.
- 5-phase structured workflow: Specification, Pseudocode, Architecture, Refinement, Completion
- Creates dedicated markdown files for each phase inside docs/sparc/
- Includes automated review checklist script to verify all phases are complete
- Hard gate: complete specification and pseudocode before architecture work
- Next-skill handoff: approved SPARC artifacts feed directly into implementation agents
Sparc Methodology by the numbers
- 1,019 all-time installs (skills.sh)
- +3 installs in the week ending Aug 5, 2026 (Skillselion tracking)
- Ranked #468 of 3,282 Productivity & Planning skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/ruvnet/ruflo --skill sparc-methodologyAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 1k |
|---|---|
| repo stars | ★ 67k |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 4, 2026 |
| Repository | ruvnet/ruflo ↗ |
How do you structure feature planning before writing code?
Follow a repeatable 5-phase workflow that forces clear thinking before writing any code.
Who is it for?
Developers who want agents to document specification, pseudocode, and architecture in five ordered SPARC phases before implementation.
Skip if: One-line hotfixes or teams that already enforce ADRs and specs outside SPARC folder conventions.
When should I use this skill?
The user starts a new feature, asks for SPARC workflow, or needs specification and architecture docs before coding.
What you get
docs/sparc feature directory with five phase markdown files and completed phase review checklists.
- specification.md
- architecture.md
- completion checklist
By the numbers
- Creates 5 phase markdown files per feature
- Scaffolds docs/sparc/$FEATURE_NAME/ directory structure
Files
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-leadScripts
| 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
#!/bin/bash
# SPARC Methodology - Init Script
# Initialize SPARC workflow for a new feature
set -e
FEATURE_NAME="${1:-new-feature}"
echo "Initializing SPARC workflow for: $FEATURE_NAME"
# Create SPARC documentation directory
mkdir -p "./docs/sparc/$FEATURE_NAME"
# Create phase files
touch "./docs/sparc/$FEATURE_NAME/1-specification.md"
touch "./docs/sparc/$FEATURE_NAME/2-pseudocode.md"
touch "./docs/sparc/$FEATURE_NAME/3-architecture.md"
touch "./docs/sparc/$FEATURE_NAME/4-refinement.md"
touch "./docs/sparc/$FEATURE_NAME/5-completion.md"
echo "SPARC workflow initialized in ./docs/sparc/$FEATURE_NAME"
#!/bin/bash
# SPARC Methodology - Review Script
# Run SPARC phase review checklist
set -e
FEATURE_DIR="${1:-.}"
echo "SPARC Phase Review Checklist"
echo "============================="
for phase in specification pseudocode architecture refinement completion; do
if [ -f "$FEATURE_DIR/${phase}.md" ]; then
echo "[x] $phase - found"
else
echo "[ ] $phase - missing"
fi
done
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493kHow it compares
Use sparc-methodology when phased markdown artifacts must exist on disk; use lightweight todo skills for single-file task breakdowns.
FAQ
How many SPARC phases does sparc-methodology create?
sparc-methodology creates five SPARC phases as separate markdown files: specification, pseudocode, architecture, refinement, and completion under ./docs/sparc/$FEATURE_NAME/.
What scripts ship with sparc-methodology?
sparc-methodology ships bash init and review scripts; the init script mkdirs the SPARC docs path and touches all five phase files for a given feature name.
Is Sparc Methodology safe to install?
skills.sh reports 3 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.