reflection

Analyze past AI sessions to identify root causes and generate actionable recommendations.

Updated Jan 27, 2026
One-click install
npx skills add https://github.com/mccode415/agent --skill reflection-mccode415
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: reflection
Source: https://github.com/mccode415/agent/tree/main/skills/reflection
Command: npx skills add https://github.com/mccode415/agent --skill reflection-mccode415

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps analyze past AI interactions to identify what worked well, what went wrong, and how to improve future sessions, leading to more efficient and effective AI usage.

Core Features & Use Cases

  • Structured Retrospective: Guides a deep dive into session performance using a defined framework.
  • Actionable Recommendations: Generates specific, implementable changes for skills, memory, or documentation.
  • Use Case: After a complex coding session that encountered several bugs, use this Skill to pinpoint the root causes of errors and create new checks within your development skills to prevent similar issues in the future.

Quick Start

Run the reflection skill to analyze the last coding session.

Frequently Asked Questions about reflection

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

FAQPage Schema
How do I conduct an AI session retrospective to analyze past interactions?

An AI session retrospective analyzes past interactions to identify what worked well, what went wrong, and how to improve future sessions. It uses a structured framework to guide a deep dive into session performance.

What is the best way to find root causes of failures in a coding session?

Finding root causes of failures in a coding session requires post-session analysis that focuses on systemic improvements rather than symptomatic fixes. This approach pinpoints underlying errors and extracts reusable lessons to prevent similar issues.

Can I generate actionable recommendations for skill development after debugging?

Post-session retrospectives generate actionable recommendations for skill development by analyzing debugging performance. They create specific, implementable changes for skills, memory, or documentation to improve future AI usage.

How do I update my knowledge base with lessons learned from session analysis?

Updating a knowledge base with lessons learned from session analysis involves extracting reusable insights from past AI interactions. This process generates specific documentation updates to ensure systemic improvements are applied to future tasks.

When do I need a structured retrospective for AI improvement?

A structured retrospective for AI improvement is needed after complex coding sessions that encounter several bugs. It helps analyze session performance, identify root causes of errors, and create new checks to prevent similar issues in the future.