ktx-ai-data-agents-context
Installation
SKILL.md
ktx AI Data Agents Context
Skill by ara.so — AI Agent Skills collection.
ktx is an executable context layer that teaches AI agents (Claude Code, Codex, Cursor, OpenCode) how to query your data warehouse accurately. It automatically builds and maintains a semantic layer from your warehouse metadata, dbt projects, LookML, Looker, Metabase, and wiki content - then serves it to agents through CLI and MCP tools with full-text and semantic search.
What ktx Does
- Learns from company knowledge: Ingests wiki content, dbt docs, Looker, Metabase - organizes it, removes duplicates, flags contradictions
- Maps the data stack: Samples tables, detects joinable columns, annotates sources so agents write better queries
- Builds a semantic layer: Combines raw tables and metrics through a join graph that resolves chasm and fan traps automatically
- Serves agents at execution: Exposes CLI and MCP tools for Claude Code, Codex, Cursor, OpenCode to query context