retrospective-agent

Analyze completed agentic tracks to extract learnings and log errors.

Updated Mar 7, 2026

Search Tags:#learning #patterns #retrospective #continuous improvement #workflow optimization #errors

Ready to run

npx skills add https://github.com/Geargrindadmin/gg-agentic-harness --skill retrospective-agent-geargrindadmin

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: retrospective-agent
Source: https://github.com/Geargrindadmin/gg-agentic-harness/tree/main/.agent/skills/retrospective-agent
Command: npx skills add https://github.com/Geargrindadmin/gg-agentic-harness --skill retrospective-agent-geargrindadmin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the process of analyzing completed tracks to identify what worked well, what failed, and to extract reusable patterns and error solutions, thereby continuously improving future workflows.

Core Features & Use Cases

Automated Learning Extraction: Runs after each track completion to analyze execution data.
Knowledge Base Updates: Updates patterns.md with new solutions and errors.json with new error patterns.
Skill Improvement Proposals: Identifies potential workflow enhancements for other skills.
Use Case: After a complex feature development track, this agent will automatically review the commits, task outcomes, and any encountered errors to document successful strategies and common pitfalls, making the next similar feature development faster and smoother.

Quick Start

Use the retrospective-agent skill to analyze the completed track 'user-auth-flow_20260131'.

Frequently Asked Questions about retrospective-agent

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

FAQPage Schema

How do I extract reusable patterns from completed agentic tracks?▼

To extract reusable patterns from completed agentic tracks, analyze execution data like commits, task outcomes, and errors. This process identifies successful strategies and common pitfalls, updating knowledge bases with documented solutions for continuous workflow improvement.

How does automated retrospective analysis improve workflow optimization?▼

Automated retrospective analysis improves workflow optimization by reviewing track metadata and specifications to log errors and identify friction. It generates skill enhancement proposals and updates knowledge bases, enabling future tasks to bypass documented pitfalls.

What data do I need to generate a comprehensive development retrospective?▼

Generating a comprehensive development retrospective requires access to the track plan, metadata, commits, and specifications. This data allows the analysis to extract learnings, identify patterns, and log errors for continuous improvement.

When should I run an automated learning extraction process?▼

You should run an automated learning extraction process after each track completion. Analyzing the finished execution data allows you to document successful strategies and update error logs, making future similar feature development smoother.

What is the best way to log errors from agentic tracks for continuous improvement?▼

The best way to log errors for continuous improvement is to analyze completed tracks and record new error patterns into an errors.json file. This captures encountered errors and their fixes for reuse in future workflows.