Sl

If you're working with pre-defined business metrics like ARR, churn, or retention in ktx's data warehouse, this is your entry point. The semantic layer is a YAML catalog that wraps tables and views with reusable measures, computed columns, joins, and named segments. You read the schema to understand what's available, then use `sl_query` to generate correct SQL without worrying about join paths or fanout. It handles three flavors: overlays that enrich manifest tables, standalone table sources, and SQL sources. The skill is read-only for research agents. If you need to capture new patterns into the catalog, that's a separate `sl_capture` skill.

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

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Semantic Layer

ktx's semantic layer (SL) is a structured catalog. Each source represents a table, a SQL view, or an overlay that enriches a manifest-backed table with measures, computed columns, joins, and named segments. The catalog is the single source of truth for reusable business metrics.

This skill covers two parts:

Part 1 - Schema reference (what an SL source looks like).
Part 2 - Querying via sl_query.

Capture (when and how to add new patterns to the SL) is a separate concern handled by the memory-agent - see the sl_capture skill if you are running in capture mode. The research agent reads and queries the SL via the tools described here; it does not write to it.

For capture-time identifier verification, load sl_capture. Synthesis writer skills must verify warehouse identifiers with discover_data, entity_details, and sql_execution before emitting table or column names.