skills.rest
m2ai-portfolio
m2ai-portfolioOFFICIAL
Explore all skills by this author →
GitHub

simulated-work-detector

Identifies and flags simulated work in agent fleet outputs.

4|1|Updated Apr 11, 2026
Search Tags:#post-mortem#observability#artifact-tracking#land-or-leave#simulated-work#fleet-audit#automation-oversight
One-click install
npx skills add https://github.com/m2ai-portfolio/m2ai-skills-pack --skill simulated-work-detector
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: simulated-work-detector
Source: https://github.com/m2ai-portfolio/m2ai-skills-pack/tree/main/skills/simulated-work-detector
Command: npx skills add https://github.com/m2ai-portfolio/m2ai-skills-pack --skill simulated-work-detector

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Recurring audit that reviews agent fleet output and flags simulated work that generated artifacts but didn't close any loops or remove work from your plate.

Core Features & Use Cases

  • Fleet-output auditing to identify artifacts that do not close loops.
  • Land/Leave analysis to classify outputs as REAL, SIMULATED, or UNCLEAR.
  • Reporting and recommendations to reduce waste.

Quick Start

Run the weekly simulated-work-check audit to identify and classify recent outputs.

Frequently Asked Questions about simulated-work-detector

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

FAQPage Schema
How do I audit agent fleet output to flag simulated work and unclosed loops?▼

To flag simulated work and unclosed loops, run a fleet audit that gathers agent outputs, applies a land/leave test to classify artifacts as REAL, SIMULATED, or UNCLEAR, and calculates a waste ratio to produce a structured report.

What is the land/leave test for identifying simulated work in automation tasks?▼

The land/leave test is a classification method used during fleet audits to determine if an automation task generated real artifacts that closed a loop, or merely simulated work by leaving the original workload untouched.

How do I calculate the waste ratio for distributed agents during a post-mortem?▼

You calculate the waste ratio during a post-mortem by comparing the volume of SIMULATED artifacts against closed-loop outputs, which surfaces the percentage of agent fleet activity that failed to remove work from your plate.

Can I use agent logs and vault notes for weekly fleet health reviews?▼

Yes, weekly fleet health reviews can be conducted by extracting outputs directly from agent logs and vault notes, then applying the land/leave analysis to identify non-closed loops and generate waste reduction recommendations.

What is the best way to identify automation oversight issues in a distributed agent fleet?▼

The best way to identify automation oversight issues is to perform a recurring fleet-output audit that classifies recent outputs, surfaces non-closed loops, and generates a structured report with recommendations to reduce waste.

Related Skills

Explore More Data & Analytics Skills→
m2ai-portfoliom2ai-portfolio
4

open-loop-audit

Classify open loops from Obsidian, Notion, calendar, and Git as delegation or simulated work.

Official
Advanced
x3fleetsafetyx3fleetsafety
1

fuel-management-and-mpg-optimization

Analyze fleet MPG performance and recommend actions to reduce fuel costs.

Official
Intermediate
iusztinpauliusztinpaul
181

day

Run a supervised SWE↔Tester loop for one task with human diff review.

Community
Intermediate
vicharanashalavicharanashala
6

Ratio & Proportion

Generate algorithmic ratio and proportion problems with adaptive difficulty scaling.

Official
Intermediate