sl

1# Semantic Layer
2 
3ktx'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.
4 
5This skill covers two parts:
6- **Part 1** - Schema reference (what an SL source looks like).
7- **Part 2** - Querying via `sl_query`.
8 
9Capture (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.
10 
11For capture-time identifier verification, load `sl_capture`. Synthesis writer
12skills must verify warehouse identifiers with `discover_data`,
13`entity_details`, and `sql_execution` before emitting table or column names.
14 
15---
16 
17## Part 1 - Schema reference
18 
19An SL source is a YAML file under `semantic-layer/<connectionId>/`. The file's `name:` field is the source's identity — it mirrors the warehouse identifier verbatim (e.g. Snowflake's uppercase `SIGNED_UP`); the filename is only a derived label. Always address sources by name through the `sl_*` tools, never by file path. There are three flavors:
20 
21### Overlay sources
22…