
Transforms raw Notion pages, databases, and evidence clusters into permanent wiki entries and semantic-layer sources inside a knowledge management system. The workflow is rigid: read assigned Notion content, search for overlapping wiki pages to avoid duplicates, pull supporting evidence chunks, then write consolidated pages that cite exact source paths and last-edited dates. It handles collision detection by searching existing wiki entries and semantic-layer sources before creating new ones, and includes a fallback protocol when Notion references warehouse tables that don't exist or lack connection mappings. The identifier verification steps are thorough, requiring entity_details and sql_execution probes to confirm every schema.table reference actually resolves before committing it to memory. Built for memory_agent callers working through staged Notion content in batches.
$ npx -y skills add kaelio/ktx --skill notion_synthesize --agent claude-codeInstalls into .claude/skills of the current project.
Use this skill when a WorkUnit contains staged Notion content from pages/**, databases/**, data-sources/**, or clustered Notion evidence.
Each WorkUnit is either a single Notion page/span or a topical cluster of related Notion pages, pre-grouped by embedding similarity. Read the assigned raw files, then write a small set of durable wiki entries and, when applicable, semantic-layer sources that synthesize the WorkUnit's knowledge. Write final memory directly; do not write candidates.
Sponsors