selbstbeobachtung

Community

Automates post-task retrospectives for improvement

AuthorPepsi1978
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill automates post-task retrospectives to capture what went well, what didn’t, and what to improve across tasks.

Core Features & Use Cases

  • Automatic trigger: activates after each commit+push, after task completion signals, or when the user asks for a review.
  • Three-tracker analysis: analyzes Retry count, Correction count, and Drift to surface actionable insights.
  • Persistent memory & rules: persists learnings to MEMORY.md, updates rules in ~/.claude/rules, and logs bug-cases for future reference.

Quick Start

Ask the AI to perform a self-review after the next task by summarizing outcomes, lessons learned, and concrete improvements.

Dependency Matrix

Required Modules

None required

Components

Standard package

đź’» Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: selbstbeobachtung
Download link: https://github.com/Pepsi1978/proggs/archive/main.zip#selbstbeobachtung

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.