Sparc Methodology
Run a five-document SPARC workflow so complex features are specified, sketched, architected, refined, and completed before you let the agent write production code.
Overview
SPARC Methodology is an agent skill most often used in Build (also Validate, Ship) that walks you through five written phases—specification, pseudocode, architecture, refinement, and completion—before committing to compl
Install
npx skills add https://github.com/ruvnet/ruflo --skill sparc-methodologyWhat is this skill?
- Initializes a 5-phase SPARC doc tree: specification, pseudocode, architecture, refinement, completion
- Bash init script creates ./docs/sparc/<feature>/ with numbered markdown phase files
- Review script prints a phase checklist for missing or present markdown gates
- Explicit use triggers: new features, architectural changes, integrations, unclear requirements
- Explicit skip triggers: trivial fixes, docs-only edits, well-scoped small tasks
- 5-phase SPARC workflow (specification through completion)
- Init script creates 5 numbered markdown phase files per feature
Adoption & trust: 648 installs on skills.sh; 58.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are starting a large or ambiguous feature with an coding agent and risk shipping architecture debt because planning lives only in chat history.
Who is it for?
Solo builders kicking off multi-file features, system redesigns, or integration projects where requirements still need hardening.
Skip if: One-line bug fixes, config tweaks, pure documentation edits, or tasks that already have an approved spec and bounded scope.
When should I use this skill?
New feature implementation, complex implementations, architectural changes, system redesign, integration work, or unclear requirements.
What do I get? / Deliverables
You get a numbered SPARC documentation set per feature plus a checklist-verified gate so implementation proceeds only after each phase file exists.
- Per-feature SPARC folder with five phase markdown files
- Phase presence checklist output from review script
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Canonical shelf is Build because SPARC is an implementation methodology that produces spec-through-completion artifacts for features you are about to or are actively building. PM subphase fits structured planning artifacts (spec, pseudocode, architecture) that solo builders use to govern agent-driven feature work.
Where it fits
Turn unclear integration requirements into a specification.md before estimating build time.
Sequence pseudocode and architecture docs so the agent implements against fixed interfaces.
Document refinement decisions before wiring a third-party API across services.
Run the phase review script to confirm completion.md exists before release review.
How it compares
Use instead of jumping straight from a vague prompt to codegen when you need a written phase gate, not a single-shot code generator.
Common Questions / FAQ
Who is sparc-methodology for?
Indie and solo developers who use AI coding agents on non-trivial features and want a repeatable planning ritual before implementation.
When should I use sparc-methodology?
During Validate when scoping is still fuzzy, during Build when starting features or integrations, and during Ship when architectural changes need documented refinement before merge.
Is sparc-methodology safe to install?
Review the Security Audits panel on this Prism page and treat bundled shell scripts as trusted only after you read what they create on disk.
SKILL.md
READMESKILL.md - Sparc Methodology
#!/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 --- 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/sp