By dasboe
AI learning coach — personalized sessions adapted to your technical level and pace. One session, one technique learned, one thing created.
npx claudepluginhub dasboe/ai-learnSets up the AI-LERN learning environment for the plugin version.
Session-Abschluss. Lies `${CLAUDE_PLUGIN_ROOT}/skills/ai-learn/close.md` und folge dem Flow komplett.
Trigger den ai-learn Skill. Lies `${CLAUDE_PLUGIN_ROOT}/skills/ai-learn/SKILL.md` und folge dem Flow.
Learn to work with AI — at your level, at your pace. A Claude Code plugin.
A Claude Code plugin that turns Claude into your personal AI tutor. It adapts to you — whether you run a business, practice law, design interfaces, or write code. Claude interviews you once, then builds a personalized learning path. Each session: one concept learned, one thing built.
You need:
Then in Claude Code:
/plugin marketplace add dasboe/ai-learn
/plugin install ai-learn@ai-learn-marketplace
Then type /ai-learn:start.
That's it. Claude interviews you once, then every session starts with /ai-learn:start.
/ai-learn:start — the first time, Claude interviews you (5 min)/ai-learn:start, learn, build, /ai-learn:end| Command | What it does |
|---|---|
/ai-learn:start | Start a session — interview (first time) or next lesson |
/ai-learn:end | Close the session — saves progress, updates context |
/ai-learn:bootstrap | Initial setup for new learners |
Everything adapts — content, complexity, pace, language. An electrician might use AI to write client proposals in seconds. A lawyer might build an AI-assisted contract review workflow. A designer might go from Figma to working prototype without waiting on developers. A retired teacher might explore AI out of pure curiosity. A developer might have a full-stack app running by session five. All are valid paths.
/end), PreToolUse (sandbox enforcement)The plugin creates these files in your working directory (not tracked by git):
your-project/
├── .settings/
│ ├── learner-profile.md <- your profile, created in the interview
│ └── context.md <- tracks where you are and what's next
├── sessions/
│ └── session-01/
│ └── README.md <- what you learned and built
├── reference/ <- lookup docs you build over time
└── project/ <- your learning project, grows session by session
What will I learn? How to work with AI effectively — starting with good prompting, then progressively deeper based on your background. Claude Code figures out what's relevant for you: practical text workflows, design-to-code prototyping, data automation, or full Claude Code mastery with CLAUDE.md, custom commands, and hooks. It depends on who you are.
Do I need to know how to code? No. Claude Code adapts to your background and profession — not just your tech level. A tradesperson gets AI tools for proposals and client communication. A designer gets prototyping workflows. A developer gets a full-stack coding partner. Everyone learns at their own pace.
What language does this work in? Any. Claude detects your language from your first message and matches it.
Can I change direction? Anytime. The learning path isn't a fixed curriculum — tell Claude what you want and it adjusts.
What's the meta-concept? You learn to work with AI by working with AI. Every session produces something real — a document, a script, a tool, an app. The learning IS the doing. There's no theory module you have to sit through first.
Copyright 2026 Björn Bösenberg. Licensed under MIT.
Created by @dasboe — built with Claude Code.
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Admin access level
Server config contains admin-level keywords
Modifies files
Hook triggers on file write and edit operations
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Intelligent prompt optimization using skill-based architecture. Enriches vague prompts with research-based clarifying questions before Claude Code executes them
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.