Self-Reflection (Continuous Improvement Protocol)

Overview

AI coding agents are naturally "stateless." You might spend 2 hours debugging a complex Webpack configuration, a subtle race condition, or a confusing project directory layout, eventually fix it, and then completely "forget" the lesson when a new conversation starts.

The core goal of this skill is to turn you from a "temporary worker" into a "systematic documenter."

Core Principle: Hard-won knowledge must be persisted. If a task was difficult because of an undocumented project quirk or architectural gotcha, you MUST write a rule so the next agent (or yourself in the future) doesn't repeat your mistakes.

When to Use

You must trigger this protocol automatically before declaring a task "done" and notifying the user in the following scenarios:

• After successfully fixing a complex or confusing bug (especially if it took multiple attempts, required new context, or reading multiple files).
• After struggling with a framework configuration.
• After discovering a codebase-specific convention ("In this project, we always use X instead of Y").
• After creating a complex workflow or tool sequence that could be reused.