Sparc Implement

Takes you from SPARC spec to working code by running phases 2 and 3 together. First it pulls your specification from memory, designs language-agnostic pseudocode with complexity annotations, then establishes module boundaries following DDD patterns with explicit API contracts and directory structure. The architecture piece is opinionated about dependency direction and separating types from services from data access. Once design is done, it can immediately implement the actual code and tests if you confirm. Stores everything in namespaced memory so later phases can retrieve decisions. Honestly most useful if you're already bought into the full SPARC methodology, otherwise it's a lot of ceremony for what could be straightforward coding.

skills.sh installs: 735
GitHub stars: 81.4K
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

SPARC Architecture + Implementation

Run Phases 2 and 3 of the SPARC methodology: design algorithms with pseudocode, then establish architecture with module boundaries and API contracts.

When to use

After the Specification phase is complete and its gate has been passed. This skill covers both the Pseudocode and Architecture phases as they are tightly coupled — algorithm design informs module boundaries and vice versa.

Steps

Retrieve specification — call mcp__plugin_ruflo-core_ruflo__memory_search with namespace sparc-phases and query for the feature's spec. Extract requirements, acceptance criteria, constraints, and edge cases.
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 2 or 3.
Search for architectural patterns — call mcp__plugin_ruflo-core_ruflo__neural_predict with the feature description to find relevant architectural decisions from past projects