learn

Identify and encode learnable moments from your most recent session into memories.

8|1|Updated Mar 1, 2026
One-click install
npx skills add https://github.com/toejough/engram --skill learn-toejough
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learn
Source: https://github.com/toejough/engram/tree/main/skills/learn
Command: npx skills add https://github.com/toejough/engram --skill learn-toejough

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

After finishing a task or project, it helps you identify and capture learnable moments from the session to improve future performance.

Core Features & Use Cases

  • Identify learnable moments from the current session (user corrections, failed approaches, discovered facts, and recurring patterns).
  • Apply a quality gate to ensure only valuable learnings are turned into memories.
  • Persist the resulting memories as actionable knowledge for future sessions and tasks.

Quick Start

Review the most recent session and extract key learnings to be stored as memories.

Frequently Asked Questions about learn

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

FAQPage Schema
How do I capture learnable moments from a coding session to improve future performance?

To capture learnable moments from a coding session, review user corrections, failed approaches, and discovered facts, then persist these insights as memories. This process identifies recurring patterns and encodes them as actionable feedback for future tasks.

What is the best way to extract recurring patterns and feedback after a debugging session?

The best way to extract recurring patterns after a debugging session is to review the workflow for user corrections and failed approaches. A quality gate filters the session feedback, ensuring only valuable learnings become persistent memories.

Can I apply a quality gate to filter session feedback before storing it as memories?

Yes, you can apply a quality gate to filter session feedback before storing it as memories. This quality gate evaluates identified candidates from the session, ensuring only high-value facts and feedback are encoded for future use.

How does post-session memory encoding work for discovered facts and failed approaches?

Post-session memory encoding works by identifying discovered facts and failed approaches from the recent session, applying a quality gate, and drafting these candidates as persistent memories. This improves future performance across coding and planning tasks.

Does identifying learnable moments work for planning and direction changes or just coding tasks?

Identifying learnable moments works for planning and direction changes as well as coding tasks. The post-session review process applies broadly across debugging, planning, and direction changes to encode valuable feedback into persistent memories.