self-eval

Analyze weekly logs from `memory/` to extract achievements, errors, and improvements.

11|2|Updated Feb 6, 2026
One-click install
npx skills add https://github.com/mupengi-bot/mupengism --skill self-eval
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: self-eval
Source: https://github.com/mupengi-bot/mupengism/tree/main/skills/self-eval
Command: npx skills add https://github.com/mupengi-bot/mupengism --skill self-eval

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the process of reviewing your weekly performance, identifying achievements, mistakes, and areas for improvement, ensuring continuous growth and adherence to your core principles.

Core Features & Use Cases

  • Weekly Performance Review: Analyzes the last 7 days of your daily logs.
  • Automated Insight Extraction: Identifies accomplishments, errors, and actionable improvements.
  • Principle Compliance Check: Assesses adherence to your SOUL.md guidelines.
  • Structured Reporting: Saves a detailed weekly self-evaluation report.
  • Event Bus Integration: Publishes a summary of the evaluation for other systems.
  • Use Case: At the end of each week, you can ask the agent to "perform a self-evaluation," and it will generate a comprehensive report detailing your progress, setbacks, and how well you've followed your defined principles.

Quick Start

Ask the agent to perform a self-evaluation for the past week.

Frequently Asked Questions about self-eval

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

FAQPage Schema
How do I automate weekly self-evaluation and performance review for my AI agent?

Weekly self-evaluation is automated by analyzing daily logs from the memory directory to extract achievements, errors, and improvements, then saving a detailed report to memory/self-eval/.

How does an AI agent perform a principle compliance check during a weekly review?

A principle compliance check assesses the agent's adherence to SOUL.md guidelines by analyzing its daily logs, ensuring actions align with defined core principles before generating the final evaluation report.

What is the best way to extract actionable improvements from AI agent daily logs?

Extracting actionable improvements is best done by running an automated weekly review that parses daily logs to identify accomplishments and errors, summarizing them into a structured JSON report.

Can I integrate AI agent performance analysis results with an event bus system?

Yes, performance analysis results integrate with an event bus by publishing a JSON summary of the weekly evaluation, allowing downstream systems to consume the extracted insights.

Does the weekly self-review process require specific file formats or memory structures?

The weekly self-review process requires daily logs stored within a memory directory and a SOUL.md file for principle compliance checks, outputting structured reports to memory/self-eval/.