/remember

> Capture observations, friction patterns, and learnings for future synthesis.

170 stars

byMiosa-osa

View on GitHub Installation ↓

Best use case

/remember is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

> Capture observations, friction patterns, and learnings for future synthesis.

Teams using /remember should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/remember/SKILL.md --create-dirs "https://raw.githubusercontent.com/Miosa-osa/canopy/main/library/skills/knowledge/remember/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/remember/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How /remember Compares

Feature / Agent	/remember	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

> Capture observations, friction patterns, and learnings for future synthesis.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# /remember

> Capture observations, friction patterns, and learnings for future synthesis.

## Usage
```
/remember "<observation>"
/remember --contextual
/remember --mine
/remember --list
/remember --escalations
```

## What It Does
Stores observations and friction patterns into the learning loop. Over time, observations accumulate evidence. When confidence reaches a threshold, they become eligible for `/rethink` synthesis. This is how the system learns from experience.

## Implementation
- Explicit: `cd engine && mix optimal.remember "always check duplicates before inserting"`
- Contextual scan: `cd engine && mix optimal.remember --contextual` (scans recent signals)
- Bulk extract: `cd engine && mix optimal.remember --mine` (from session transcripts)
- List stored: `cd engine && mix optimal.remember --list`
- Check escalations: `cd engine && mix optimal.remember --escalations` (categories ready for rethink)

## Examples
```bash
# Store an explicit observation
/remember "Lead developer needs explicit constraints or they over-engineer"

# Scan recent signals for friction patterns
/remember --contextual

# See what's accumulated enough evidence for synthesis
/remember --escalations
```

## Command