Pantheon Reflection (Mnemosyne)

Extract learnings from completed development stories into reusable playbooks.

Updated Aug 27, 2026

Search Tags:#code quality #knowledge management #playbook #ai development #learning #reflection

Ready to run

npx skills add https://github.com/jschulte/pantheon --skill pantheon-reflection-mnemosyne

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Pantheon Reflection (Mnemosyne)
Source: https://github.com/jschulte/pantheon/tree/main/src/skills/pantheon-reflection
Command: npx skills add https://github.com/jschulte/pantheon --skill pantheon-reflection-mnemosyne

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the process of extracting valuable lessons learned from completed software development stories and consolidating them into actionable playbooks, preventing future mistakes and accelerating development.

Core Features & Use Cases

Automated Learning Extraction: Identifies patterns, missed issues, and anti-patterns from build, test, and review artifacts.
Intelligent Playbook Updates: Updates existing playbooks with new learnings or creates new ones for novel domains, ensuring knowledge is captured and reused.
Use Case: After a complex feature is built and tested, this Skill analyzes the outcomes, identifies why certain bugs were missed during development, and updates the relevant coding playbook with specific examples and corrected approaches.

Quick Start

Use the Pantheon Reflection skill to extract learnings from story key 1-3 using artifacts in the sprint artifacts directory.

Frequently Asked Questions about Pantheon Reflection (Mnemosyne)

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

FAQPage Schema

How do I extract learnings from completed software development stories?▼

To extract learnings from completed software development stories, you can use automated reflection tools that analyze build, test, and review artifacts to identify patterns, missed issues, and anti-patterns, consolidating outcomes into actionable playbooks for future builds.

What is automated playbook creation in AI development pipelines?▼

Automated playbook creation in AI development pipelines is the process of capturing knowledge from post-development analysis. It identifies why bugs were missed during development and updates coding playbooks with specific examples and corrected approaches to prevent future mistakes.

How do I update coding playbooks with knowledge from previous sprints?▼

You can update coding playbooks with knowledge from previous sprints by applying post-development analysis to story artifacts. The system intelligently updates existing playbooks with new learnings or creates new ones for novel domains, ensuring knowledge is captured and reused.

What artifacts do I need to analyze missed issues in multi-agent coding pipelines?▼

To analyze missed issues in multi-agent coding pipelines, you need access to story artifacts including builder completions, inspection reports, and triage results. These artifacts allow the system to identify anti-patterns and extract valuable lessons from completed stories.

When should I use post-development analysis for code quality improvement?▼

You should use post-development analysis for code quality improvement after a complex feature is built and tested. It analyzes the outcomes to identify why certain bugs were missed during development and updates the relevant coding playbook with corrected approaches.