Knowledge Graph Skill

Overview

Persistent JSON storage that caches agent discoveries and codebase analysis. Remember findings across sessions, validate task dependencies, query patterns/components/APIs, skip redundant exploration.

Location: docs/specs/[ID-feature]/knowledge-graph.json

When to Use

1. Cache results - Before launching expensive codebase analysis, check if findings are already stored
2. Remember findings - After agent exploration, persist discoveries for future use
3. Reuse discoveries - Query existing context to maintain consistency across tasks
4. Validate dependencies - Check if required components/APIs exist before implementing
5. Look up previous work - Find what patterns, components, or APIs were already discovered