remember

Name: remember
Availability: InStock
Author: kinnerkarmanish

Capture behavioral friction and lessons as structured observations for the rethink loop.

Updated Apr 26, 2026

Search Tags:#feedback #deduplication #mining #observations #remember #learning-loop #contextual

Ready to run

npx skills add https://github.com/kinnerkarmanish/mak --skill remember-kinnerkarmanish

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: remember
Source: https://github.com/kinnerkarmanish/mak/tree/main/library/skills/learning/remember
Command: npx skills add https://github.com/kinnerkarmanish/mak --skill remember-kinnerkarmanish

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Capture behavioral friction and lessons as structured observations. Three modes: explicit (user states a lesson), contextual (scan conversation for corrections and patterns), and session mining (bulk extract from transcripts). Stores observations for later synthesis via /rethink.

Core Features & Use Cases

Explicit mode: capture lessons directly from user input.
Contextual mode: detect corrections in ongoing conversations.
Mining mode: bulk extract patterns from transcripts to inform synthesis.

Quick Start

Use the /remember command to capture an explicit lesson, such as /remember "Always check for duplicates before inserting into the knowledge base".

Frequently Asked Questions about remember

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

FAQPage Schema

How do I capture behavioral lessons from conversations to improve my systems?▼

Behavioral friction and lessons are captured as structured observations using explicit, contextual, or mining modes. The system extracts these data points from user input, ongoing conversations, or transcripts, storing them locally with tags for later synthesis via the rethink loop.

What is the best way to extract patterns from chat transcripts for later analysis?▼

Session mining mode enables bulk extraction of behavioral patterns from transcripts. It categorizes extracted observations with tags and applies deduplication before storing them locally, ensuring clean data for later synthesis via the rethink loop.

How does contextual correction detection work during an ongoing conversation?▼

Contextual correction detection scans ongoing conversations to identify behavioral friction and corrections as they occur. It captures these contextual patterns as structured observations, categorizes them with tags, and stores them locally to accumulate evidence for system improvements.

Do I need a local observation store to use the behavioral lesson capture workflow?▼

Yes, a local observation store is required. The workflow depends on this local store to accumulate categorized observations, apply deduplication, and manage the evidence needed to escalate ready categories to the rethink phase for system improvements.

How do I escalate categorized observations to the rethink loop?▼

The workflow monitors the local observation store for categories that have accumulated sufficient evidence. Once a category is ready, the workflow triggers the escalation to /rethink for downstream synthesis and system improvements.