score

Tracks and analyzes the Autonomy Score using local markdown files.

Updated Feb 22, 2026
One-click install
npx skills add https://github.com/mentilead/growthOS --skill score
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: score
Source: https://github.com/mentilead/growthOS/tree/main/skills/autonomy-tracker
Command: npx skills add https://github.com/mentilead/growthOS --skill score

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill tracks and analyzes the Autonomy Score, a key performance indicator measuring the percentage of operational decisions made without human intervention, helping to optimize AI efficiency and identify areas for improvement.

Core Features & Use Cases

  • Decision Logging: Record autonomous decisions, human escalations, and agent failures.
  • Score Review: Provide a snapshot of the current Autonomy Score with context relevant to the experiment's chapter.
  • Trend Analysis: Visualize the score's progression over time and identify top escalation drivers.
  • Use Case: A product manager can use this Skill to monitor how effectively their AI agents are operating autonomously, ensuring they are meeting efficiency targets as the project progresses through different development phases.

Quick Start

Use the autonomy tracker skill to update the log with 5 additional autonomous decisions for the current month.

Frequently Asked Questions about score

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

FAQPage Schema
How do I track AI autonomy and measure operational decisions requiring no human input?

AI autonomy tracking measures the percentage of operational decisions made without human intervention by logging autonomous decisions, human escalations, and agent failures over a rolling period. This helps identify efficiency gaps and areas for improvement.

What is the best way to log autonomous decisions and human escalations for performance analysis?

Log autonomous decisions and human escalations by updating decision counts in local markdown files. This persistent state tracking records operational choices and agent failures, enabling accurate trend analysis and ongoing performance evaluation.

Can I analyze AI performance trends and identify top escalation drivers across multiple months?

AI performance trend analysis visualizes the autonomy score's progression over time and identifies top escalation drivers across months. This contextual review highlights recurring operational bottlenecks affecting autonomous decision rates.

Does this AI metrics tracking approach work with local markdown files for persistent state logging?

Yes, AI metrics tracking utilizes local markdown files for persistent state and decision logging. This lightweight approach ensures operational decision data is stored locally without requiring external databases or complex infrastructure.

When do I need to review the current Autonomy Score with chapter-appropriate context for experimentation?

Review the current Autonomy Score with chapter-appropriate context during experimentation phases to evaluate whether AI agents meet efficiency targets. This snapshot contextualizes performance within specific development milestones.

Why does decision tracking matter for optimizing AI agent efficiency and autonomy?

Decision tracking matters for AI agent efficiency because it quantifies the autonomy percentage, revealing how often agents operate without human input. This data identifies escalation drivers and guides optimization for better performance.