CORTEXSKILLS

Master orchestrator — end-to-end guide for building on Cortex. Routes you to the right skill at each phase of development.

Deploy MOCA Library via Docker or Coolify. All 50+ environment variables, first steps, and health checks.

API key management with 4 permission tiers (read, manage, admin). X-API-Key auth, session security, and prompt injection protection.

Document ingestion for PDF, DOCX, XLSX, PPTX, HTML, images, audio, and LaTeX. Chunking config, batch processing, custom inputs, and vision analysis.

Hybrid search combining vector similarity (0.5), keyword matching (0.3), and graph traversal (0.2). RRF fusion with cross-encoder re-ranking.

RAG-powered Q&A with streaming SSE, agentic multi-step reasoning, deep research mode, conversation history, and collection scoping.

Knowledge graph operations — 10 entity types, typed relationships, subgraph queries, multi-hop traversal, and semantic entity resolution.

Organize documents by team, project, or use case. Scoped knowledge graphs, bulk operations, and document assignment.

Automatic entity clustering via Louvain algorithm. LLM-generated community summaries that enrich RAG context and discovery.

GPU-accelerated inference via Compute3. Start/stop dedicated B200 GPU jobs with per-second billing for massive document uploads.

Connect Cortex to LangChain, CrewAI, AutoGen, LangGraph, ElizaOS, MCP, Slack bots, webhooks, and automation platforms.

App ecosystem — YouTube Importer, Web Crawler, Notion Sync, Slack Archive Importer, Research Dashboard, API Playground, and custom builds.

Sync agent memory files to a Cortex Library knowledge graph for enhanced retrieval, hybrid search (vector + keyword + graph), AI-powered Q&A with agentic deep research, and knowledge graph exploration.

The Bold Typography design system for Cortex-ecosystem UIs. Dark mode, orange accent, sharp edges, Inter Tight + JetBrains Mono, and full component specs.