learn

Review conversations to extract learnings and durable facts for persistent memory.

Updated Jul 29, 2026

Search Tags:#knowledge management #memory #self-reflection #conversation analysis #fact extraction

Ready to run

npx skills add https://github.com/2lab-ai/soma-work --skill learn-2lab-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: learn
Source: https://github.com/2lab-ai/soma-work/tree/main/src/local/skills/learn
Command: npx skills add https://github.com/2lab-ai/soma-work --skill learn-2lab-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps users reflect on their conversations, extract learnings, and save durable facts to persistent memory.

Core Features & Use Cases

Self-Reflection: Analyze conversations to identify what went well, what went wrong, and key decisions made.
Durable Fact Extraction: Identify facts that will still be true in future sessions and save them to persistent memory.
Memory Management: Manage memory entries by adding, updating, or removing facts based on priority and memory constraints.

Quick Start

Trigger the learn skill to review the current conversation and extract learnings.

Frequently Asked Questions about learn

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

FAQPage Schema

How do I extract durable facts and learnings from a conversation for knowledge management?▼

To extract durable facts from a conversation for knowledge management, trigger the skill to review your current session. It reflects on the dialogue, identifies key decisions, and saves long-lasting facts to persistent memory for future use.

What is self-reflection in conversation analysis and how does it identify user preferences?▼

Self-reflection in conversation analysis reviews ongoing dialogue to evaluate what went well, what went wrong, and the decisions made. It identifies user preferences by extracting specific, durable facts from the session and saving them to memory.

Can I use this to generate session summaries for project knowledge management?▼

Yes, you can use this to generate session summaries for project knowledge management. It analyzes your conversation history to extract relevant learnings and durable facts, saving them directly into persistent memory for later retrieval.

How do I manage memory entries when persistent memory reaches its constraints?▼

To manage memory entries under constraints, you can add, update, or remove facts based on their priority. This ensures your persistent memory remains optimized and only retains the most relevant durable facts for future sessions.

Does fact extraction work without setting up external dependencies?▼

Yes, fact extraction works without setting up external dependencies. The skill operates independently using internal scripts to review conversations, reflect on the content, and save extracted durable facts directly to persistent memory.

When should I not use automated conversation analysis for saving durable facts?▼

You should not use automated conversation analysis for saving durable facts when a session contains only transient information. If the dialogue lacks long-lasting decisions or stable user preferences, extracting facts provides little value for persistent memory.