learn — community motoko, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for AI Agents like Claude Code needing intelligent knowledge management and session summary analysis. Filesystem-first knowledge management for Claude Code. Context Lake pattern with MCP integration.

joshuacook joshuacook
[0]
[0]
Updated: 3/5/2026

Agent Capability Analysis

The learn skill by joshuacook is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance.

Ideal Agent Persona

Ideal for AI Agents like Claude Code needing intelligent knowledge management and session summary analysis.

Core Value

Empowers agents to intelligently update roles and documents based on session summaries, leveraging Context Lake patterns and MCP integration for advanced knowledge curation, and utilizing filesystem-first approaches for efficient data management.

Capabilities Granted for learn

Intelligently curating role structures with dynamic 'Right Now' and 'Recent Context' sections
Automating updates to documentation based on compressed session summaries
Analyzing inbox session summaries to inform agent learning and knowledge management

! Prerequisites & Limits

  • Requires integration with Context Lake and MCP
  • Dependent on filesystem access for knowledge management
  • Optimized for use with Claude Code and similar AI agents
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

learn

Install learn, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with one-command setup.

SKILL.md
Readonly

Learn (System Learning)

Intelligently update roles and docs based on session summaries.

When to Activate

  • User says: "learn", "update roles"
  • After compressing sessions
  • When inbox has session summaries

Approach

OLD: Append bullets to logs NEW: Intelligent curation

Role structure:

  • What This Role Does (rarely changes)
  • Right Now ← CURATE (what's currently relevant)
  • Recent Context ← APPEND (timestamped, last 30 days)
  • How This Role Operates (rarely changes)

Process

1. Read Inbox

bash
1ls inbox/session-summaries/ 2cat inbox/session-summaries/*.md

2. Analyze Changes

Extract from summaries:

  • Decisions made
  • Tools/workflows built
  • Role activity
  • Context changes

Categorize:

  • Right Now: What's newly relevant for ongoing work
  • Recent Context: Timestamped decisions (auto-prune > 30 days)

3. Create Branch

bash
1git checkout -b learning-$(date +%Y-%m-%d)

4. Update Roles

For each affected role:

A. Read Current Role

bash
1cat roles/[role-file].md

B. Curate "Right Now"

This is CURATION, not appending:

  1. Read existing "Right Now"
  2. Add newly relevant context
  3. Remove stale/no-longer-relevant items
  4. Keep tight (5-10 bullets max)

C. Append "Recent Context"

Add timestamped entry at top:

markdown
1## Recent Context (Last 30 Days) 2 3**YYYY-MM-DD:** [Summary] 4- Key point 1 5- Key point 2 6 7[...existing entries...]

Auto-prune if > 10 entries.

D. Update "Last Updated"

5. Commit and PR

bash
1git add roles/*.md 2git commit -m "System learning: [summary]" 3git push -u origin learning-$(date +%Y-%m-%d) 4gh pr create --title "System Learning $(date +%Y-%m-%d)" --body "..." 5git checkout main

6. Report

System learning complete.

Processed: [N] session summaries
Roles updated: [list]
Branch: learning-YYYY-MM-DD
PR: #[number]

Next: Review and merge PR.

Curation Guidelines

"Right Now" = what's relevant:

  • Shapes how role operates TODAY
  • Would need to know this to do role's job
  • NOT just recent - could be weeks old but still relevant

"Recent Context" = what happened:

  • Timestamped decisions
  • Links to details if needed
  • Auto-prune oldest when > 10 entries

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is learn?

Ideal for AI Agents like Claude Code needing intelligent knowledge management and session summary analysis. Filesystem-first knowledge management for Claude Code. Context Lake pattern with MCP integration.

How do I install learn?

Run the command: npx killer-skills add joshuacook/motoko. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for learn?

Key use cases include: Intelligently curating role structures with dynamic 'Right Now' and 'Recent Context' sections, Automating updates to documentation based on compressed session summaries, Analyzing inbox session summaries to inform agent learning and knowledge management.

Which IDEs are compatible with learn?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for learn?

Requires integration with Context Lake and MCP. Dependent on filesystem access for knowledge management. Optimized for use with Claude Code and similar AI agents.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add joshuacook/motoko. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use learn immediately in the current project.

Related Skills

Looking for an alternative to learn or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

149.6k
0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

138.4k
0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
AI