remember

Capture friction points as methodology insights in structured files.

6|2|Updated Nov 2, 2022
One-click install
npx skills add https://github.com/arolariu/arolariu.ro --skill remember-arolariu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: remember
Source: https://github.com/arolariu/arolariu.ro/tree/main/.claude/skills/remember
Command: npx skills add https://github.com/arolariu/arolariu.ro --skill remember-arolariu

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps capture and codify learnings from agent interactions, turning friction points into actionable methodology improvements and preventing recurring issues.

Core Features & Use Cases

  • Explicit Capture: Directly record user-defined friction points and desired behaviors.
  • Contextual Review: Analyze recent conversation history for implicit corrections and user feedback.
  • Session Mining: Scan past session transcripts for recurring patterns of friction and uncaptured learnings.
  • Use Case: After an agent repeatedly misunderstands a user's request for concise summaries, you can use /remember "always provide concise summaries, avoid lengthy explanations" to capture this as a methodology insight.

Quick Start

Use the remember skill to capture the friction point by describing it directly.

Frequently Asked Questions about remember

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

FAQPage Schema
How do I capture agent friction points and refine methodology from chat history?

You capture agent friction points by parsing explicit user input, analyzing conversation history for contextual corrections, or mining past session transcripts to write structured methodology insights into `ops/methodology/` and `ops/observations/`.

What is session mining for contextual learning and when do I need it?

Session mining for contextual learning is the process of scanning past agent conversation transcripts to identify recurring patterns of uncaptured friction, needed when you want to operationalize learnings and prevent recurring agent issues.

How to operationalize learnings from agent behavior corrections into structured files?

You operationalize learnings by analyzing recent conversation history for implicit corrections and writing the extracted methodology insights into structured files within the `ops/methodology/` and `ops/observations/` directories.

Does this methodology capture approach work without external dependencies?

Yes, this methodology capture approach works without external dependencies, relying entirely on internal scripts and references to parse user input and analyze conversation history for friction points.

What is the best way to record explicit user feedback for agent methodology refinement?

The best way to record explicit feedback is by directly providing a description of the friction point and desired behavior, which the system then parses and codifies as an actionable methodology insight in structured files.

When should I not rely on explicit capture for refining agent behavior?

You should not rely on explicit capture when friction points are implicit, requiring you to instead analyze recent conversation history or mine past session transcripts to identify uncaptured learnings and recurring patterns.