ktx-ai-data-agents-context — Claude Code skill: install
The ktx-ai-data-agents-context skill configures ktx as context for agents querying a data warehouse. Use it to bring schema, metric definitions, and business knowledge into MCP-powered data work.
no license 145 installs ★ 9 updated 2026-10-09
npx skills add reason-machines/mcp-skills --skill ktx-ai-data-agents-context -a claude-codeWhat ktx-ai-data-agents-context does
The skill guides setup of ktx, a context layer that gathers warehouse structure, metric definitions, and business knowledge for AI agents. It can ingest sources such as dbt, Looker, Metabase, and Notion, then expose searchable context through MCP. Warehouse access is read-only.
Run ktx setup to configure an LLM provider, an embeddings provider, a database, and context sources. The listed database options include PostgreSQL, Snowflake, BigQuery, ClickHouse, MySQL, SQL Server, and SQLite. Provider API keys may be required; without a database connection, ktx cannot build warehouse context.
Use ktx ingest to refresh indexed sources, ktx status to check project readiness, and ktx sl to search metrics and dimensions. Project configuration and semantic-layer files can be committed, while .ktx/ holds local state and secrets and is git-ignored.
What it helps with
- assemble warehouse context from schema and business rules
- search for metric and dimension definitions
- connect an agent to warehouse context through MCP
- spot conflicting metric and wiki definitions
Example prompts for the agent
- Set up ktx for my warehouse and connect the agent through MCP.
- Build context from dbt and find the revenue metrics.
- Check the ktx project status and refresh the warehouse index.
How to install ktx-ai-data-agents-context
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill ktx-ai-data-agents-context -a claude-code2Manually: put the files in place
~/.claude/skills/ktx-ai-data-agents-context/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ktx-ai-data-agents-context/
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill ktx-ai-data-agents-context -a codex2Manually: put the files in place
.agents/skills/ktx-ai-data-agents-context/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill ktx-ai-data-agents-context -a cursor2Manually: put the files in place
.cursor/skills/ktx-ai-data-agents-context/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/mcp-skills skills/ktx-ai-data-agents-context2Manually: put the files in place
.github/skills/ktx-ai-data-agents-context/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill ktx-ai-data-agents-context -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/ktx-ai-data-agents-contextManually: put the files in place
.devin/skills/ktx-ai-data-agents-context/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill ktx-ai-data-agents-context -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about ktx-ai-data-agents-context
How do I install ktx-ai-data-agents-context in Claude Code?
Run npx skills add reason-machines/mcp-skills --skill ktx-ai-data-agents-context -a claude-code. The skill file is at ~/.claude/skills/ktx-ai-data-agents-context/SKILL.md.
What does ktx-ai-data-agents-context do?
It helps configure ktx so an agent can search warehouse structure, metric definitions, and business context, then access that context through MCP.
Which databases can I connect?
The setup lists PostgreSQL, Snowflake, BigQuery, ClickHouse, MySQL, SQL Server, and SQLite. Context sources include dbt, LookML, Looker, Metabase, and Notion.