KaelioOfficial·17 Agent Skills Included

ktx

Teaches AI agents to query your data warehouse accurately

Builds a self-improving context layer so AI agents query your warehouse with approved metric definitions instead of inventing SQL. Ingests schemas, dbt models, Looker, Metabase, Notion, and wiki knowledge, then detects joinable columns and flags contradictions. Serves agents through CLI and MCP tools with semantic search, eliminating wrong numbers and repeated warehouse exploration.

1,570|101

↗

npx skills add Kaelio/ktx --all -g -y

Available:

Gives AI agents working in this repository strict operating rules for task tracking, testing, package management, and design decisions when modifying the ktx codebase.

All Skills in This Repository (17)

Pure Emerald Level Indicators

📦 In Repo

Kaelio

notion_synthesize

Synthesize Notion pages and databases into wiki entries with citations.

sl

Query pre-defined business metrics through a YAML semantic layer catalog.

sl_capture

Captures reusable metrics, segments, and joins into ktx semantic layer YAML sources.

historic_sql_table_digest

Convert historic SQL table usage buckets into typed table usage evidence for schema projection.

dbt_ingest

Maps dbt schema.yml models and sources into ktx semantic-layer overlays and column notes.

lookml_ingest

Convert LookML views, models, and explores into ktx semantic layer sources.

looker_ingest

Extracts ktx knowledge and semantic-layer proposals from staged Looker dashboard, Look, and explore JSON.

metabase_ingest

Convert Metabase questions, models, and metrics into ktx Semantic Layer source definitions.

sigma_ingest

Extracts durable wiki knowledge from staged Sigma data model specs and workbook summaries.

gdrive_synthesize

Synthesizes durable KTX wiki pages from staged Google Drive document pulls.

historic_sql_patterns

Identifies recurring cross-table analytical intents from historic SQL shards and emits typed pattern evidence.

live_database_ingest

Converts live database schema snapshots into semantic-layer sources and wiki pages.

Official

Advanced

Frequently Asked Questions

FAQPage Schema

How to install ktx?▼

Run `npx skills add Kaelio/ktx --all -g -y` in your terminal to install the full ktx skill suite globally.

What problem does ktx solve for data teams?▼

It stops AI agents from inventing their own metric logic by giving them approved definitions, join paths, and business knowledge pulled automatically from your warehouse and docs.

Which databases and tools does ktx support?▼

It works with PostgreSQL, Snowflake, BigQuery, MySQL, DuckDB, and more, and ingests context from dbt, Looker, Metabase, MetricFlow, Notion, and Google Drive.

Does ktx work with Claude Code and other AI agents?▼

Yes. ktx exposes CLI and MCP tools that plug directly into Claude Code, Codex, Cursor, and OpenCode using your own LLM keys or local sign-in.

Is my warehouse data safe with ktx?▼

Yes. ktx runs locally with read-only connections, and the only data leaving your machine is what you send to your chosen LLM provider.