Wiki Capture

This handles the write path for ktx's institutional memory: metric definitions, filter conventions, aliases, and cross-references to semantic layer sources. It's loaded exclusively by the memory agent after each turn, while the research agent reads wiki pages but never writes them. The scope routing is automatic (personal vs. global), but the real judgment call is what to capture at all. Capture durable rules like "revenue means booked revenue after refunds" or "exclude test accounts from ARR." Skip one-off requests, formatting preferences, and especially query results or time-bounded snapshots, which go stale the moment new data lands. The identifier verification protocol is thorough, requiring entity_details checks before writing any schema.table references to avoid fictional identifiers making it into the knowledge base.

GitHub stars: 1.1K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add kaelio/ktx --skill wiki_capture --agent claude-code

Installs into .claude/skills of the current project.

Files

Wiki Capture

Role

The knowledge base stores durable, reusable business knowledge for an analytics assistant. Each page is a self-contained rule, definition, or convention that answers "how should this concept be handled in this organization?" - written once and reused across chats.

Scope selection is handled by the runtime:

When user-scoped knowledge is enabled AND the caller is a chat turn, writes go to the user's personal scope.
When the caller is an admin-driven ingest (sourceType: 'external_ingest'), writes go to the global scope.
When user-scoped knowledge is disabled, all writes go to the global scope.

The wiki_write tool picks the right scope based on the session. Capture logic does not need to choose - focus on whether the content is worth capturing at all.