learn

Scan .commandcode/learnings, prune outdated entries, and export summaries to EXPORT_YYYYMMDD.md.

15|5|Updated May 17, 2026
One-click install
npx skills add https://github.com/cropsgg/skills --skill learn-cropsgg
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learn
Source: https://github.com/cropsgg/skills/tree/main/skills/productivity/learn
Command: npx skills add https://github.com/cropsgg/skills --skill learn-cropsgg

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Keeps a cumulative record of learnings across sessions to prevent repeating mistakes and friction.

Core Features & Use Cases

  • Cross-session pattern detection: identify recurring issues, fixes, and insights to streamline future work.
  • Aggressive pruning: remove outdated or conflicting learnings, flagging as [OUTDATED].
  • Knowledge export: generate concise, context-ready exports for upcoming sessions and knowledge bases.

Quick Start

Run an export by scanning .commandcode/learnings and saving to .commandcode/learnings/EXPORT_YYYYMMDD.md.

Frequently Asked Questions about learn

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

FAQPage Schema
How do I consolidate cross-session learnings into a reusable knowledge base?

Cross-session learnings are consolidated by scanning the .commandcode/learnings/ directory to detect recurring patterns and mistakes, then exporting a concise summary to preserve history for future work and auditing.

What is the best way to export a knowledge summary for an upcoming session?

Exporting a knowledge summary involves scanning existing learnings and generating a context-ready file saved as .commandcode/learnings/EXPORT_YYYYMMDD.md to inform upcoming project work.

How does pruning outdated memory entries work in a knowledge base?

Pruning outdated memory entries works by identifying conflicting or obsolete learnings, flagging them with an [OUTDATED] marker, and removing them to maintain a concise, reusable knowledge base.

Can I detect recurring mistakes and patterns across multiple project sessions?

Yes, recurring mistakes and patterns are detected by applying the consolidation process across multiple sessions on the same project, scanning accumulated learnings to identify issues and opportunities for improvement.

Do I need a specific directory structure to maintain cross-session learnings?

Yes, maintaining cross-session learnings requires a .commandcode/learnings/ directory to store entries, apply pruning with [OUTDATED] markers, and export dated markdown summaries for auditing.