capture-learnings

Capture user feedback and preferences as structured memories in a SQL-backed index.

3|Updated Jun 10, 2026
One-click install
npx skills add https://github.com/BuilderIO/builder-agent-native-starter --skill capture-learnings-builderio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: capture-learnings
Source: https://github.com/BuilderIO/builder-agent-native-starter/tree/main/.agents/skills/capture-learnings
Command: npx skills add https://github.com/BuilderIO/builder-agent-native-starter --skill capture-learnings-builderio

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Capture and organize user feedback and preferences as memories for future conversations.

Core Features & Use Cases

  • Proactively capture user feedback, preferences, corrections, and project context as structured memories.
  • Persist memories across sessions so they can be recalled to tailor responses, improve suggestions, and maintain consistency.
  • Use memory types like user, feedback, project, and reference to organize context.

Quick Start

Save a memory about user preferences or corrections so it can be recalled in future conversations.

Frequently Asked Questions about capture-learnings

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

FAQPage Schema
How do I save user feedback and preferences to reuse across future conversations?

Saving user feedback and preferences across conversations involves capturing context as structured memories using types like user, feedback, project, and reference. The system persists corrections and preferences in a SQL-backed personal index for future sessions.

How does memory persistence work for maintaining project context across sessions?

Memory persistence for project context works by storing user feedback and corrections in a SQL-backed personal index. It supports save-memory and resource-read commands to apply relevant context across different task scenarios in future conversations.

Can I organize captured learnings into different memory types for specific tasks?

Yes, you can organize captured learnings into specific memory types including user, feedback, project, and reference. This categorization maintains structured context to tailor responses when applying memories to relevant task scenarios.

How do I delete or list saved memories in my personal index?

You can delete or list saved memories in your personal index using the delete-memory and resource-list commands. These functions manage stored feedback and preferences within the SQL-backed memory index.

Do I need a SQL database to store and retrieve conversation memories?

A SQL database serves as the backend for the personal memory index to store and retrieve conversation memories. This infrastructure supports saving and applying feedback, corrections, and project context across sessions.