A Claude Code plugin for knowledge-graph-driven development (KGDD). PRD and Plan as structured Node/Edge/Fact graphs, enabling AI Agents to work with full spec traceability — from user stories to source code — with automated review, multi-Agent execution, testing, visualization, and a built-in design system.
Visualize PRD/Plan knowledge graphs as interactive force-directed diagrams. Parses Graph + Facts sections from design documents and produces a self-contained HTML visualization.
Execute assigned Agent tasks from the Plan. Loads assigned Phase Nodes and Facts, implements code changes, validates specs with evidence, and writes back Plan deviations.
Extract structured knowledge graphs from existing materials (documents, code, or both). Produces a source-traced knowledge base with domain/application/story Nodes, optionally extended with Package/Symbol Nodes from code.
Model implementation plans as a Code-layer knowledge graph (Package/Symbol Nodes + Edges + Facts organized by Phase). Maps PRD specs to Plan specs via implements relationships and assigns Agents for execution.
Model product requirements as a Product-layer knowledge graph (domain/application/story Nodes + Edges + Facts). Produces a PRD document with spec traceability for downstream Plan implementation.
Generate E2E test skeletons from PRD + Plan. Creates version test index (README.md) and bone-skeleton test files with test.todo placeholders, categorized by verification type (AUTO/AGENT/HUMAN).