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.
npx -y skills add kaelio/ktx --skill wiki_capture --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
supercent-io/skills-template
supercent-io/skills-template
huangjia2019/claude-code-engineering
reactjs/react.dev
reactjs/react.dev