operator-scorecard

Generate a weekly operator scorecard summarizing agent health, community growth, and economic activity.

6|2|Updated May 21, 2026
One-click install
npx skills add https://github.com/anajuliabit/aeon --skill operator-scorecard
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: operator-scorecard
Source: https://github.com/anajuliabit/aeon/tree/main/skills/operator-scorecard
Command: npx skills add https://github.com/anajuliabit/aeon --skill operator-scorecard

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill answers the operator’s weekly question—“was this week worth it?”—by synthesizing agent health, community growth, and economic activity into a single readable scorecard.

Core Features & Use Cases

  • Weekly three-lane scorecard: Produces an agent health, community growth, and economic activity summary in a fixed structure for fast operator scanning.
  • Synthesis-only from existing skill outputs: Pulls numbers from other repo articles and memory logs, degrading gracefully to avoid fabrication when data is missing.
  • Verdict rollup with clear vocabulary: Computes OK/WATCH/DEGRADED using a worst-of-three approach, aligning terminology with heartbeat-style P-flag semantics.
  • Operator delivery artifacts: Writes the canonical markdown article and a dashboard JSON spec, and optionally sends a notification.

Quick Start

Run operator-scorecard with var set to dry-run to generate the weekly scorecard artifacts without sending a notification, or leave var empty to run normally for the default 7-day window.

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 scorecard for autonomous operations?

To generate a weekly agent health scorecard, run the operator-scorecard skill with var set to dry-run for a preview without notifications, or leave var empty to process the default 7-day window and emit notification artifacts.

What is the worst-of-three verdict semantics for agent health monitoring?

Worst-of-three verdict semantics compute an overall OK, WATCH, or DEGRADED status by taking the lowest score among agent health, community growth, and economic activity lanes, aligning with heartbeat P-flag terminology.

How do I handle missing analytics data when generating weekly agent reports?

Missing analytics data is handled gracefully during synthesis by returning an INSUFFICIENT_DATA state, ensuring the weekly agent report degrades safely without fabricating numbers from incomplete upstream inputs.

Does operator scorecard reporting require any external API calls?

Operator scorecard reporting requires no external API calls, relying strictly on local-only file scanning to assemble repo pulse deltas, token distribution logs, and memory data into the weekly summary.

What file formats are produced by the weekly agent operator report?

The weekly agent operator report produces a canonical markdown article named articles/operator-scorecard-${today}.md and a dashboard JSON spec at dashboard/outputs/operator-scorecard.json for operator delivery.

Can I use agent ops scorecards for unattended autonomous-agent operations?

Agent ops scorecards are designed specifically for unattended autonomous-agent operations, applying deterministic arithmetic rollups to assemble community metrics and token activity into a Monday-style notification artifact.