Record learning insights as JSON objects in .claude/learnings.jsonl.
npx skills add https://github.com/manastalukdar/ai-devstudio --skill learn-manastalukdar
Please help me install this Agent Skill. Skill: learn Source: https://github.com/manastalukdar/ai-devstudio/tree/main/skills/learn Command: npx skills add https://github.com/manastalukdar/ai-devstudio --skill learn-manastalukdar
Record, list, search, and apply cross-session learnings — capture insights from completed work as JSONL entries so patterns persist across conversations and accumulate into institutional knowledge. Inspired by gstack's learn skill.
Add a new learning entry by describing the insight you want to persist.
High-intent search queries and answers about installing and using this skill.
To capture learning insights across sessions, you can record them as JSONL entries with automatic category inference and tagging. This stores each insight as a structured JSON object in a local learnings file so patterns persist across future conversations.
Yes, you can list, search, and filter recorded learnings by tags or categories across sessions. The system stores entries with specific fields for tags and auto-detected categories, allowing you to quickly retrieve relevant institutional knowledge.
The best way to build institutional knowledge from conversations is to record insights directly into a JSONL store. This captures work outputs as structured data with dates, categories, and tags, accumulating session patterns into a searchable knowledge base.
You can apply past learnings to current work by searching the stored JSONL entries and surfacing relevant insights. This quickly brings previously captured institutional knowledge into your active context to guide ongoing tasks.
No, recording cross-session learnings requires no external dependencies or databases. The system writes entries directly into a local JSONL file, storing fields like id, date, category, learning, tags, and source without needing additional setup.
Automatic category inference works by analyzing the content of the learning insight you provide. It detects the relevant category from the text itself, automatically populating the category field in the JSONL entry alongside your specified tags.
timurgaleevRecord, organize, and retrieve project learnings in a local JSONL store.
ShmurdocCapture and organize project learnings into a searchable JSONL knowledge base.
a29paulReview, search, prune, and export project learnings from JSONL files.
project-axManage audit logging providers for system events with JSONL or database storage.
