skill-analytics

Aggregate Aeon skill run data into fleet-wide rankings and anomaly reports.

Updated Jun 2, 2026
One-click install
npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill skill-analytics-atrium-hermes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-analytics
Source: https://github.com/Atrium-Hermes/atrium-lighthouse/tree/main/skills/skill-analytics
Command: npx skills add https://github.com/Atrium-Hermes/atrium-lighthouse --skill skill-analytics-atrium-hermes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Fleet-wide visibility into Aeon skills performance over a rolling window, enabling operators to see which skills run most, which fail, and where degradations or quiet runs occur.

Core Features & Use Cases

  • Fleet-wide ranking of skills by run counts within the target window.
  • Health signals and anomaly flags including success rates and exit taxonomy distribution.
  • Automated reports and dashboards that guide maintenance, governance, and optimization.

Quick Start

Run the Skill Analytics workflow to generate the latest fleet-wide performance report for all skills within the configured window.

Frequently Asked Questions about skill-analytics

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

FAQPage Schema
How do I analyze fleet-wide skill performance and run data across a rolling window?

Fleet-wide analytics aggregate run data across a selected window to detect silent schedules, characterize exit taxonomies from logs, and present fleet-wide rankings alongside anomaly signals for decision making.

What are silent schedules in skill analytics and how are they detected?

Silent schedules are detected by cross-referencing configured schedules and cron-state against fetched run data, identifying scheduled skills that produced no execution records within the configured rolling window.

How do I generate a dashboard spec and automated report from skill logs?

You generate a dashboard spec and report by running scripts that fetch run data, parse daily logs for exit taxonomy, and produce an article plus a dashboard spec for distribution across the fleet.

Can I rank scheduled skills by run counts and success rates for maintenance decisions?

Yes, you can rank scheduled skills by run counts within a target window to surface health signals, success rates, and exit taxonomy distributions that guide maintenance, governance, and optimization decisions.

Do I need any dependencies to run fleet-wide analytics on Aeon skills?

No external dependencies are required. The Skill leverages internal scripts to fetch run data, cross-reference schedules and cron-state, parse daily logs, and generate the analytics article and dashboard spec.