Skip to content
Back to skills

Distill Memory

ASecurity

Save durable Nowledge Mem insights when a Proma conversation produces decisions, procedures, preferences, plans, learnings, or project context that should survive future sessions.

  • 182 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 24, 2026
ai-agentsbashsecurity

Works with

  • cli
  • mcp

Security analysis

A100/100

Scanned September 24, 2026

npx -y skills add nowledge-co/community --skill distill-memory --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Distill Memory?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Distill Memory
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/nowledge-co-distill-memory-b78ed002/badge)](https://www.skillsdirectory.com/skills/nowledge-co-distill-memory-b78ed002)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: distill-memory
description: Save durable Nowledge Mem insights when a Proma conversation produces decisions, procedures, preferences, plans, learnings, or project context that should survive future sessions.
---

# Distill Memory

Save durable insights to Nowledge Mem autonomously. Don't wait to be asked — save proactively when the conversation produces a durable fact, preference, decision, plan, procedure, learning, event, or important context.

## When to Save

**Save proactively when the conversation produces:**
- A fact (durable reference detail, tool constraint, environment fact)
- A decision (architecture choice, tool selection, process change)
- A preference (code style, workflow, tool configuration)
- A plan (multi-step task design, roadmap item)
- A procedure (how to set up, how to debug, how to deploy)
- A learning (bug root cause, pitfall discovered, pattern recognized)
- An event (meeting outcome, release milestone, incident timeline)
- Important context (project background, stakeholder constraint)

## Usage

**Primary (MCP)**:
```
mcp__nowledge-mem__add_memory
  content: "<what was decided or learned>"
  title: "<short descriptive title>"
  unit_type: "fact|preference|decision|plan|procedure|learning|context|event"
  importance: 0.3-1.0
  tags: ["<relevant tags>"]
```

**Fallback (CLI)**:
```bash
nmem --json m add "JWT refresh failures came from clock skew." \
  --title "JWT refresh failures traced to clock skew" \
  --importance 0.9 --unit-type learning -l auth -s proma
```

## Importance Guide

| Level | When |
|-------|------|
| 0.3-0.5 | Minor preference, small tip |
| 0.5-0.7 | Useful pattern, reusable snippet |
| 0.7-0.9 | Important decision, hard-won lesson |
| 0.9-1.0 | Critical architecture choice, security rule |

## Add vs Update

- **Add** (`mcp__nowledge-mem__add_memory`): new insight, first time capturing something
- **Update** (`mcp__nowledge-mem__update_memory`): refining or correcting an existing memory
- When unsure, search first to check if a related memory already exists

## Guidance

1. Save after the decision is made, not mid-discussion
2. Include enough context for your future self (or another AI) to understand 3 months later
3. Don't save trivialities — "we used port 3000" doesn't belong unless the choice of port was significant
4. Built-in `mcp__mem__add_memory` is for session-level notes; use nmem for cross-session durability

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.