Run natural-language BI analysis with OpenChatBI agents
Deploy OpenChatBI when an agent needs to turn business questions into SQL, charts, anomaly analysis, and explainable BI results.
npx skills add agentskillexchange/skills --skill run-natural-language-bi-analysis-with-openchatbi-agents
pip install openchatbi, configure the target database/catalog and LLM settings, then run the CLI or sample Gradio/Streamlit interface to ask natural-language BI questions.Use OpenChatBI when a user needs an agentic BI workflow that can inspect a data catalog, translate natural-language questions into SQL, run analysis code, visualize results, and escalate complex cases to its analysis agent. Invoke this instead of using a BI product normally when the job is conversational investigation across database schema, metrics, forecasting, anomaly detection, or root-cause drill-down, and the operator needs the agent to produce query-backed evidence rather than a dashboard click path. The scope boundary is the OpenChatBI analyst-agent workflow and its configured database/catalog/MCP tools; it is not a generic LangChain/LangGraph framework listing or a broad BI platform card.
What this skill actually does
Inputs and prerequisites: Python, pip, database connection, configured LLM provider, optional MCP tools, optional Gradio or Streamlit UI.
Setup notes: Install with pip install openchatbi , configure the target database/catalog and LLM settings, then run the CLI or sample Gradio/Streamlit interface to ask natural-language BI questions.
Source and verification boundary: use https://zhongyu09.github.io/openchatbi/ as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.