Skip to content
Back to skills

Memories

ASecurity

View and manage learned memories (patterns, preferences, mistakes, decisions). Use to check current learnings.

  • 8 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added February 7, 2026
ai-agentstypescriptgobashreactdatabasesecurity

Security analysis

A100/100

Scanned February 12, 2026

npx -y skills add seokan-jeong/team-shinchan --skill memories --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Memories?

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

Security grade badge for Memories
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/seokan-jeong-memories/badge)](https://www.skillsdirectory.com/skills/seokan-jeong-memories)

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: team-shinchan:memories
description: View and manage learned memories (patterns, preferences, mistakes, decisions). Use to check current learnings.
user-invocable: true
---

# Memories Skill

**View what Team-Shinchan has learned about this project.**

## Usage

```bash
/team-shinchan:memories              # View all learnings
/team-shinchan:memories pattern      # Filter by category
/team-shinchan:memories search auth  # Search for keyword
```

## Process

### Step 1: Read Learning File

Read `.team-shinchan/learnings.md`

If file doesn't exist:
```
πŸ“š [Memories] No learnings yet.

Start teaching with:
  /team-shinchan:learn "Your learning here"

Or just work - I learn automatically after tasks!
```

### Step 2: Parse and Display

**Full view** (`/memories`):

```
πŸ“š [Memories] {N} learnings stored

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

πŸ“Œ PREFERENCES ({count})
β€’ Use Zustand over Redux [high] #state-management
β€’ Prefer functional components [high] #react

πŸ“Œ PATTERNS ({count})
β€’ Early returns for validation [high] #typescript
β€’ Repository pattern for data access [medium] #architecture

πŸ“Œ CONVENTIONS ({count})
β€’ Use pnpm, not npm [high] #tooling
β€’ camelCase for functions [high] #naming

πŸ“Œ MISTAKES ({count})
β€’ Always null-check before .map() [high] #typescript

πŸ“Œ DECISIONS ({count})
β€’ JWT with refresh token rotation [high] #auth

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

πŸ’‘ These learnings are applied automatically.
πŸ—‘οΈ Use /team-shinchan:forget to remove outdated ones.
```

**Filtered view** (`/memories pattern`):

```
πŸ“š [Memories] Showing: patterns

β€’ Early returns for validation [high]
  Context: Learned from UserService refactor

β€’ Repository pattern for data access [medium]
  Context: Applied during database migration

Found 2 patterns.
```

**Search view** (`/memories search auth`):

```
πŸ“š [Memories] Search: "auth"

1. [decision] JWT with refresh token rotation
   Tags: #auth #security #jwt

2. [pattern] Auth middleware pattern
   Tags: #auth #middleware

Found 2 results.
```

## Memory Categories

| Category | Description | Icon |
|----------|-------------|------|
| `preference` | User preferences | πŸ’œ |
| `pattern` | Reusable code patterns | πŸ”· |
| `convention` | Project conventions | πŸ“ |
| `mistake` | Errors to avoid | ⚠️ |
| `decision` | Architecture decisions | πŸ—οΈ |
| `insight` | General insights | πŸ’‘ |

## Important

- Learnings are stored in `.team-shinchan/learnings.md`
- Automatically loaded at session start
- Higher confidence learnings are prioritized
- Old learnings can be removed with `/forget`

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.