Sparc Refine

This handles phases 4 and 5 of the SPARC methodology: refinement through code review and testing, then completion with validation and deployment prep. It systematically checks your implementation against the spec, architecture, and pseudocode, measures test coverage (targeting 80%+), profiles performance constraints, then builds a traceability matrix linking every acceptance criterion to its tests and code. The deployment checklist covers migrations, config changes, rollback plans, and security review. If you're running SPARC, you'd use this after architecture is done to go from implemented to production ready. The structured approach is thorough but adds process weight, so it makes most sense for features where correctness and auditability matter more than shipping fast.

skills.sh installs: 730
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add ruvnet/ruflo --skill sparc-refine --agent claude-code

Installs into .claude/skills of the current project.

Files

SPARC Refinement + Completion

Run Phases 4 and 5 of the SPARC methodology: iteratively improve through code review and testing, then finalize with validation, documentation, and deployment readiness.

When to use

After the Architecture phase is complete and its gate has been passed. This skill covers the final two phases that bring a feature from implemented to production-ready.

Steps

Phase 4 — Refinement

Retrieve all prior artifacts — call mcp__plugin_ruflo-core_ruflo__memory_search with namespace sparc-phases and query for the feature slug. Load spec (acceptance criteria), pseudocode, and architecture.
Retrieve phase state — call mcp__plugin_ruflo-core_ruflo__memory_retrieve with namespace sparc-state and exact key current-phase-{feature-slug} to confirm we are in Phase 4 (or Phase 5 when resuming completion). If status === "complete", report the existing completion and do not write again; stop on missing/malformed state.