How do I add a learning?

Use /team-shinchan:learn with a quoted string describing the memory you want Team-Shinchan to remember.

Where are learnings stored?

In the project file .shinchan-docs/learnings.md and loaded at startup via load-kb.

How do I remove a learning?

Use /team-shinchan:forget to delete a saved memory from memory and the docs.

team-shinchan:learn

Scanned

npx machina-cli add skill seokan-jeong/team-shinchan/learn --openclaw

Files (1)

SKILL.md

1.6 KB

Learn Skill

Teach Team-Shinchan something to remember.

Usage

/team-shinchan:learn "Always use TypeScript strict mode in this project"
/team-shinchan:learn "User prefers functional components over class components"

Process

Auto-Categorize based on keywords:

Keywords	Category	Tier
prefer, like, want	`preference`	`preference`
pattern, approach, way	`pattern`	`procedural`
always, never, rule, use	`convention`	`procedural`
error, mistake, avoid	`mistake`	`procedural`
decided, architecture	`decision`	`procedural`
other	`insight`	`procedural`

Note: tool tier is set when user explicitly passes --tier tool or AI detects tool-specific phrasing (CLI flags, tool config patterns).

Append to .shinchan-docs/learnings.md (create if missing):

### [{category}] {title}
- **Date**: {YYYY-MM-DD}
- **Source**: manual
- **Tier**: {auto-mapped tier}
- **Confidence**: high
- **Tags**: #{auto-generated tags}
- **Insight**: {content}

---

Confirm:

🧠 [Learn] Saved to memory:
Category: {category}
Learning: "{content}"
📁 Location: .shinchan-docs/learnings.md

Important

Learnings are project-specific (saved in .shinchan-docs/)
High confidence because user explicitly taught it
Loaded at every session start via load-kb hook
Remove with /team-shinchan:forget

Source

git clone https://github.com/seokan-jeong/team-shinchan/blob/main/skills/learn/SKILL.mdView on GitHub

Overview

Teach Team-Shinchan to remember specific information by manually adding learnings (patterns, preferences, rules). Learnings are saved to the project's .shinchan-docs/learnings.md and loaded at startup for consistency. This makes project-specific memory reliable and explicit.

How This Skill Works

You invoke /team-shinchan:learn with a content string describing what to remember. The tool auto-categorizes using keywords into category and tier, then appends a markdown entry to .shinchan-docs/learnings.md and confirms the save. Learnings are loaded at every session start via the load-kb hook.

When to Use It

To lock in a project rule or pattern (e.g., Always enable TypeScript strict mode in this project).
To encode a user or team preference (e.g., User prefers functional components over class components).
To document a coding pattern or approach (e.g., Pattern: fetch data in useEffect with cleanup).
To record a mistake or pitfall to avoid in future work (e.g., Avoid mutating state directly).
To log a strategic decision or architecture choice (e.g., Decided to migrate to a modular monorepo).

Quick Start

Step 1: Run /team-shinchan:learn \"Always use TypeScript strict mode in this project\"
Step 2: Review the confirmation message that the learning was saved
Step 3: (Optional) Open .shinchan-docs/learnings.md to verify or use /team-shinchan:forget to remove it

Best Practices

Be concise and explicit in the learning content.
Use the appropriate category (preference, pattern, convention, mistake, decision, or insight).
Keep learnings project-scoped and avoid duplicates.
Include a clear content string so future sessions apply the memory reliably.
Verify the memory after saving and update the source file when needed.

Example Use Cases

Always use TypeScript strict mode in this project
User prefers functional components over class components
Pattern: fetch data in useEffect with cleanup
Avoid mutating state directly in reducers
Decided: migrate to a modular monorepo structure

Frequently Asked Questions

Add this skill to your agents