Skill UI

A persistent knowledge base that transcends standard RAG by integrating three core layers: raw source storage, a structured knowledge graph, and a dynamic wiki layer. It ingests documents once, automatically extracting entities and relations to build a comprehensive, cross-referenced, and verifiable knowledge graph. Ideal for enterprise research, complex Q&A, and deep knowledge accumulation.

This skill guides users through the installation and configuration of the OpenViking long-term memory plugin for OpenClaw. It enables the system to automatically capture crucial facts from conversations and recall relevant context across sessions (auto-capture + auto-recall). It is designed for users who do not know CLI commands, making advanced, knowledge-based chat capabilities accessible via natural conversation.

This skill addresses the gap in research wiki maintenance by automatically populating scaffolded paper sections (Problem, Method, Results, etc.). It implements the Karpathy LLM-wiki principle, fetching content from multiple external sources (e.g., arXiv, AlphaXiv) and using advanced summarization to rewrite placeholder TODOs into detailed, structured prose. Ideal for transforming raw research scaffolds into comprehensive, LLM-maintained knowledge bases.

A self-hosted, semantic memory service designed for AI agents. It allows agents to save worklogs, decisions, and notes, and recall this knowledge across sessions based on meaning rather than exact keywords. Using pgvector and structured workspaces, it maintains persistent, context-aware knowledge bases, making it ideal for collaborative AI projects.