insight_query

Query triad-based data and return insights, charts, and entities.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/huangxn27/broadband-agent-demo --skill insight-query
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: insight_query
Source: https://github.com/huangxn27/broadband-agent-demo/tree/main/backend/skills/insight_query
Command: npx skills add https://github.com/huangxn27/broadband-agent-demo --skill insight-query

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ce_insight_core, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Enables structured triad-based data queries and multi-function insights to surface meaningful measurements, trends, and entities for operational decisions.

Core Features & Use Cases

  • Triad query support: Retrieve data using dimensions, breakdown, and measures to form a precise analysis scope.
  • 12 insights functions: Execute a variety of insight computations (e.g., OutstandingMin, Trend, Correlation) and return chart_configs, significance, and found_entities.
  • Streaming results: Provide structured outputs suitable for downstream visualization and decision making.

Quick Start

Run an insight query with a prepared payload to obtain chart configurations and discovered entities.

Frequently Asked Questions about insight_query

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate automated insights and chart configurations from multi-dimensional data queries?

You can run triad-based data queries using dimensions, breakdowns, and measures to automatically generate chart configurations, significance scores, and found entities for operational decisions.

What are triad queries and when do I need them for KPI tracking?

Triad queries define an analysis scope using dimensions, breakdown, and measures. You need them for KPI tracking and performance dashboards where quick, structured interpretation of multi-dimensional data is required.

How do I set up a payload to query data and surface significance and anomalies?

Prepare a payload with query_config, table_level, and data_path parameters. Executing this returns fixed_query_config, data_shape, records, and chart_configs to visualize anomalies and trends.

Can I use this for performance dashboards if I only have raw multi-dimensional data?

Yes, it targets data-analytic scenarios like performance dashboards and anomaly detection by processing raw multi-dimensional data to execute 12 insight computations such as Trend, Correlation, and OutstandingMin.

Does insight_query require the ce_insight_core dependency to function?

Yes, it satisfies the inputs and outputs contract of ce_insight_core, requiring this dependency to process query configurations and return structured streaming results suitable for downstream visualization.

What limitations should I expect when running trend and correlation computations on my data?

It returns fix_warnings alongside fixed_query_config if issues arise during triad-based querying, indicating data shape or configuration corrections needed before executing the 12 insight functions reliably.