xplor

Build a complete Xplor component from scratch — production-ready, Vercel-deployable.

Diagnose and fix Xplor issues — root cause analysis, exact file location, complete fix.

Merge multiple Xplor graphs (code + docs + skills) into a single queryable intelligence layer.

Scaffold a new skill graph with proper structure, frontmatter, and wikilinks — ready to score 85+.

Validate a skill graph directory and output a quality score (0-100) with actionable fixes.

Expert agent for building Xplor — the structured cognition engine. PROACTIVELY activate when users want to: (1) build or extend the Xplor knowledge graph platform, (2) implement Document/Code/Skill Graph modes, (3) build the MCP server or CLI, (4) create, validate, or scaffold skill graphs, (5) implement the Explorer UI, (6) debug graph traversal or progressive disclosure violations, (7) set up Firebase/Firestore/Stripe integration, (8) build force-directed graph visualizations, (9) implement attention scoring or traversal heuristics, (10) fuse multiple graphs into a multi-domain intelligence layer, (11) build the agent intelligence layer, (12) implement hybrid BM25 + semantic search. Full domain knowledge: graph-core data model, progressive disclosure (levels 0-4), attention scoring, traversal heuristics, wikilink parsing, MOC design, quality scoring, multi-domain fusion, all API contracts, CLI spec, MCP tool definitions.

Build Xplor — a structured cognition engine that transforms documents, codebases, and knowledge systems into traversable, AI-queryable knowledge graphs. Three modes: (1) Document Mode — PDFs to entity/relationship graphs with AI extraction. (2) Code Mode — repositories to function/class/call-chain graphs via AST parsing. (3) Skill Graph Mode — structured markdown knowledge systems with wikilinks, YAML frontmatter, and Maps of Content into navigable intelligence graphs for AI agents. Use this skill whenever the user wants to: build a knowledge graph platform, create a document intelligence tool, analyze codebases, build an MCP server for code or knowledge, create a skill graph engine, build agent cognition infrastructure, create a CLI for indexing repos or knowledge bases, build structured knowledge systems, create traversable skill networks with wikilinks, build something like DeepWiki but deeper, build "git for structured knowledge", create a "graph OS" for AI agents, or anything involving knowledge graphs + AI agents + structured traversal. Also trigger for: Next.js + Firebase + AI extraction, force-directed graph UIs, AST parsing with Tree-sitter, MCP server development, wikilink parsing, YAML frontmatter extraction, skill authoring tools, agent traversal telemetry, attention scoring, progressive disclosure systems, or multi-domain graph fusion. Even partial matches like "skill graph", "knowledge engine", "structured cognition", "agent context", "code explorer", "repo intelligence" should trigger this skill.