Ktx Analytics

Turns natural language questions into queries against a ktx-connected database. It discovers tables and semantic layers first, validates business values like company names or statuses before filtering, and prefers the semantic layer over raw SQL when possible. The workflow is thorough: it inspects schema details, plans the grain and metrics, runs the query, then validates results. It also calls memory_ingest to capture business rules and schema gotchas for future sessions. Good for exploratory analysis where you don't know the schema cold or need to compare periods and break down metrics. The dictionary search step is smart: it looks up actual values in the warehouse instead of guessing spelling or case, though it warns you the index is sampled so a miss isn't definitive.

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

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

ktx Analytics Workflow

You have access to ktx MCP tools for data discovery, semantic-layer analysis, raw read-only SQL, wiki context, and memory ingest. Follow this workflow.

SKILL.md on GitHub

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly