Kaelio

Maps dbt `schema.yml` / `properties.yml` models and sources to KTX semantic-layer overlays and column notes. It covers `sources:` vs `models:`, column `data_tests`, and how bundle-time writes complement manifest backfill, loading when `dbt_ingest` is active or dbt YAML files are present.

Classify and resolve conflicts detected during bundle ingest, including structural duplicates, definitional contradictions, near-duplicate clusters, re-ingest changes, and evictions.

KTX's semantic layer is a structured catalog of sources (tables/views), measures, joins, and segments expressed as YAML. It covers the schema and how to query it via `sl_query`.

Use when answering a question that needs data from a KTX-connected database - investigating, analyzing, how many, show me, what's the breakdown of, finding records by value, exploring tables, comparing periods, explaining metrics, or any data-analysis request. Triggers even when the user does not say "analytics"; if the answer requires querying a configured KTX connection, this skill applies.

Capture semantic-layer and knowledge updates from a live database schema snapshot.

How to capture new reusable patterns into KTX's semantic layer, determining when a measure, segment, or join belongs in the catalog and writing it generically for long-term utility. This is loaded by the post-turn memory-agent only; the research agent does not write to the SL.

Synthesize durable KTX wiki pages and semantic-layer sources from staged Notion pages, databases, data-source rows, and clustered Notion evidence. Load when a WorkUnit contains Notion raw files or Notion evidence chunks.

Maps a LookML view/model/explore to KTX semantic layer sources, covering the LookML to KTX primitive table, provenance tagging, and three worked examples (overlay, standalone from derived_table, standalone with sql_always_where). It loads when the turn contains `.lkml` content.

Installs and configures ktx, the open-source context layer for data agents. It runs ktx setup non-interactively, configures database connections and embeddings, installs agent integration, and verifies readiness, typically used when adding ktx to a project or troubleshooting an install.

Extracts durable KTX knowledge and semantic-layer contribution proposals from staged Looker runtime dashboard, Look, and explore JSON. Loads for WorkUnits whose raw files are under explores/, dashboards/, or looks/.

Converts historical SQL table usage data into typed evidence for deterministic schema projection.

This skill maps MetricFlow semantic models or metrics into KTX semantic layer sources, covering primitive table mapping, inheritance flattening, various metric types, and model resolution with four examples. It loads when .yml or .yaml files with top-level semantic_models: or metrics: are present.

Identify recurring cross-table historic-SQL analytical intents from a bounded pattern shard and emit typed pattern evidence for deterministic wiki projection.

Converts Metabase questions, models, and metrics into KTX Semantic Layer source definitions, covering result-metadata to KSL column type mapping, FK/PK detection, near-duplicate deduplication, pre-aggregation decomposition, join-graph connectivity, and reaction to priorProvenance from earlier ingest syncs. It loads when the WorkUnit contains `cards/<id>.json` files under a Metabase bundle.

KTX's knowledge base comprises wiki pages for durable, reusable business knowledge, covering user preferences, metric definitions, and organizational conventions, with cross-references to semantic-layer sources. It is loaded by the post-turn memory-agent, and while the research agent can read it, it cannot write to it.