What problem does it solve?
Projects with multiple languages and independent language servers suffer from fragmented code intelligence, slow cross-references, and inconsistent navigation results; this Skill unifies heterogeneous LSP clients into a single semantic graph so editors and web UIs can deliver fast, consistent go-to-definition, hover, and reference queries across a polyglot codebase.
Core Features & Use Cases
- Multi-LSP Orchestration: Initialize and manage concurrent LSP clients (TypeScript, PHP, Go, Rust, Python) with proper capability negotiation and lifecycle management.
- Semantic Graph Construction: Transform LSP responses into a unified graph of file and symbol nodes with typed edges for contains/imports/calls/references and maintain strict graph consistency.
- Real-time Incremental Indexing: Produce nav.index.jsonl and LSIF import/export artifacts, stream graph diffs via WebSocket, and persist caches in SQLite/JSON for fast startup and incremental updates.
- Performance & Scale Targets: Designed to meet sub-100ms lookup goals, aggressive but precise caching, batching of LSP requests, and strategies for handling 25k–100k+ symbols with low memory overhead.
- Use Case: Power a web-based code explorer that provides instant cross-language navigation and live symbol updates after commits or file saves.
Quick Start
Start the LSP orchestrator on your project root to initialize TypeScript and PHP language servers, build the semantic graph, and generate a nav.index.jsonl navigation index.