learn

Aggregate and organize project learnings from gstack sessions into a local JSONL store.

Updated May 14, 2026
One-click install
npx skills add https://github.com/lemig/transcriptor --skill learn-lemig
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learn
Source: https://github.com/lemig/transcriptor/tree/main/.claude/skills/gstack/learn
Command: npx skills add https://github.com/lemig/transcriptor --skill learn-lemig

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Centralize and organize project learnings from gstack sessions to prevent knowledge loss, reduce repeated mistakes, and accelerate future improvements across teams.

Core Features & Use Cases

  • Review learnings across multiple sessions and projects to surface guidance and patterns.
  • Search, prune stale or irrelevant learnings, and export insights for sharing or archiving.
  • Use Case: When preparing a post-mortem or knowledge base update, quickly surface relevant learnings and export them in a structured format for teammates.

Quick Start

Summarize the latest learnings and export them to learnings.jsonl.

Frequently Asked Questions about learn

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

FAQPage Schema
How do I capture and review project learnings across multiple sessions?

Capture and review project learnings across sessions by aggregating session data into a local JSONL store to surface guidance and patterns. This prevents knowledge loss and helps you avoid repeating past mistakes.

Can I export learnings to a structured format for team knowledge sharing?

You can export learnings to a structured learnings.jsonl file for sharing or archiving. This allows teammates to quickly access relevant project insights during post-mortems or knowledge base updates.

What is the best way to manage and prune stale knowledge in a local store?

Prune stale or irrelevant learnings by applying the built-in tooling to search and clean your local learnings store. This keeps your knowledge base relevant and prevents outdated patterns from cluttering future reviews.

Do I need a specific local file setup to store and search project learnings?

You need a local learnings store at a path like ~/.gstack/projects/${SLUG:-unknown}/learnings.jsonl to aggregate session data. This local file acts as the central repository for searching, pruning, and exporting.

When should I search past project learnings instead of starting fresh?

Search past project learnings when preparing a post-mortem, updating a knowledge base, or reviewing past patterns and improvements. This surfaces relevant historical data to accelerate future improvements and prevent repeated mistakes.