The essentials at a glance

Learning Skill v2.0
Under the Hood

A Claude Code plugin that transforms codebases into interactive HTML courses and Knowledge Graphs. Here's how it works on the inside.

+ 6 deep-dive pages available

01
The Learning Skill from the Inside
Architecture overview: skill.md as the heart, 8 agents, 3 modes

The entire system is orchestrated by a single file: skill.mdThe central configuration file with YAML frontmatter containing all rules, phase definitions, and templates for the skill.. It contains the YAML metadata, mode detection logic, all phase definitions, and quality gates. Claude reads this file and executes the pipelines defined within it.

Eight specialized agentsMarkdown files in the agents/ directory, dispatched as sub-agents by Claude. Each agent has a clear mandate and a defined output format. handle the analysis work in the comprehension pipeline: from project scanning through file analysis to graph validation. Three modes control what gets produced: Course, Knowledge Graph, or both.

Architecture Diagram
skill.md
Orchestrator + Rules
Course Mode
Phase 0-6
Comprehension Mode
Phase 0-7
Combined Mode
KG then Course
project-scanner
Inventory
file-analyzer
5x parallel
architecture-analyzer
Layers
tour-builder
Learning paths
graph-reviewer
Validation
assemble-reviewer
Assembly
domain-analyzer
Domain logic
knowledge-graph-guide
Dashboard
languages/
23 languages
frameworks/
10 frameworks
Dive into architecture
02
The Agent Pipeline
8 agents working together: Scan, Analyze, Architecture, Tour, Review

The comprehension pipeline starts with the project-scannerScans the codebase, detects languages and frameworks, produces a file inventory JSON with paths, LOC, and import maps., which creates a complete file inventory. Then up to five file-analyzer instances run in parallel, extracting nodes and edges for the Knowledge Graph.

The architecture-analyzerIdentifies 3-10 logical architecture layers (e.g., Core, Infrastructure, API) and assigns every file to exactly one layer. detects the layer structure, the tour-builder creates guided learning paths from it, and the graph-reviewer validates the entire graph with systematic checks.

Pipeline Flow
PS
project-
scanner
Inventory
FA1
file-
analyzer
FA2
file-
analyzer
FA3
file-
analyzer
FA4
file-
analyzer
FA5
file-
analyzer
AR
assemble-
reviewer
Merge
AA
architecture-
analyzer
Layers
TB
tour-
builder
Paths
GR
graph-
reviewer
Validation
Explore agents in detail
03
Knowledge Graph Pipeline
Phase 0-7: From pre-flight to the finished graph with 16 node types and 29 edge types

The comprehension pipeline runs through eight phases that produce a complete Knowledge GraphA JSON data structure containing nodes (files, functions, classes, concepts ...), edges (imports, calls, contains ...), layers, and a guided tour path.. Each phase has clear input/output contracts and is controlled by the orchestrator in skill.md.

The graph supports 16 node types (13 structural + 3 domain) and 29 edge types (26 structural + 3 domain). These types are defined as a schema in graph-reviewer.md and are strictly validated during the review phase.

Phase Overview
Phase 0
PRE-FLIGHT
Check git status, load config, create output directory .claude-learning/
Phase 1
SCAN
project-scanner creates file inventory: paths, languages, LOC, import maps
Phase 2
ANALYZE
5 file-analyzer instances extract nodes + edges per file batch in parallel
Phase 3
ASSEMBLE REVIEW
assemble-reviewer merges all batches, normalizes IDs, removes duplicates
Phase 4
ARCHITECTURE
architecture-analyzer identifies 3-10 layers and assigns every file to one
Phase 5
TOUR
tour-builder creates 5-15 guided learning steps through the codebase
Phase 6
REVIEW
graph-reviewer validates schema, referential integrity, completeness
Phase 7
SAVE
Save knowledge-graph.json + auto-launch dashboard
Dive into KG pipeline
04
HTML Course Pipeline
Phase 0-6: From bootstrap to depth map with Helpfulness Scoring

The course pipeline produces interactive HTML pages in seven phases. Central to it is the Helpfulness ScoringEach topic is rated on a 1-10 scale. Only topics above the audience-specific threshold (Dev: >=6) get their own sub-page. in Phase 2: it autonomously decides which topics deserve their own deep-dive page and which remain as a paragraph on the parent page.

Each audience runs an independent pipeline with its own depth profile. Developers get up to L3 (deep detail), users up to L2, executives only L1. Within a pipeline, topics and languages (DE/EN) are built in parallel.

HS Scoring — Interactive Calculator
HS = Complexity(0-3) + Relevance(0-3) + Learning Value(0-2) + Independence(0-2)
Helpfulness Score: 6 / 10
Developer: Create dedicated page
Dive into course pipeline
05
Design System & Templates
Energy-corporate palette, typography, CSS variables, module templates

All generated courses use the energy-corporate design with three primary colors: Deep Blue#000099 — used for navigation, hero sections, and module numbers (at 12% opacity). (#000099), Impulse Orange#FE8F11 — used for accents, buttons, links, progress bars, and deep-dive links. (#FE8F11), and Warm Gray#E4DAD4 — used for borders, alternating backgrounds (odd modules), and subtle dividers. (#E4DAD4).

The typography hierarchy uses Bricolage Grotesque for headlines, DM Sans as body font, and JetBrains Mono for code. CSS is driven by custom properties and fully embedded in each HTML file — no external build process required.

Color Palette
#000099
Deep Blue
--color-deep-blue
#FE8F11
Impulse Orange
--color-impulse-orange
#E4DAD4
Warm Gray
--color-warm-gray
#F3EFEB
Warm Gray BG
--color-warm-gray-bg
#000066
Code BG
--color-code-bg
#1A1A2E
Text
--color-text
Typography Preview
Bricolage Grotesque — Display / Headlines
Architecture of the Learning Skill
DM Sans — Body / Running Text
The skill transforms any codebase into interactive multi-level HTML courses with up to four depth levels and audience-specific helpfulness scoring.
JetBrains Mono — Code / Mono
HS = Complexity(0-3) + Relevance(0-3) + LearningValue(0-2) + Independence(0-2)
Dive into design system
06
How the Modes Work Together
Course Mode, Comprehension Mode, Combined Mode — and how KG data improves scoring

In Course Mode, Claude analyzes the codebase directly and produces HTML courses. In Comprehension Mode, only the Knowledge Graph with dashboard is created. Combined Mode is the best of both worlds: the KG is generated first, then its data feeds into course creation.

The key advantage of Combined Mode: KG data like fan-in/fan-outFan-in = number of incoming edges (how many other files import this one). Fan-out = outgoing edges. High fan-in indicates a core component., layer assignments, and complexity ratings make the Helpfulness Scoring more objective. A node with high fan-in automatically receives a relevance bonus.

Mode Comparison
Property Course Mode Comprehension Mode Combined Mode
Output HTML courses (L0-L3) knowledge-graph.json + dashboard Both
Phases Phase 0-6 Phase 0-7 Phase A0-A7, then B0-B6
Agents None (Claude directly) 8 specialized agents 8 agents + Claude directly
HS Scoring Heuristic-based Not applicable KG-enhanced (more objective)
KG Bonus Not available Not applicable +1 Complexity, +1 Fan-in, +1 Core-Layer, +1 Edge density
Keywords "course", "tutorial", "HTML" "understand", "graph", "dashboard" "both", "combined", "everything"
Dive into mode interplay
07
Extensibility
Languages, frameworks, agent definitions, custom audiences

The Learning Skill is modular by design. New programming languages are added as Markdown files in languages/ (currently 23 languages from C++ to YAML). Framework-specific rules live in frameworks/ (10 frameworks from Django to Vue). Each file extends agent knowledge without touching skill.md.

Beyond the three predefined audiences (User, Developer, Executive), custom audiences with their own depth profiles can be defined. Agent definitions in agents/ are equally extensible — each agent is a standalone Markdown file with YAML frontmatter and a clear prompt template.

Directory Structure
# Learning Skill v2.0 — Directory Tree skill.md # Orchestrator + rules agents/ project-scanner.md # File inventory file-analyzer.md # Extract nodes + edges architecture-analyzer.md # Layer detection tour-builder.md # Learning paths graph-reviewer.md # Graph validation assemble-reviewer.md # Batch merge domain-analyzer.md # Domain logic knowledge-graph-guide.md # Dashboard languages/ # 23 language addenda typescript.md python.md rust.md go.md ... frameworks/ # 10 framework addenda react.md nextjs.md django.md spring.md ...