operator-scorecard

Synthesize health, growth, and economic signals into a weekly operator scorecard.

626|225|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/aaronjmars/aeon --skill operator-scorecard-aaronjmars
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: operator-scorecard
Source: https://github.com/aaronjmars/aeon/tree/main/skills/operator-scorecard
Command: npx skills add https://github.com/aaronjmars/aeon --skill operator-scorecard-aaronjmars

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Operator Scorecard turns scattered internal signals into one weekly, plain-language check of whether Aeon's autonomous activity was actually worth it.

Core Features & Use Cases

  • Weekly agent health synthesis: Summarizes fleet run success, anomalies, and heartbeat verdicts to produce a clear health paragraph.
  • Community growth rollup: Aggregates repo star/fork deltas and identifies new contributor signals into a growth paragraph.
  • Economic activity summary: Totals AEON distribution and reports token 7-day performance into an economic activity paragraph.

Quick Start

Request a weekly operator notification by running operator-scorecard for the default 7-day window (or a custom retrospective window) using the var parameter.

Frequently Asked Questions about operator-scorecard

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

FAQPage Schema
How do I generate a weekly agent health and economic activity report?

You can generate a weekly agent health report by running a scorecard that synthesizes heartbeat logs, repo pulse, and token reports into a plain-language verdict. It scans local files read-only to compute whether autonomous activity was worthwhile.

What is a worst-of-three rollup for autonomous agent operations?

A worst-of-three rollup is a deterministic method for computing weekly agent health verdicts by evaluating health, growth, and economic signals. It applies the weakest of the three scores to ensure conservative status reporting.

Can I run a custom retrospective window for agent reporting instead of 7 days?

Yes, you can run a custom retrospective window for agent reporting by passing a var parameter. This overrides the default 7-day window to analyze specific historical periods of agent operations and economic activity.

Does weekly agent reporting support idempotent artifact generation for dashboards?

Yes, weekly agent reporting supports idempotent artifact generation for dashboards. This ensures repeated runs over the same reporting window produce identical, deterministic output files without duplicating data or overwriting prior results.

What local log formats are required to synthesize agent community growth and token performance?

Synthesizing community growth and token performance requires local read-only access to skill-analytics, heartbeat, repo pulse, tweet allocator, and memory logs. The scorecard scans these specific log files to aggregate deltas and report token performance.