Loading...
Loading...
Found 3 Skills
Cube.js integration. Manage data, records, and automate workflows. Use when the user wants to interact with Cube.js data.
Run a Cube.js query against the semantic model and show the result inline in chat as an ASCII table and (where it makes sense) an ASCII bar chart. Use whenever the user asks a business question that can be answered from the cubes — "how many orders…", "top N…", "revenue by…", "trend over time", "compare X to Y" — or explicitly asks to "query the semantic model", "run a cube query", "show me a chart", "plot…", "graph…". Discovers measures and dimensions via `revos cubes meta`, executes the query with `revos cubes query`, and renders the results without leaving the chat.
Answer business questions about the org's RevOS data directly in chat by querying its live semantic model over MCP — "how many orders…", "revenue by…", "top N…", "trend over time…", "compare X to Y…" — and schema-discovery questions like "what's in my semantic model", "what can I query", "list cubes/datasets/fields", "describe a cube" — or when explicitly asked to "query the semantic model", "run a cube query", "show me a chart", "plot…", "graph…". Use this whenever you would otherwise call the RevOS api_read tool against the `cubes` resource directly — this skill is what turns its raw JSON into a rendered table, a chart when the shape fits, a safe choice of join path when a query spans multiple cubes, and a plain-English explanation, instead of a dumped tool result. This applies even when the question names a specific source system (HubSpot, Zammad, Exact Online, …) — answer aggregate/analytical questions from the semantic model, not a direct source connector.