This skill generates code tutorials from source code using Large Language Models (LLMs). It analyzes the source code, identifies abstractions and relationships, and generates a structured tutorial with chapters.
It has various commands such as analysis, build and preview.
npx @sshaaf/tutorial-skill install
# reload the coding agent. e.g. claude.
/tutorial build
You can preview the files in markdown on disk. for example preview in VSCode. however if you want to preview in html then use the following command.
/tutorial preview
- Code Discovery: Find and read source files
- Identify Abstractions: Extract core concepts
- Analyze Relationships: Map component interactions
- Code Discovery: Find and read source files
- Identify Abstractions: Extract core concepts
- Analyze Relationships: Map component interactions
- Organize Chapters: Determine pedagogical order
- Generate Metadata: Create tutorial info
- Write Content: Generate introduction + chapters
Works with any programming language:
- Java, Python, JavaScript/TypeScript, Go, C#, Ruby, PHP, Rust, Kotlin etc.
Fast codebase analysis with architecture diagrams
- Time: 2-5 minutes
- Output: Interactive summary + Mermaid diagram
- Use for: Understanding codebases, onboarding, planning refactors
Complete tutorial generation with chapters
- Time: 10-30 minutes
- Output: Multiple Markdown files + HonKit-ready docs scaffolding
- Use for: Creating learning materials, documentation, training resources
Local tutorial preview with HonKit
- Time: 5-30 seconds to start
- Output: Local docs site (usually
http://localhost:4000) - Use for: Reviewing generated docs before publishing
Diagnostics for local preview/runtime + docs scaffolding
- Time: ~10-30 seconds
- Output: Pass/fail checklist
- Use for: Verifying HonKit runtime +
book.jsonbefore publishing
# Install via NPM (recommended)
npx @sshaaf/tutorial-skill installThe installer bootstraps a local HonKit runtime under ~/.claude/skills/tutorial/.runtime/honkit and installs honkit-plugin-mermaid-hybrid for diagram rendering.
Alternative methods:
# Manual install from source
cp -r tutorial ~/.claude/skills/tutorial
# Or extract from package
tar -xzf tutorial.skill -C ~/.claude/skills/Note: alternative/manual installation methods do not bootstrap the bundled HonKit runtime; use the NPM installer for the default preview workflow.
# Quick analysis
/tutorial analyze .
# With path
/tutorial analyze ./src/main/java
# Full tutorial
/tutorial build .
# With output directory
/tutorial build --output ./docs/tutorial
# Preview generated tutorial in Claude mode
/tutorial preview ./docs/tutorial
# Diagnose local preview/runtime/docs scaffolding
/tutorial doctor ./docs/tutorial
# Initialize docs files for HonKit
npx @sshaaf/tutorial-skill docs init --dir ./docs/tutorial
# Preview locally with HonKit
npx @sshaaf/tutorial-skill docs preview --dir ./docs/tutorial
# Build static site with HonKit
npx @sshaaf/tutorial-skill docs build --dir ./docs/tutorial
# Diagnose runtime/plugin setup
npx @sshaaf/tutorial-skill docs doctor --dir ./docs/tutorialhonkit is the default docs engine. --engine honkit is optional and supported for future engine compatibility.
If you are testing changes before publishing to npm, use the repo CLI (not npx), because npx resolves the published package version:
See DEV_TESTING.md for the short checklist.
- Focus on specific directories for large projects
- Exclude test files (done automatically)
- Ask follow-up questions after analysis
- Specify target audience (beginner/intermediate/advanced)
- Review chapter order before generation
- Regenerate specific chapters if needed
- SKILL.md: Complete skill implementation
- DEV_TESTING.md: Local testing checklist for maintainers
- Installation: See parent directory QUICK-START.md
- Comparison: See parent directory SKILLS-README.md
Extracted from Waver LLM by Shaaf Syed.
MIT License (same as Waver LLM)