What problem does it solve?
Maintaining a large, up-to-date research wiki with accurate cross-links and complete concept coverage is extremely time-consuming for human operators, and manual gap identification often misses thin or stub content that degrades knowledge graph quality.
Core Features & Use Cases
- Automated Gap Discovery: Identifies high-priority stub pages, thin coverage, and unresolved open questions in the wiki, with priority elevation for stubs linked to active concept clusters.
- Knowledge Graph & Wiki Integration: Uses Synapse MCP tools to query the Neo4j knowledge graph, traverse hidden relationships, and write curated, properly tagged concept pages directly to the Obsidian wiki vault.
- End-to-End Research Pipeline: Ingests web sources (academic papers, articles, documentation) via built-in tools, archives them to the wiki clippings library, and generates structured summary pages with correct frontmatter and cross-links.
Use case: For a team maintaining an AI research wiki, this skill automatically finds incomplete stubs on emerging topics like constitutional AI, fetches relevant arXiv papers, and writes fully linked, sourced concept pages to fill knowledge gaps without manual intervention.
Quick Start
Use the researcher-agent skill to fill the top-priority stub page from your carryover file with a fully sourced, cross-linked concept page.
