diff --git a/CHANGELOG.md b/CHANGELOG.md
index 22eaa4f..e63c7b9 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,6 +6,37 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 
 ## [Unreleased]
 
+## [3.1.0] - 2026-01-13
+
+### Changed
+- **Major repository restructuring** - Reorganized 15 root files into 4 thematic directories
+  - `guide/` - Core documentation (ultimate-guide.md, cheatsheet.md, adoption-approaches.md)
+  - `tools/` - Interactive utilities (audit-prompt.md, onboarding-prompt.md, mobile-access.md)
+  - `machine-readable/` - LLM/AI consumption (reference.yaml, llms.txt)
+  - `exports/` - Generated outputs (notebooklm.pdf, kimi.pdf)
+- **File renaming** for cleaner paths:
+  - `english-ultimate-claude-code-guide.md` → `guide/ultimate-guide.md`
+  - `cheatsheet-en.md` → `guide/cheatsheet.md`
+  - `claude-setup-audit-prompt.md` → `tools/audit-prompt.md`
+  - `personalized-onboarding-prompt.md` → `tools/onboarding-prompt.md`
+  - `mobile-access-setup.md` → `tools/mobile-access.md`
+  - `claude-code-reference.yaml` → `machine-readable/reference.yaml`
+- **README.md** - Added "Repository Structure" section with visual tree
+- **150+ internal links updated** across all documentation files
+- **Deleted** empty `to-ignore/` directory
+
+### Added
+- `guide/README.md` - Index for core documentation folder
+- `tools/README.md` - Index for interactive utilities folder
+- `machine-readable/README.md` - Index for LLM consumption folder
+- `exports/README.md` - Index for generated outputs folder
+
+### Stats
+- 10 files moved to new locations
+- 4 new README.md files created
+- 150+ links updated
+- Navigation significantly improved
+
 ## [3.0.7] - 2026-01-13
 
 ### Added
diff --git a/README.md b/README.md
index 2c06e47..f2b1a00 100644
--- a/README.md
+++ b/README.md
@@ -4,10 +4,6 @@
 [![GitHub stars](https://img.shields.io/github/stars/FlorianBruniaux/claude-code-ultimate-guide?style=social)](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/stargazers)
 [![Ask Zread](https://img.shields.io/badge/Ask_Zread-_.svg?style=flat&color=00b0aa&labelColor=000000&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB3aWR0aD0iMTYiIGhlaWdodD0iMTYiIHZpZXdCb3g9IjAgMCAxNiAxNiIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPHBhdGggZD0iTTQuOTYxNTYgMS42MDAxSDIuMjQxNTZDMS44ODgxIDEuNjAwMSAxLjYwMTU2IDEuODg2NjQgMS42MDE1NiAyLjI0MDFWNC45NjAxQzEuNjAxNTYgNS4zMTM1NiAxLjg4ODEgNS42MDAxIDIuMjQxNTYgNS42MDAxSDQuOTYxNTZDNS4zMTUwMiA1LjYwMDEgNS42MDE1NiA1LjMxMzU2IDUuNjAxNTYgNC45NjAxVjIuMjQwMUM1LjYwMTU2IDEuODg2NjQgNS4zMTUwMiAxLjYwMDEgNC45NjE1NiAxLjYwMDFaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00Ljk2MTU2IDEwLjM5OTlIMi4yNDE1NkMxLjg4ODEgMTAuMzk5OSAxLjYwMTU2IDEwLjY4NjQgMS42MDE1NiAxMS4wMzk5VjEzLjc1OTlDMS42MDE1NiAxNC4xMTM0IDEuODg4MSAxNC4zOTk5IDIuMjQxNTYgMTQuMzk5OUg0Ljk2MTU2QzUuMzE1MDIgMTQuMzk5OSA1LjYwMTU2IDE0LjExMzQgNS42MDE1NiAxMy43NTk5VjExLjAzOTlDNS42MDE1NiAxMC42ODY0IDUuMzE1MDIgMTAuMzk5OSA0Ljk2MTU2IDEwLjM5OTlaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik0xMy43NTg0IDEuNjAwMUgxMS4wMzg0QzEwLjY4NSAxLjYwMDEgMTAuMzk4NCAxLjg4NjY0IDEwLjM5ODQgMi4yNDAxVjQuOTYwMUMxMC4zOTg0IDUuMzEzNTYgMTAuNjg1IDUuNjAwMSAxMS4wMzg0IDUuNjAwMUgxMy43NTg0QzE0LjExMTkgNS42MDAxIDE0LjM5ODQgNS4zMTM1NiAxNC4zOTg0IDQuOTYwMVYyLjI0MDFDMTQuMzk4NCAxLjg4NjY0IDE0LjExMTkgMS42MDAxIDEzLjc1ODQgMS42MDAxWiIgZmlsbD0iI2ZmZiIvPgo8cGF0aCBkPSJNNCAxMkwxMiA0TDQgMTJaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00IDEyTDEyIDQiIHN0cm9rZT0iI2ZmZiIgc3Ryb2tlLXdpZHRoPSIxLjUiIHN0cm9rZS1saW5lY2FwPSJyb3VuZCIvPgo8L3N2Zz4K&logoColor=ffffff)](https://zread.ai/FlorianBruniaux/claude-code-ultimate-guide)
 
-```bash
-npm install -g @anthropic-ai/claude-code && claude
-```
-
 ---
 
 **Transparency note**: This guide reflects my personal experience after several months of daily Claude Code usage. I'm sharing what I've learned, not claiming expertise. The tool evolves constantly, and so does my understanding. [Feedback welcome](./CONTRIBUTING.md).
@@ -15,11 +11,11 @@ npm install -g @anthropic-ai/claude-code && claude
 ---
 
 **Start here:**
-- [Cheat Sheet](./cheatsheet-en.md) — print this, start coding
-- [15-min Quick Start](./english-ultimate-claude-code-guide.md#1-quick-start-day-1) — first workflow
+- [Cheat Sheet](./guide/cheatsheet.md) — print this, start coding
+- [15-min Quick Start](./guide/ultimate-guide.md#1-quick-start-day-1) — first workflow
 - [Audit your setup](./examples/scripts/audit-scan.sh) — quick scan
 
-**Go deeper** (optional): [Learning paths by role](#-by-role-tailored-learning-paths) | [Full guide](./english-ultimate-claude-code-guide.md)
+**Go deeper** (optional): [Learning paths by role](#-by-role-tailored-learning-paths) | [Full guide](./guide/ultimate-guide.md)
 
 ---
 
@@ -46,9 +42,8 @@ npm install -g @anthropic-ai/claude-code && claude
 
 ### Prerequisites
 
-- **Node.js 18+** (or use the [shell installer](./english-ultimate-claude-code-guide.md#11-installation) on macOS/Linux)
+- **Node.js 18+** (or use the [shell installer](./guide/ultimate-guide.md#11-installation) on macOS/Linux)
 - **Anthropic API key** — [Get one here](https://console.anthropic.com/)
-- **~$5-20/month** typical usage cost (varies with usage intensity)
 
 ---
 
@@ -58,19 +53,19 @@ npm install -g @anthropic-ai/claude-code && claude
 
 | If you... | Start here | Depth |
 |-----------|------------|-------|
-| Just installed Claude Code | [Quick Start](#-quick-start-15-minutes) | Essentials |
+| Just installed Claude Code | [Quick Start](./guide/ultimate-guide.md#1-quick-start-day-1) | Essentials |
 | Want to understand core concepts | [Junior Path](#-by-role-tailored-learning-paths) | Foundation |
 | Already use AI coding tools | [Senior Path](#-by-role-tailored-learning-paths) | Intermediate |
 | Need to configure a team setup | [Power User Path](#-by-role-tailored-learning-paths) | Comprehensive |
 | Need to evaluate/approve adoption | [PM Path](#-by-role-tailored-learning-paths) | Overview |
-| Choosing turnkey vs. autonomous approach | [Adoption Guide](./adoption-approaches.md) | Quick read |
+| Choosing turnkey vs. autonomous approach | [Adoption Guide](./guide/adoption-approaches.md) | Quick read |
 | Want to check your current setup | [Audit Your Setup](#-audit-your-setup) | Quick scan |
 | Want AI assistants to know Claude Code | [LLM Reference](#-llm-reference) | Reference |
 | Want personalized recommendations | [Deep Audit](#-deep-audit-personalized-recommendations) | Quick scan |
 | Want to test your knowledge | [Knowledge Quiz](#-knowledge-quiz) | Interactive |
-| Want a guided tour | [Personalized Onboarding](./personalized-onboarding-prompt.md) | Interactive |
+| Want a guided tour | [Personalized Onboarding](./tools/onboarding-prompt.md) | Interactive |
 | Having issues with Claude Code | [/diagnose command](./examples/commands/diagnose.md) | Quick fix |
-| Want mobile access to Claude Code | [Mobile Access Setup](./mobile-access-setup.md) | WIP |
+| Want mobile access to Claude Code | [Mobile Access Setup](./tools/mobile-access.md) | WIP |
 
 ### ⚡ Audit Your Setup
 
@@ -82,19 +77,19 @@ curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-
 
 **Instant checks**: Config files, tech stack, extensions, security hooks, MCP servers, CLAUDE.md quality
 
-**Want deeper analysis?** Use [`claude-setup-audit-prompt.md`](./claude-setup-audit-prompt.md) for personalized recommendations (~3 min).
+**Want deeper analysis?** Use [`tools/audit-prompt.md`](./tools/audit-prompt.md) for personalized recommendations (~3 min).
 
 ### 🤖 LLM Reference
 
 Give any AI assistant instant Claude Code expertise (~2K tokens):
 
 ```bash
-curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/claude-code-reference.yaml
+curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/machine-readable/reference.yaml
 ```
 
-**Use cases**: Paste output into ChatGPT/Claude/Gemini, add to system prompts, or reference in Claude Code with `@claude-code-reference.yaml`
+**Use cases**: Paste output into ChatGPT/Claude/Gemini, add to system prompts, or reference in Claude Code with `@machine-readable/reference.yaml`
 
-**What's inside**: Decision trees, command reference, context zones, MCP servers, agent templates, troubleshooting—optimized for machine consumption. Points to line numbers in the [full guide](./english-ultimate-claude-code-guide.md) for deep dives.
+**What's inside**: Decision trees, command reference, context zones, MCP servers, agent templates, troubleshooting—optimized for machine consumption. Points to line numbers in the [full guide](./guide/ultimate-guide.md) for deep dives.
 
 ### 🔬 Deep Audit (Personalized Recommendations)
 
@@ -111,7 +106,7 @@ curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-
 ```bash
 # Claude Code Deep Audit - Context-Aware Version
 # Downloads reference files, reads YOUR local files, analyzes with Claude
-REF=$(curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/claude-code-reference.yaml)
+REF=$(curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/machine-readable/reference.yaml)
 SCAN=$(curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/examples/scripts/audit-scan.sh | bash -s -- --json 2>/dev/null)
 README_CONTENT=$(head -100 README.md 2>/dev/null || echo "No README.md found")
 CLAUDE_MD=$(cat CLAUDE.md 2>/dev/null || echo "No CLAUDE.md found")
@@ -151,7 +146,7 @@ Based on ALL this context, provide:
 - Domain-aware suggestions (e.g., EdTech → session planning agents, E-commerce → inventory commands)
 - Non-duplicate suggestions: Only recommends agents/commands you don't already have
 
-**Want maximum depth?** Use [claude-setup-audit-prompt.md](./claude-setup-audit-prompt.md) with `claude --ultrathink`
+**Want maximum depth?** Use [tools/audit-prompt.md](./tools/audit-prompt.md) with `claude --ultrathink`
 
 ### 🧠 Knowledge Quiz
 
@@ -208,7 +203,7 @@ Explanation:
 Exit code 2 blocks the operation. Exit code 0 allows it to proceed.
 Other exit codes are treated as errors and logged but don't block.
 
-See: english-ultimate-claude-code-guide.md#72-creating-hooks
+See: guide/ultimate-guide.md#72-creating-hooks
 
 ------------------------------------------------------------
    QUIZ COMPLETE
@@ -248,22 +243,22 @@ Weak Areas (< 75%):
 
 **Junior Developer** (Foundation path)
 
-1. [Quick Start](./english-ultimate-claude-code-guide.md#1-quick-start-day-1) — Install & first workflow
-2. [Essential Commands](./english-ultimate-claude-code-guide.md#13-essential-commands) — The 7 commands
-3. [Context Management](./english-ultimate-claude-code-guide.md#22-context-management) — Critical concept
-4. [Memory Files](./english-ultimate-claude-code-guide.md#31-memory-files-claudemd) — Your first CLAUDE.md
-5. [Cheat Sheet](./cheatsheet-en.md) — Print this
+1. [Quick Start](./guide/ultimate-guide.md#1-quick-start-day-1) — Install & first workflow
+2. [Essential Commands](./guide/ultimate-guide.md#13-essential-commands) — The 7 commands
+3. [Context Management](./guide/ultimate-guide.md#22-context-management) — Critical concept
+4. [Memory Files](./guide/ultimate-guide.md#31-memory-files-claudemd) — Your first CLAUDE.md
+5. [Cheat Sheet](./guide/cheatsheet.md) — Print this
 
 </td>
 <td width="50%">
 
 **Senior Developer** (Intermediate path)
 
-1. [Core Concepts](./english-ultimate-claude-code-guide.md#2-core-concepts) — Mental model
-2. [Plan Mode](./english-ultimate-claude-code-guide.md#23-plan-mode) — Safe exploration
-3. [Agents](./english-ultimate-claude-code-guide.md#4-agents) — Custom AI personas
-4. [Hooks](./english-ultimate-claude-code-guide.md#7-hooks) — Event automation
-5. [CI/CD Integration](./english-ultimate-claude-code-guide.md#93-cicd-integration) — Pipelines
+1. [Core Concepts](./guide/ultimate-guide.md#2-core-concepts) — Mental model
+2. [Plan Mode](./guide/ultimate-guide.md#23-plan-mode) — Safe exploration
+3. [Agents](./guide/ultimate-guide.md#4-agents) — Custom AI personas
+4. [Hooks](./guide/ultimate-guide.md#7-hooks) — Event automation
+5. [CI/CD Integration](./guide/ultimate-guide.md#93-cicd-integration) — Pipelines
 
 </td>
 </tr>
@@ -272,10 +267,10 @@ Weak Areas (< 75%):
 
 **Power User** (Comprehensive path)
 
-1. [Complete Guide](./english-ultimate-claude-code-guide.md) — End-to-end
-2. [MCP Servers](./english-ultimate-claude-code-guide.md#8-mcp-servers) — Extended capabilities
-3. [Trinity Pattern](./english-ultimate-claude-code-guide.md#91-the-trinity) — Advanced workflows
-4. [Audit](./claude-setup-audit-prompt.md) — Optimize setup
+1. [Complete Guide](./guide/ultimate-guide.md) — End-to-end
+2. [MCP Servers](./guide/ultimate-guide.md#8-mcp-servers) — Extended capabilities
+3. [Trinity Pattern](./guide/ultimate-guide.md#91-the-trinity) — Advanced workflows
+4. [Audit](./tools/audit-prompt.md) — Optimize setup
 5. [Examples](./examples/) — Production templates
 
 </td>
@@ -285,8 +280,8 @@ Weak Areas (< 75%):
 
 1. [What's Inside](#-complete-toolkit) — Scope
 2. [Golden Rules](#-golden-rules) — Key principles
-3. [Core Concepts](./english-ultimate-claude-code-guide.md#2-core-concepts) — High-level
-4. [Context Management](./english-ultimate-claude-code-guide.md#22-context-management) — Why it matters
+3. [Core Concepts](./guide/ultimate-guide.md#2-core-concepts) — High-level
+4. [Context Management](./guide/ultimate-guide.md#22-context-management) — Why it matters
 
 </td>
 </tr>
@@ -300,21 +295,55 @@ Weak Areas (< 75%):
 
 | File | Purpose | Time Investment |
 |------|---------|-----------------|
-| **[Ultimate Guide](./english-ultimate-claude-code-guide.md)** | Complete reference, 10 sections | ~3 hours (or by section) |
-| **[Cheat Sheet](./cheatsheet-en.md)** | 1-page printable reference | 5 minutes |
-| **[LLM Reference](./claude-code-reference.yaml)** | Machine-optimized index (~2K tokens) | For Claude/AI assistants |
-| **[Setup Audit](./claude-setup-audit-prompt.md)** | Optimize your configuration | ~10 minutes |
+| **[Ultimate Guide](./guide/ultimate-guide.md)** | Complete reference, 10 sections | ~3 hours (or by section) |
+| **[Cheat Sheet](./guide/cheatsheet.md)** | 1-page printable reference | 5 minutes |
+| **[LLM Reference](./machine-readable/reference.yaml)** | Machine-optimized index (~2K tokens) | For Claude/AI assistants |
+| **[Setup Audit](./tools/audit-prompt.md)** | Optimize your configuration | ~10 minutes |
 | **[Examples Library](./examples/)** | Production-ready templates | Browse as needed |
 
 <details>
 <summary><strong>Alternative Formats</strong> (Interactive AI, PDFs)</summary>
 
 - **[DeepWiki](https://deepwiki.com/FlorianBruniaux/claude-code-ultimate-guide/1-overview)** — AI-powered Q&A, semantic search, instant summaries
-- **[NotebookLM Slides](./claude-code-ultimate-guide_notebooklm.pdf)** — Visual overview (~20 min)
-- **[Kimi PDF](./claude-code-ultimate-guide_kimi.pdf)** — Full text export (~3 hours)
+- **[NotebookLM Slides](./exports/notebooklm.pdf)** — Visual overview (~20 min)
+- **[Kimi PDF](./exports/kimi.pdf)** — Full text export (~3 hours)
 
 </details>
 
+### Repository Structure
+
+```
+claude-code-ultimate-guide/
+├── guide/                    # 📖 Core documentation
+│   ├── ultimate-guide.md     # Complete reference (8500+ lines)
+│   ├── cheatsheet.md         # 1-page printable reference
+│   └── adoption-approaches.md # Team implementation strategies
+│
+├── tools/                    # 🔧 Interactive utilities
+│   ├── audit-prompt.md       # Setup audit with recommendations
+│   ├── onboarding-prompt.md  # Personalized guided tour
+│   └── mobile-access.md      # Mobile access setup (ttyd + Tailscale)
+│
+├── machine-readable/         # 🤖 LLM/AI consumption
+│   ├── reference.yaml        # Structured index (~2K tokens)
+│   └── llms.txt              # Standard LLM context file
+│
+├── exports/                  # 📄 Generated outputs
+│   ├── notebooklm.pdf        # Visual slides
+│   └── kimi.pdf              # Full PDF export
+│
+├── examples/                 # 📦 Production templates
+│   ├── agents/               # Custom AI personas
+│   ├── commands/             # Slash commands (/pr, /commit, /diagnose...)
+│   ├── hooks/                # Security & automation (bash + PowerShell)
+│   ├── skills/               # Reusable knowledge modules
+│   ├── scripts/              # Setup & diagnostic utilities
+│   ├── github-actions/       # CI/CD workflows
+│   └── ...
+│
+└── quiz/                     # 🧠 Interactive knowledge quiz (159 questions)
+```
+
 ---
 
 ## 🎯 Production-Ready Examples
@@ -353,20 +382,20 @@ Copy-paste templates from [`examples/`](./examples/) for immediate use:
 
 ## 📖 Guide Navigation
 
-Jump directly to any section in the [Ultimate Guide](./english-ultimate-claude-code-guide.md):
+Jump directly to any section in the [Ultimate Guide](./guide/ultimate-guide.md):
 
 | Section | After this, you can... | When |
 |---------|------------------------|------|
-| **[1. Quick Start](./english-ultimate-claude-code-guide.md#1-quick-start-day-1)** | Run Claude Code and complete your first AI-assisted task | Day 1 |
-| **[2. Core Concepts](./english-ultimate-claude-code-guide.md#2-core-concepts)** | Manage context efficiently and avoid common pitfalls | Week 1 |
-| **[3. Memory & Settings](./english-ultimate-claude-code-guide.md#3-memory--settings)** | Create CLAUDE.md files that improve AI responses | First project |
-| **[4. Agents](./english-ultimate-claude-code-guide.md#4-agents)** | Build custom AI personas for specialized workflows | Advanced |
-| **[5. Skills](./english-ultimate-claude-code-guide.md#5-skills)** | Package reusable knowledge modules for your team | Scaling |
-| **[6. Commands](./english-ultimate-claude-code-guide.md#6-commands)** | Create custom slash commands with variable interpolation | Automation |
-| **[7. Hooks](./english-ultimate-claude-code-guide.md#7-hooks)** | Automate security checks and formatting on every action | Production |
-| **[8. MCP Servers](./english-ultimate-claude-code-guide.md#8-mcp-servers)** | Extend Claude with databases, browsers, and external tools | Extended |
-| **[9. Advanced Patterns](./english-ultimate-claude-code-guide.md#9-advanced-patterns)** | Orchestrate Trinity workflows and CI/CD pipelines | Power user |
-| **[10. Reference](./english-ultimate-claude-code-guide.md#10-reference)** | Look up commands, shortcuts, and troubleshooting tips | Daily |
+| **[1. Quick Start](./guide/ultimate-guide.md#1-quick-start-day-1)** | Run Claude Code and complete your first AI-assisted task | Day 1 |
+| **[2. Core Concepts](./guide/ultimate-guide.md#2-core-concepts)** | Manage context efficiently and avoid common pitfalls | Week 1 |
+| **[3. Memory & Settings](./guide/ultimate-guide.md#3-memory--settings)** | Create CLAUDE.md files that improve AI responses | First project |
+| **[4. Agents](./guide/ultimate-guide.md#4-agents)** | Build custom AI personas for specialized workflows | Advanced |
+| **[5. Skills](./guide/ultimate-guide.md#5-skills)** | Package reusable knowledge modules for your team | Scaling |
+| **[6. Commands](./guide/ultimate-guide.md#6-commands)** | Create custom slash commands with variable interpolation | Automation |
+| **[7. Hooks](./guide/ultimate-guide.md#7-hooks)** | Automate security checks and formatting on every action | Production |
+| **[8. MCP Servers](./guide/ultimate-guide.md#8-mcp-servers)** | Extend Claude with databases, browsers, and external tools | Extended |
+| **[9. Advanced Patterns](./guide/ultimate-guide.md#9-advanced-patterns)** | Orchestrate Trinity workflows and CI/CD pipelines | Power user |
+| **[10. Reference](./guide/ultimate-guide.md#10-reference)** | Look up commands, shortcuts, and troubleshooting tips | Daily |
 
 ---
 
@@ -482,7 +511,7 @@ If this guide saved you time, helped you master Claude Code, or inspired your wo
 
 ---
 
-*Version 3.0.5 | January 2026 | Crafted with Claude*
+*Version 3.1.0 | January 2026 | Crafted with Claude*
 
 <!-- SEO Keywords -->
 <!-- claude code, claude code tutorial, anthropic cli, ai coding assistant, claude code mcp,
diff --git a/examples/README.md b/examples/README.md
index 33d0a93..c59d606 100644
--- a/examples/README.md
+++ b/examples/README.md
@@ -122,4 +122,4 @@ Ready-to-use templates for Claude Code configuration.
 
 ---
 
-*See the [main guide](../english-ultimate-claude-code-guide.md) for detailed explanations.*
+*See the [main guide](../guide/ultimate-guide.md) for detailed explanations.*
diff --git a/examples/commands/diagnose.md b/examples/commands/diagnose.md
index 29fcd90..09031c0 100644
--- a/examples/commands/diagnose.md
+++ b/examples/commands/diagnose.md
@@ -19,7 +19,7 @@ Silently fetch the troubleshooting reference:
 
 ```bash
 # Fetch the latest troubleshooting guide from the repo
-curl -sL "https://raw.githubusercontent.com/flobby41/claude-code-ultimate-guide/main/english-ultimate-claude-code-guide.md" | head -n 3000
+curl -sL "https://raw.githubusercontent.com/flobby41/claude-code-ultimate-guide/main/guide/ultimate-guide.md" | head -n 3000
 ```
 
 Use Section 10.4 (Troubleshooting) as your primary reference.
diff --git a/examples/hooks/README.md b/examples/hooks/README.md
index cd3c2b3..fbd584e 100644
--- a/examples/hooks/README.md
+++ b/examples/hooks/README.md
@@ -440,10 +440,10 @@ exit 0
 
 ## Resources
 
-- [Main Guide - Section 7: Hooks](../../english-ultimate-claude-code-guide.md#7-hooks)
+- [Main Guide - Section 7: Hooks](../../guide/ultimate-guide.md#7-hooks)
 - [Claude Code Documentation](https://docs.anthropic.com/en/docs/claude-code)
-- [Hook Event Reference](../../english-ultimate-claude-code-guide.md#71-hook-events)
+- [Hook Event Reference](../../guide/ultimate-guide.md#71-hook-events)
 
 ---
 
-*See the [main guide](../../english-ultimate-claude-code-guide.md) for detailed explanations and advanced patterns.*
+*See the [main guide](../../guide/ultimate-guide.md) for detailed explanations and advanced patterns.*
diff --git a/examples/modes/README.md b/examples/modes/README.md
index f2a7091..7dd98dc 100644
--- a/examples/modes/README.md
+++ b/examples/modes/README.md
@@ -72,5 +72,5 @@ SuperClaude also includes:
 
 ## See Also
 
-- [Guide Section 10.5: SuperClaude Framework](../../english-ultimate-claude-code-guide.md#105-superclaude-framework) — Full documentation
+- [Guide Section 10.5: SuperClaude Framework](../../guide/ultimate-guide.md#105-superclaude-framework) — Full documentation
 - [SuperClaude Repository](https://github.com/SuperClaude-Org/SuperClaude_Framework) — Complete framework
diff --git a/exports/README.md b/exports/README.md
new file mode 100644
index 0000000..38ae134
--- /dev/null
+++ b/exports/README.md
@@ -0,0 +1,20 @@
+# Exported Formats
+
+Alternative formats generated from the main guide.
+
+## Contents
+
+| File | Description | Best For |
+|------|-------------|----------|
+| [notebooklm.pdf](./notebooklm.pdf) | Visual overview generated by NotebookLM | Quick visual scan (~20 min) |
+| [kimi.pdf](./kimi.pdf) | Full text PDF export | Offline reading |
+
+## Notes
+
+- These files are **generated outputs**, not source content
+- The source of truth is [`guide/ultimate-guide.md`](../guide/ultimate-guide.md)
+- PDFs may lag behind the latest guide updates
+
+---
+
+*Back to [main README](../README.md)*
diff --git a/claude-code-ultimate-guide_kimi.pdf b/exports/kimi.pdf
similarity index 100%
rename from claude-code-ultimate-guide_kimi.pdf
rename to exports/kimi.pdf
diff --git a/claude-code-ultimate-guide_notebooklm.pdf b/exports/notebooklm.pdf
similarity index 100%
rename from claude-code-ultimate-guide_notebooklm.pdf
rename to exports/notebooklm.pdf
diff --git a/guide/README.md b/guide/README.md
new file mode 100644
index 0000000..123a618
--- /dev/null
+++ b/guide/README.md
@@ -0,0 +1,21 @@
+# Guide Documentation
+
+Core documentation for mastering Claude Code.
+
+## Contents
+
+| File | Description | Time |
+|------|-------------|------|
+| [ultimate-guide.md](./ultimate-guide.md) | Complete reference covering all Claude Code features | ~3 hours |
+| [cheatsheet.md](./cheatsheet.md) | 1-page printable quick reference | 5 min |
+| [adoption-approaches.md](./adoption-approaches.md) | Implementation strategies for teams | 15 min |
+
+## Recommended Reading Order
+
+1. **New users**: Start with Quick Start section in `ultimate-guide.md`
+2. **Daily reference**: Print `cheatsheet.md`
+3. **Team leads**: Read `adoption-approaches.md` for rollout strategies
+
+---
+
+*Back to [main README](../README.md)*
diff --git a/adoption-approaches.md b/guide/adoption-approaches.md
similarity index 91%
rename from adoption-approaches.md
rename to guide/adoption-approaches.md
index 5ce7a43..592f805 100644
--- a/adoption-approaches.md
+++ b/guide/adoption-approaches.md
@@ -109,7 +109,7 @@ If you prefer understanding before configuring, here's a progressive approach. N
 
 **Goal**: Understand how Claude Code operates before adding config.
 
-1. Read [Section 5: Mental Model](./english-ultimate-claude-code-guide.md) (line 1675)
+1. Read [Section 5: Mental Model](./ultimate-guide.md) (line 1675)
 2. Core concept: Claude works in a loop — prompt → plan → execute → verify
 3. **Try it**: Complete a few real tasks with zero config. Notice where friction appears.
 
@@ -117,7 +117,7 @@ If you prefer understanding before configuring, here's a progressive approach. N
 
 **Goal**: Understand the main constraint of the tool.
 
-1. Read [Context Management](./english-ultimate-claude-code-guide.md) (line 944)
+1. Read [Context Management](./ultimate-guide.md) (line 944)
 2. The general idea (exact thresholds vary by use case):
    - Low usage: work freely
    - Medium usage: be more selective
@@ -129,7 +129,7 @@ If you prefer understanding before configuring, here's a progressive approach. N
 
 **Goal**: Give Claude project context.
 
-1. Read [Memory Files](./english-ultimate-claude-code-guide.md) (line 2218)
+1. Read [Memory Files](./ultimate-guide.md) (line 2218)
 2. Precedence: project `.claude/CLAUDE.md` > global `~/.claude/CLAUDE.md`
 3. **Try it**: Create a minimal CLAUDE.md, test if Claude picks it up.
 
@@ -139,9 +139,9 @@ Add complexity only when you hit real problems:
 
 | Friction | Possible Solution | Reference |
 |----------|-------------------|-----------|
-| Repeating same task often | Consider an agent | [Agent Template](./english-ultimate-claude-code-guide.md) line 2793 |
-| Security concern | Consider a hook | [Hook Templates](./english-ultimate-claude-code-guide.md) line 4172 |
-| Need external tool access | Consider MCP | [MCP Config](./english-ultimate-claude-code-guide.md) line 4771 |
+| Repeating same task often | Consider an agent | [Agent Template](./ultimate-guide.md) line 2793 |
+| Security concern | Consider a hook | [Hook Templates](./ultimate-guide.md) line 4172 |
+| Need external tool access | Consider MCP | [MCP Config](./ultimate-guide.md) line 4771 |
 | AI repeats same mistake | Add a specific rule | Start with one line, not ten |
 
 Whether these solutions are worth the setup cost depends on your context.
@@ -355,12 +355,12 @@ Most people start with Sonnet. Adjust based on your experience.
 
 ## Related Resources
 
-- [Personalized Onboarding](./personalized-onboarding-prompt.md) — Interactive setup
-- [Setup Audit](./claude-setup-audit-prompt.md) — Diagnose configuration issues
-- [Examples Library](./examples/README.md) — Templates to adapt
-- [Main Guide](./english-ultimate-claude-code-guide.md) — Full reference
-- [Reference YAML](./claude-code-reference.yaml) — Condensed lookup
+- [Personalized Onboarding](../tools/onboarding-prompt.md) — Interactive setup
+- [Setup Audit](../tools/audit-prompt.md) — Diagnose configuration issues
+- [Examples Library](../examples/README.md) — Templates to adapt
+- [Main Guide](./ultimate-guide.md) — Full reference
+- [Reference YAML](../machine-readable/reference.yaml) — Condensed lookup
 
 ---
 
-*This guide reflects current observations, not proven best practices. The field is young — adapt heavily to your context. Feedback welcome: [CONTRIBUTING.md](./CONTRIBUTING.md)*
+*This guide reflects current observations, not proven best practices. The field is young — adapt heavily to your context. Feedback welcome: [CONTRIBUTING.md](../CONTRIBUTING.md)*
diff --git a/cheatsheet-en.md b/guide/cheatsheet.md
similarity index 98%
rename from cheatsheet-en.md
rename to guide/cheatsheet.md
index 8610336..a06de83 100644
--- a/cheatsheet-en.md
+++ b/guide/cheatsheet.md
@@ -6,7 +6,7 @@
 
 **Written with**: Claude (Anthropic)
 
-**Version**: 3.0.7 | **Last Updated**: January 2026
+**Version**: 3.1.0 | **Last Updated**: January 2026
 
 ---
 
@@ -370,7 +370,7 @@ where.exe claude; claude doctor; claude mcp list
 
 - **Official docs**: [docs.anthropic.com/claude-code](https://docs.anthropic.com/en/docs/claude-code)
 - **Advanced guide**: [Claudelog.com](https://claudelog.com/) - Tips & patterns
-- **Full guide**: `english-ultimate-claude-code-guide.md` (this repo)
+- **Full guide**: `ultimate-guide.md` (this repo)
 - **Project memory**: Create `CLAUDE.md` at project root
 - **DeepSeek (cost-effective)**: Configure via `ANTHROPIC_BASE_URL`
 
diff --git a/english-ultimate-claude-code-guide.md b/guide/ultimate-guide.md
similarity index 99%
rename from english-ultimate-claude-code-guide.md
rename to guide/ultimate-guide.md
index 0cfd3e9..fb93b99 100644
--- a/english-ultimate-claude-code-guide.md
+++ b/guide/ultimate-guide.md
@@ -10,7 +10,7 @@
 
 **Last updated**: January 2026
 
-**Version**: 3.0.7
+**Version**: 3.1.0
 
 ---
 
@@ -7912,7 +7912,7 @@ claude --add-dir ../shared-lib ../utils ../config
 
 ## 10.4 Troubleshooting
 
-> **Interactive Troubleshooting**: Use the `/diagnose` command for guided, interactive problem-solving. It auto-scans your environment and provides targeted solutions. See [examples/commands/diagnose.md](./examples/commands/diagnose.md).
+> **Interactive Troubleshooting**: Use the `/diagnose` command for guided, interactive problem-solving. It auto-scans your environment and provides targeted solutions. See [examples/commands/diagnose.md](../examples/commands/diagnose.md).
 
 ### Quick Diagnostic Guide
 
@@ -8813,7 +8813,7 @@ Use rebase for clean history before push, merge for shared branches.
 
 Use the included audit prompt to analyze your current Claude Code configuration:
 
-**File**: [`claude-setup-audit-prompt.md`](./claude-setup-audit-prompt.md)
+**File**: [`tools/audit-prompt.md`](../tools/audit-prompt.md)
 
 **What it does**:
 1. Scans your global (`~/.claude/`) and project (`.claude/`) configuration
diff --git a/machine-readable/README.md b/machine-readable/README.md
new file mode 100644
index 0000000..e4d969c
--- /dev/null
+++ b/machine-readable/README.md
@@ -0,0 +1,33 @@
+# Machine-Readable References
+
+Files optimized for LLM/AI consumption.
+
+## Contents
+
+| File | Description | Tokens |
+|------|-------------|--------|
+| [reference.yaml](./reference.yaml) | Structured index with line numbers for deep dives | ~2K |
+| [llms.txt](./llms.txt) | Standard LLM context file for repository indexation | ~1.5K |
+
+## Usage
+
+### Give Claude Code instant expertise
+
+```bash
+# Paste into any AI assistant
+curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/machine-readable/reference.yaml
+```
+
+### Reference in Claude Code
+
+```
+@machine-readable/reference.yaml
+```
+
+### Add to system prompts
+
+Include the YAML content in your AI assistant's system prompt for Claude Code expertise.
+
+---
+
+*Back to [main README](../README.md)*
diff --git a/llms.txt b/machine-readable/llms.txt
similarity index 75%
rename from llms.txt
rename to machine-readable/llms.txt
index 0c6e247..93b8dac 100644
--- a/llms.txt
+++ b/machine-readable/llms.txt
@@ -6,9 +6,9 @@
 
 This repository provides everything needed to go from Claude Code beginner to power user:
 
-1. **Complete Guide** (`english-ultimate-claude-code-guide.md`) - 4700+ lines covering all aspects of Claude Code
-2. **Cheatsheet** (`cheatsheet-en.md`) - 1-page printable daily reference
-3. **Audit Prompt** (`claude-setup-audit-prompt.md`) - Self-contained prompt to analyze your Claude Code setup against best practices
+1. **Complete Guide** (`guide/ultimate-guide.md`) - 4700+ lines covering all aspects of Claude Code
+2. **Cheatsheet** (`guide/cheatsheet.md`) - 1-page printable daily reference
+3. **Audit Prompt** (`tools/audit-prompt.md`) - Self-contained prompt to analyze your Claude Code setup against best practices
 
 ## Target Audience
 
@@ -50,12 +50,23 @@ This repository provides everything needed to go from Claude Code beginner to po
 ```
 claude-code-ultimate-guide/
 ├── README.md                           # Overview and quick start
-├── english-ultimate-claude-code-guide.md  # Complete guide (main content)
-├── cheatsheet-en.md                    # 1-page reference
-├── claude-setup-audit-prompt.md        # Setup audit tool
 ├── CONTRIBUTING.md                     # Contribution guidelines
 ├── CHANGELOG.md                        # Version history
-├── llms.txt                            # This file (for AI indexation)
+├── LICENSE                             # CC BY-SA 4.0
+├── guide/                              # Core documentation
+│   ├── ultimate-guide.md               # Complete guide (main content)
+│   ├── cheatsheet.md                   # 1-page reference
+│   └── adoption-approaches.md          # Implementation strategy
+├── tools/                              # Interactive utilities
+│   ├── audit-prompt.md                 # Setup audit tool
+│   ├── onboarding-prompt.md            # Personalized onboarding
+│   └── mobile-access.md                # Mobile access setup
+├── machine-readable/                   # LLM/AI consumption
+│   ├── reference.yaml                  # Machine-optimized index
+│   └── llms.txt                        # This file (for AI indexation)
+├── exports/                            # Generated outputs
+│   ├── notebooklm.pdf                  # Visual overview
+│   └── kimi.pdf                        # Full text export
 ├── examples/                           # Ready-to-use templates
 │   ├── agents/                         # Custom AI personas
 │   ├── skills/                         # Knowledge modules
@@ -63,7 +74,7 @@ claude-code-ultimate-guide/
 │   ├── hooks/                          # Event automation (bash + PowerShell)
 │   ├── config/                         # Configuration files
 │   └── memory/                         # CLAUDE.md templates
-└── *.pdf                               # Alternative formats
+└── quiz/                               # Interactive knowledge quiz
 ```
 
 ## Guide Structure (10 Sections)
@@ -122,14 +133,14 @@ CC BY-SA 4.0 - Free to share and adapt with attribution.
 
 1. **New to Claude Code?** Start with README.md Quick Start section
 2. **Choose your path** See Learning Paths in README for audience-specific guides
-3. **Want comprehensive learning?** Read english-ultimate-claude-code-guide.md
-4. **Need daily reference?** Print cheatsheet-en.md
-5. **Want to audit your setup?** Use claude-setup-audit-prompt.md
+3. **Want comprehensive learning?** Read guide/ultimate-guide.md
+4. **Need daily reference?** Print guide/cheatsheet.md
+5. **Want to audit your setup?** Use tools/audit-prompt.md
 6. **Need templates?** Browse examples/ folder for ready-to-use configs
 
 ## Machine-Optimized Reference
 
-For fast LLM parsing, see `claude-code-reference.yaml` (~2K tokens) - structured YAML with:
+For fast LLM parsing, see `machine-readable/reference.yaml` (~2K tokens) - structured YAML with:
 - Decision tree for task routing
 - Prompting formula (WHAT/WHERE/HOW/VERIFY)
 - Commands, shortcuts, CLI flags
diff --git a/claude-code-reference.yaml b/machine-readable/reference.yaml
similarity index 99%
rename from claude-code-reference.yaml
rename to machine-readable/reference.yaml
index 070bd2e..52ce59f 100644
--- a/claude-code-reference.yaml
+++ b/machine-readable/reference.yaml
@@ -1,13 +1,13 @@
 # claude-code-reference.yaml
 # Quick lookup for Claude Code - ~2K tokens target
-# Source: english-ultimate-claude-code-guide.md
+# Source: guide/ultimate-guide.md
 # Purpose: Condensed index for LLMs to quickly answer user questions about Claude Code
 
 version: "2.9.9"
 updated: "2026-01"
 
 # ════════════════════════════════════════════════════════════════
-# DEEP DIVE - Line numbers in english-ultimate-claude-code-guide.md
+# DEEP DIVE - Line numbers in guide/ultimate-guide.md
 # Usage: Read file at line N for detailed documentation on topic
 # ════════════════════════════════════════════════════════════════
 deep_dive:
diff --git a/quiz/README.md b/quiz/README.md
index 7a87479..d49010f 100644
--- a/quiz/README.md
+++ b/quiz/README.md
@@ -133,7 +133,7 @@ Explanation:
 Exit code 2 blocks the operation. Exit code 0 allows it to proceed.
 Other exit codes are treated as errors and logged but don't block.
 
-See: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/english-ultimate-claude-code-guide.md#72-creating-hooks
+See: https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/guide/ultimate-guide.md#72-creating-hooks
      (Line 4164)
 
 Progress: ██░░░░░░░░░░░░░░░░░░ 2/20 | Score: 1/2 (50%)
@@ -156,7 +156,7 @@ Weak Areas (< 75%):
   - Agents: Review section 4 in the guide
 
 Recommended Reading:
-  4. english-ultimate-claude-code-guide.md#4-agents
+  4. guide/ultimate-guide.md#4-agents
 
 Time: 9 minutes 2 seconds
 
diff --git a/quiz/questions/01-quick-start.yaml b/quiz/questions/01-quick-start.yaml
index 6b89356..b91f629 100644
--- a/quiz/questions/01-quick-start.yaml
+++ b/quiz/questions/01-quick-start.yaml
@@ -1,6 +1,6 @@
 category: "Quick Start"
 category_id: 1
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "01-001"
@@ -16,7 +16,7 @@ questions:
     explanation: |
       The universal installation method that works across all platforms (Windows, macOS, Linux) is `npm install -g @anthropic-ai/claude-code`. While shell scripts and Homebrew are available for specific platforms, npm is the recommended cross-platform approach. This ensures consistent installation regardless of your operating system.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.1 Installation"
       anchor: "#11-installation"
 
@@ -33,7 +33,7 @@ questions:
     explanation: |
       When Claude proposes a change, you have three options: press 'y' to accept the change, 'n' to reject and ask for alternatives, or 'e' to edit the change manually. This gives you full control over what gets applied to your codebase. Always review diffs before accepting - this is your safety net.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.2 First Workflow"
       anchor: "#12-first-workflow"
 
@@ -50,7 +50,7 @@ questions:
     explanation: |
       The `/help` command displays all available Claude Code commands. This is the go-to command when you're lost or want to discover available functionality. It's one of the 7 essential commands that cover 90% of daily usage.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.3 Essential Commands"
       anchor: "#13-essential-commands"
 
@@ -67,7 +67,7 @@ questions:
     explanation: |
       The `!` prefix executes shell commands immediately without asking Claude to do it. For example, `!git status` runs the command directly. Use this for quick status checks, view commands, and already-known commands. It's faster than asking Claude when you know exactly what command you need.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.3 Essential Commands"
       anchor: "#shell-commands-with-"
 
@@ -84,7 +84,7 @@ questions:
     explanation: |
       The `@` symbol references specific files in your prompts for targeted operations. For example, `Review @src/auth/login.tsx for security issues` directly loads that file. This provides precision (target exact files), speed (skip file discovery), and clarity (makes your intent explicit). Claude automatically loads the file content.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.3 Essential Commands"
       anchor: "#file-references-with-"
 
@@ -101,7 +101,7 @@ questions:
     explanation: |
       The guide recommends a hybrid approach: use Copilot for quick autocomplete and boilerplate while using Claude Code for feature implementation, debugging, code reviews, and understanding unfamiliar codebases. This leverages the strengths of both tools - Copilot excels at inline suggestions while Claude Code handles multi-file operations and complex reasoning.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.6 Migrating from Other AI Coding Tools"
       anchor: "#migration-guide-github-copilot--claude-code"
 
@@ -118,7 +118,7 @@ questions:
     explanation: |
       Plan Mode is Claude Code's "look but don't touch" mode. It allows reading files, searching the codebase, analyzing architecture, and proposing approaches. It prevents editing files, running state-modifying commands, creating new files, and making commits. Perfect for safe exploration before making changes.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.4 Permission Modes"
       anchor: "#plan-mode"
 
@@ -135,7 +135,7 @@ questions:
     explanation: |
       Use `claude --continue` or `claude -c` to automatically resume your most recent conversation. This maintains full context and conversation history across terminal sessions. For resuming a specific session by ID, use `claude --resume <id>` or `claude -r <id>`. This is particularly useful for multi-day features or when interrupted.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.3 Essential Commands"
       anchor: "#session-continuation-and-resume"
 
@@ -152,7 +152,7 @@ questions:
     explanation: |
       Always read the diff before accepting changes - this is your safety net. The guide emphasizes this as critical: "Always review diffs before accepting changes." While running tests is good practice, reviewing the diff is the immediate required step before any acceptance. You need to understand what changes are being proposed.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.2 First Workflow"
       anchor: "#step-3-review-the-diff"
 
@@ -169,7 +169,7 @@ questions:
     explanation: |
       Ctrl+C cancels the current operation in Claude Code. This is useful for stopping long-running analysis or when Claude is taking an approach you don't want. Esc dismisses the current suggestion, while Ctrl+R retries the last operation. Knowing these shortcuts helps maintain control during your workflow.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.3 Essential Commands"
       anchor: "#quick-actions--shortcuts"
 
@@ -186,7 +186,7 @@ questions:
     explanation: |
       Auto-accept mode should only be used for well-defined, reversible operations. The guide warns: "Only use auto-accept for well-defined, reversible operations." It's dangerous for complex or risky changes. Default mode (asking permission) is safest, especially for learning and production work.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.4 Permission Modes"
       anchor: "#auto-accept-mode"
 
@@ -203,7 +203,7 @@ questions:
     explanation: |
       The guide provides clear guidance: less than 5 lines of code - use Copilot/autocomplete; 5-50 lines in a single file - either tool works; more than 50 lines or multi-file changes - use Claude Code. This helps you choose the right tool for the task's complexity level.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.6 Migrating from Other AI Coding Tools"
       anchor: "#common-migration-issues"
 
@@ -220,7 +220,7 @@ questions:
     explanation: |
       Claude Code supports PNG, JPG, JPEG, WebP, and static GIF formats. You can paste images directly in the terminal (Cmd+V/Ctrl+V), drag and drop, or reference by path. This is useful for implementing UI from mockups, debugging visual issues, analyzing diagrams, and accessibility audits. Note that images consume significant context tokens (1000-2000 words equivalent).
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.3 Essential Commands"
       anchor: "#working-with-images-and-screenshots"
 
@@ -237,7 +237,7 @@ questions:
     explanation: |
       When you resume a session, Claude retains: full conversation history, files previously read/edited, CLAUDE.md and project settings, MCP server state (if Serena is used), and uncommitted code changes awareness. This comprehensive context preservation allows seamless continuation of complex, multi-day tasks.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.3 Essential Commands"
       anchor: "#context-preservation"
 
@@ -254,6 +254,6 @@ questions:
     explanation: |
       Use `claude --version` to verify your installation and display the current version. This is also useful before reporting bugs. After installation, you can also use `claude doctor` to verify auto-updater health and `claude update` to check for available updates.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.1 Installation"
       anchor: "#verify-installation"
diff --git a/quiz/questions/02-core-concepts.yaml b/quiz/questions/02-core-concepts.yaml
index faf5a9c..3969cce 100644
--- a/quiz/questions/02-core-concepts.yaml
+++ b/quiz/questions/02-core-concepts.yaml
@@ -1,6 +1,6 @@
 category: "Core Concepts"
 category_id: 2
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "02-001"
@@ -16,7 +16,7 @@ questions:
     explanation: |
       Use /compact when context reaches 70-90% (the red zone). The context zones are: Green (0-50%) - work freely; Yellow (50-75%) - start being selective; Red (75-90%) - use /compact; Critical (90%+) - must /clear or risk errors. Using /compact at 70% reduces usage by approximately 50% while preserving key context.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#context-zones"
 
@@ -33,7 +33,7 @@ questions:
     explanation: |
       Claude has a 200,000 token context window. Think of it like RAM - when it fills up, things slow down or fail. This context includes all messages, files read, command outputs, and tool results. Effective context management is described as "the most important concept in Claude Code."
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#the-context-budget"
 
@@ -50,7 +50,7 @@ questions:
     explanation: |
       The statusline metric 'Ctx(u): 45%' shows you've used 45% of your context window. The full statusline format is: `Claude Code | Ctx(u): 45% | Cost: $0.23 | Session: 1h 23m`. Monitoring this helps you know when to use /compact or /clear before context-related issues occur.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#reading-the-statusline"
 
@@ -67,7 +67,7 @@ questions:
     explanation: |
       /compact summarizes the conversation, preserving key context while reducing usage by approximately 50%. Use it when running low on context. /clear starts completely fresh, losing all context - use it when changing topics or context is severely bloated. Choose based on whether you need to maintain continuity.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#context-recovery-strategies"
 
@@ -84,7 +84,7 @@ questions:
     explanation: |
       Reading large files (5K+ tokens) and multi-file searches (3K+ tokens) consume the most context. A small file costs ~500 tokens, running commands ~1K tokens. Long conversations accumulate over time. To optimize, be specific in queries, use symbol references like "read the calculateTotal function" instead of entire files.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#what-consumes-context"
 
@@ -101,7 +101,7 @@ questions:
     explanation: |
       The Last 20% Rule recommends reserving approximately 20% of your context for: multi-file operations at end of session, last-minute corrections, and generating summary/checkpoint documents. This buffer ensures you can complete your work properly even as context fills up.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#context-inspection"
 
@@ -118,7 +118,7 @@ questions:
     explanation: |
       Context poisoning occurs when information from one task contaminates another. Examples include: style bleeding (blue button style applies to unrelated forms), instruction contamination (conflicting rules cause confusion), and temporal confusion (Claude uses outdated file names). Use explicit task boundaries and clarify priorities to prevent it.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#context-poisoning-bleeding"
 
@@ -135,7 +135,7 @@ questions:
     explanation: |
       The interaction loop is: 1) DESCRIBE - explain what you need, 2) ANALYZE - Claude explores the codebase, 3) PROPOSE - Claude suggests changes (diff), 4) REVIEW - you read and evaluate, 5) DECIDE - Accept/Reject/Modify, 6) VERIFY - run tests, check behavior, 7) COMMIT - save changes (optional). The key insight: you remain in control throughout.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.1 The Interaction Loop"
       anchor: "#21-the-interaction-loop"
 
@@ -152,7 +152,7 @@ questions:
     explanation: |
       Use /execute to exit Plan Mode and begin implementing changes. While in Plan Mode, Claude can only read and analyze - no modifications are allowed. You can also respond to Claude's prompt "Ready to implement this plan?" to transition. This staged approach ensures you understand the plan before execution.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.3 Plan Mode"
       anchor: "#exiting-plan-mode"
 
@@ -169,7 +169,7 @@ questions:
     explanation: |
       OpusPlan uses Opus for planning (with superior reasoning capabilities) and automatically switches to Sonnet for implementation (more cost-efficient). Enable with `/model opusplan`. This provides Opus-quality planning while preserving tokens through Sonnet-speed execution. Particularly valuable for Pro subscribers with limited Opus tokens.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.3 Plan Mode"
       anchor: "#opusplan-mode"
 
@@ -186,7 +186,7 @@ questions:
     explanation: |
       Context depletion symptoms include: shorter responses than usual (warning), forgetting CLAUDE.md instructions (serious), inconsistencies with earlier conversation (critical), errors on code already discussed (critical), and "I can't access that file" for files already read (critical). When critical symptoms appear, start a new session immediately.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#context-depletion-symptoms"
 
@@ -203,7 +203,7 @@ questions:
     explanation: |
       /rewind reverts file changes made by Claude. It works across multiple files but only on Claude's changes (not manual edits), only within the current session, and does NOT automatically revert git commits. For risky operations, create a git checkpoint first: "Let's commit what we have before trying this experimental approach."
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.4 Rewind"
       anchor: "#24-rewind"
 
@@ -220,7 +220,7 @@ questions:
     explanation: |
       Claude knows: file structure, code content, git state, and project rules (CLAUDE.md). Claude does NOT know: runtime state (can't see running processes), external services (can't access databases directly), your intent (needs clear instructions), and hidden files (respects .gitignore by default). Understanding this mental model helps you communicate effectively.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.5 Mental Model"
       anchor: "#what-claude-doesnt-know"
 
@@ -237,7 +237,7 @@ questions:
     explanation: |
       The Sanity Check Technique verifies Claude loaded your configuration. Add identifiable info to CLAUDE.md (like your name, project name, tech stack), then ask Claude "What is my name? What project am I working on?" Correct answers confirm configuration is loaded. For advanced checking, add multiple checkpoints throughout long CLAUDE.md files.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#sanity-check-technique"
 
@@ -254,7 +254,7 @@ questions:
     explanation: |
       Use XML-structured prompts when requests have 3+ distinct aspects (instruction + context + constraints), when ambiguity causes misunderstanding, when creating reusable templates, or for complex hierarchy. Don't use them for simple one-liner requests or quick typo fixes - the overhead outweighs the benefit. Tags like <instruction>, <context>, <constraints> help Claude understand different aspects.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.6 Structured Prompting with XML Tags"
       anchor: "#when-to-use-xml-structured-prompts"
 
@@ -271,7 +271,7 @@ questions:
     explanation: |
       The Session Handoff Pattern creates a document to bridge gaps between sessions. It includes: what was accomplished, current state, decisions made, next steps, and context for the next session. Create handoffs at end of work day, before context limit, when switching focus areas, or during interruptions. Store in `claudedocs/handoffs/handoff-YYYY-MM-DD.md`.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#session-handoff-pattern"
 
@@ -288,7 +288,7 @@ questions:
     explanation: |
       A typical 1-hour session costs $0.10 - $0.50 depending on usage patterns. The guide provides cost budgets: quick task (5-10 min) $0.05-$0.10, feature work (1-2 hours) $0.20-$0.50, deep refactor (half day) $1.00-$2.00. Spending $0.50 to save 30 minutes provides 60x ROI if your time is worth $30/hour - don't over-optimize!
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#cost-awareness--optimization"
 
@@ -305,6 +305,6 @@ questions:
     explanation: |
       Auto Plan Mode makes Claude present a plan and wait for explicit user approval before executing ANY tool. Configure via `~/.claude/auto-plan-mode.txt` and launch with `claude --append-system-prompt "$(cat ~/.claude/auto-plan-mode.txt)"`. Results in 76% fewer tokens with better results because plans are validated before execution.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.3 Plan Mode"
       anchor: "#auto-plan-mode"
diff --git a/quiz/questions/03-memory-settings.yaml b/quiz/questions/03-memory-settings.yaml
index 006b640..e77063f 100644
--- a/quiz/questions/03-memory-settings.yaml
+++ b/quiz/questions/03-memory-settings.yaml
@@ -1,6 +1,6 @@
 category: "Memory & Settings"
 category_id: 3
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "03-001"
@@ -16,7 +16,7 @@ questions:
     explanation: |
       The precedence is: Local (.claude/CLAUDE.md) > Project (/project/CLAUDE.md) > Global (~/.claude/CLAUDE.md). More specific beats more general. Local overrides are personal (gitignored), project settings are shared (committed), and global settings apply to all projects. This hierarchy allows personal preferences to override team conventions when needed.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.4 Precedence Rules"
       anchor: "#claudemd-precedence"
 
@@ -33,7 +33,7 @@ questions:
     explanation: |
       Team conventions should be stored in `/project/CLAUDE.md` (the project root). This file is committed to git and shared with the team. Local overrides go in `/project/.claude/CLAUDE.md` (gitignored), and personal global preferences go in `~/.claude/CLAUDE.md`. This separation ensures team standards are enforced while allowing personal customization.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.1 Memory Files (CLAUDE.md)"
       anchor: "#level-2-project-projectclaudemd"
 
@@ -50,7 +50,7 @@ questions:
     explanation: |
       settings.local.json stores personal permission overrides and is gitignored. It allows you to customize which tools are auto-allowed, denied, or require asking for your personal workflow without affecting team settings. For example, you might allow all git commands while the team requires confirmation for certain operations.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.3 Settings & Permissions"
       anchor: "#settingslocaljson-personal-permissions"
 
@@ -67,7 +67,7 @@ questions:
     explanation: |
       The `.claude/` folder in your project contains: agents/ (custom agent definitions), commands/ (custom slash commands), hooks/ (event-driven scripts), skills/ (knowledge modules), rules/ (auto-loaded conventions), and settings files. This is your project's Claude Code configuration directory for all extensions.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.2 The .claude/ Folder Structure"
       anchor: "#full-structure"
 
@@ -84,7 +84,7 @@ questions:
     explanation: |
       Tools in the 'deny' category are blocked completely - Claude cannot use them at all. The three permission behaviors are: 'allow' (auto-approve without asking), 'deny' (block completely), and 'ask' (prompt for confirmation). For example, denying "Bash(rm -rf *)" prevents accidental destructive operations.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.3 Settings & Permissions"
       anchor: "#permission-behavior"
 
@@ -101,7 +101,7 @@ questions:
     explanation: |
       The Single Source of Truth Pattern stores conventions in `/docs/conventions/` (coding-standards.md, architecture.md, testing.md, etc.) and references them from CLAUDE.md, CodeRabbit, and other tools. This prevents conflicts where one tool approves code that another flags. All tools enforce the same standards from one source.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.1 Memory Files (CLAUDE.md)"
       anchor: "#single-source-of-truth-pattern"
 
@@ -118,7 +118,7 @@ questions:
     explanation: |
       Project CLAUDE.md should include: tech stack (frameworks, versions), code conventions (naming, patterns), architecture (folder structure, layers), and common commands (dev, test, lint). This gives Claude project context. Never include API keys or secrets. Keep it concise with examples, and update when conventions change.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.1 Memory Files (CLAUDE.md)"
       anchor: "#level-2-project-projectclaudemd"
 
@@ -135,7 +135,7 @@ questions:
     explanation: |
       The pattern 'Bash(git *)' matches any git command. Permission patterns use wildcards: 'Bash(git *)' matches any git command, 'Bash(pnpm *)' matches any pnpm command, 'mcp__serena__*' matches all Serena MCP tools. You can also use specific patterns like 'Bash(git status:*)' to match only git status.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.3 Settings & Permissions"
       anchor: "#permission-patterns"
 
@@ -152,7 +152,7 @@ questions:
     explanation: |
       Dynamic Memory means temporarily modifying CLAUDE.md for specific tasks then restoring it. Techniques include: git stash (stash original, modify, restore), profile library (keep profiles like security-audit.md, debugging.md in ~/.claude/profiles/), or parallel instances (different CLAUDE.md in different worktrees). Switch profiles with a script: `claude-profile security-audit`.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.3 Settings & Permissions"
       anchor: "#dynamic-memory-profile-switching"
 
@@ -169,7 +169,7 @@ questions:
     explanation: |
       Files in `.claude/rules/` are automatically loaded and combined. You can create multiple files like code-conventions.md, git-workflow.md, and architecture.md - all are loaded automatically without manual imports. This allows modular organization of project conventions that Claude will follow.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.4 Precedence Rules"
       anchor: "#rules-auto-loading"
 
@@ -186,7 +186,7 @@ questions:
     explanation: |
       Files that should be gitignored are: .claude/CLAUDE.md (local personal instructions) and .claude/settings.local.json (personal permissions). Files that should be committed include: agents/, commands/, hooks/, skills/, rules/, and settings.json. This separation allows personal customization while sharing team configurations.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.2 The .claude/ Folder Structure"
       anchor: "#what-goes-where"
 
@@ -203,7 +203,7 @@ questions:
     explanation: |
       The allowedTools configuration in ~/.claude.json provides granular control with specific patterns. For example: 'Read(*)' allows all reads, 'Bash(git status:*)' allows only git status, 'Bash(pnpm *:*)' allows pnpm commands. You can set progressive permission levels from beginner (very restrictive) to advanced. Never use --dangerously-skip-permissions.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.3 Settings & Permissions"
       anchor: "#allowedtools-configuration-alternative"
 
@@ -220,7 +220,7 @@ questions:
     explanation: |
       On macOS/Linux, the global config path is ~/.claude/. On Windows, it's %USERPROFILE%\.claude\ or C:\Users\YourName\.claude\. This directory contains your global CLAUDE.md, settings, and can include a profiles/ subdirectory for dynamic memory switching.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "1.1 Installation"
       anchor: "#platform-specific-paths"
 
@@ -237,7 +237,7 @@ questions:
     explanation: |
       The three progressive permission levels are: Beginner (very restrictive - only Read, Grep, Glob), Intermediate (adds Bash git/pnpm, TodoRead/Write), and Advanced (adds Edit, Write, WebFetch, Task). Start restrictive and expand as you gain confidence. This prevents accidents while learning.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.3 Settings & Permissions"
       anchor: "#progressive-permission-levels"
 
@@ -254,7 +254,7 @@ questions:
     explanation: |
       Never use --dangerously-skip-permissions because it can lead to destructive operations. Horror stories include: `rm -rf node_modules` followed by `rm -rf .` (path error), `git push --force` to main unintentionally, `DROP TABLE users` in poorly generated migrations, and deletion of .env files with credentials. Always prefer granular allowedTools instead.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.3 Settings & Permissions"
       anchor: "#-warning-never-use---dangerously-skip-permissions"
 
@@ -271,7 +271,7 @@ questions:
     explanation: |
       Global CLAUDE.md (~/.claude/CLAUDE.md) should contain personal preferences that apply to all your projects: communication style (be concise, use code examples), preferred tools (TypeScript over JavaScript, pnpm over npm), and safety rules (always run tests, never force push). Project-specific settings go in project CLAUDE.md.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.1 Memory Files (CLAUDE.md)"
       anchor: "#level-1-global-claudeclaudemd"
 
@@ -288,6 +288,6 @@ questions:
     explanation: |
       settings.json stores hook configurations and is committed to the repo for team sharing. It defines hooks for PreToolUse, PostToolUse, UserPromptSubmit events - specifying matchers and hook scripts. Personal permission overrides go in settings.local.json (gitignored). This separation allows team automation while respecting personal preferences.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "3.3 Settings & Permissions"
       anchor: "#settingsjson-team-configuration"
diff --git a/quiz/questions/04-agents.yaml b/quiz/questions/04-agents.yaml
index b877f7e..97cbe43 100644
--- a/quiz/questions/04-agents.yaml
+++ b/quiz/questions/04-agents.yaml
@@ -1,6 +1,6 @@
 category: "Agents"
 category_id: 4
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "04-001"
@@ -16,7 +16,7 @@ questions:
     explanation: |
       Agents are specialized sub-processes (AI personas) that Claude can delegate tasks to. They encapsulate domain expertise, like a security reviewer knowing OWASP Top 10 or a backend architect understanding API design. Think of them as "expert consultants" - instead of explaining everything in your prompt, you invoke an agent that already has that expertise.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.1 What Are Agents"
       anchor: "#41-what-are-agents"
 
@@ -33,7 +33,7 @@ questions:
     explanation: |
       Custom agent files should be stored in `.claude/agents/` within your project directory. They are markdown files with YAML frontmatter. For example: `.claude/agents/backend-architect.md`, `.claude/agents/code-reviewer.md`. These can be committed to version control to share with your team.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.2 Creating Custom Agents"
       anchor: "#42-creating-custom-agents"
 
@@ -50,7 +50,7 @@ questions:
     explanation: |
       Only `name` and `description` are required in agent frontmatter. Optional fields include: model (sonnet default, opus, or haiku), tools (comma-separated list), skills (to inherit), and disallowedTools. The description is crucial - it determines when Claude auto-activates the agent, so make it clear and specific.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.2 Creating Custom Agents"
       anchor: "#frontmatter-fields"
 
@@ -67,7 +67,7 @@ questions:
     explanation: |
       Agents encapsulate expertise. Without agents, you'd write: "Review this code for security issues, focusing on OWASP Top 10, checking for SQL injection, XSS, CSRF..." With agents: "Use the security-reviewer agent to audit this code." The agent already has that expertise, making your prompts shorter and more consistent.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.1 What Are Agents"
       anchor: "#agent-vs-direct-prompt"
 
@@ -84,7 +84,7 @@ questions:
     explanation: |
       Use opus for complex reasoning and architecture tasks. Model selection guidelines: haiku (fast, low cost) for quick tasks and simple changes; sonnet (balanced, default) for most tasks; opus (slow, high cost) for complex reasoning, architecture decisions, and critical security reviews. Match the model to the task's complexity.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.2 Creating Custom Agents"
       anchor: "#model-selection"
 
@@ -101,7 +101,7 @@ questions:
     explanation: |
       Tool SEO optimizes the agent's description field to improve auto-activation. Techniques include: using "use PROACTIVELY" to encourage automatic activation, listing explicit trigger keywords, describing specific contexts, and adding short nicknames. A good description: "Security code reviewer - use PROACTIVELY when: reviewing auth code, analyzing API endpoints... Triggers: security, auth, vulnerability, OWASP"
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.6 Advanced Agent Patterns"
       anchor: "#tool-seo---optimizing-agent-descriptions"
 
@@ -118,7 +118,7 @@ questions:
     explanation: |
       Always prefer specialization over generalization. Good: separate agents for backend-architect (API, database, performance), security-reviewer (OWASP, auth, encryption), test-engineer (test strategy, coverage, TDD). Bad: one full-stack-expert that "does everything (poorly)". Specialized agents have focused context and domain-specific expertise.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.4 Best Practices"
       anchor: "#specialization-over-generalization"
 
@@ -135,7 +135,7 @@ questions:
     explanation: |
       Agents inherit skills using the `skills` field in frontmatter. For example: `skills: [security-guardian]`. This composes expertise without duplication - instead of copying OWASP knowledge into every security-related agent, they all inherit from the security-guardian skill. This follows DRY principles for knowledge organization.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.4 Best Practices"
       anchor: "#skill-composition"
 
@@ -152,7 +152,7 @@ questions:
     explanation: |
       The 7-Parallel-Task Method launches 7 specialized sub-agents in parallel: 1) Components, 2) Styles, 3) Tests, 4) Types, 5) Hooks, 6) Integration, 7) Config. All run in parallel, then results are consolidated. This dramatically speeds up feature implementation by parallelizing independent work streams.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.6 Advanced Agent Patterns"
       anchor: "#the-7-parallel-task-method"
 
@@ -169,7 +169,7 @@ questions:
     explanation: |
       Use lightweight agents (<3K tokens, <1s init time) for frequent tasks and workers. Golden Rule: "A lightweight agent used 100x > A heavy agent used 10x." Agent weight categories: Lightweight (<3K tokens) for frequent tasks, Medium (10-15K) for analysis/reviews, Heavy (25K+) for architecture/full audits. Match weight to task frequency.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.6 Advanced Agent Patterns"
       anchor: "#agent-weight-classification"
 
@@ -186,7 +186,7 @@ questions:
     explanation: |
       The recommended pattern is: Sonnet as orchestrator (coordinates), Haiku workers (parallel execution), Sonnet validator (final check). This is 2-2.5x cheaper than using Opus everywhere with equivalent quality for 90% of tasks. For example, refactoring 100 files: Sonnet analyzes and plans, Haiku does parallel edits, Sonnet validates - saving 80-90% cost.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.6 Advanced Agent Patterns"
       anchor: "#multi-agent-orchestration-pattern"
 
@@ -203,7 +203,7 @@ questions:
     explanation: |
       An agent's output format should specify structured deliverables. For example, a code reviewer agent outputs: Summary, Critical Issues (Must Fix) with file:line references, Warnings (Should Fix), Suggestions (Nice to Have), and Positive Notes. Clear output format ensures consistent, actionable results across all invocations.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.5 Agent Examples"
       anchor: "#example-1-code-reviewer-agent"
 
@@ -220,7 +220,7 @@ questions:
     explanation: |
       The disallowedTools field blocks specific tools from being used by the agent. For example, a code reviewer agent might have `disallowedTools: [WebSearch]` to ensure it focuses on the actual code rather than searching the web. This provides security boundaries and focuses the agent on its core purpose.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.2 Creating Custom Agents"
       anchor: "#agent-file-structure"
 
@@ -237,7 +237,7 @@ questions:
     explanation: |
       Split Role Sub-Agents provide multi-perspective analysis in parallel. Process: 1) Activate Plan Mode + ultrathink, 2) Ask "What expert roles would analyze this?", 3) Select roles (e.g., Security Expert, Senior Dev, Code Reviewer), 4) Run parallel analysis from each perspective, 5) Consolidate reports into recommendations. Great for comprehensive code and UX reviews.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.6 Advanced Agent Patterns"
       anchor: "#split-role-sub-agents"
 
@@ -254,7 +254,7 @@ questions:
     explanation: |
       Avoid parallel execution for destructive (write) operations that are dependent on each other. The decision matrix: Independent + Non-destructive = Parallel (max efficiency); Independent + Destructive = Sequential with Plan Mode first; Dependent operations = Sequential (order matters). Parallel writes risk conflicts if files share imports/exports.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.6 Advanced Agent Patterns"
       anchor: "#parallelization-decision-matrix"
 
@@ -271,7 +271,7 @@ questions:
     explanation: |
       A systematic Debugger agent follows: 1) Reproduce - confirm the issue exists, 2) Isolate - narrow down to smallest reproducible case, 3) Analyze - read code, check logs, trace execution, 4) Hypothesize - form theories about cause, 5) Test - verify hypothesis with minimal changes, 6) Fix - implement solution, 7) Verify - confirm fix works without breaking other things. Never guess - always verify.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.5 Agent Examples"
       anchor: "#example-2-debugger-agent"
 
@@ -288,6 +288,6 @@ questions:
     explanation: |
       "Backend stuff" is a bad description - it's too vague to help Claude know when to activate the agent. Good descriptions are specific: "Use when designing APIs, reviewing database schemas, or optimizing backend performance" or "Security code reviewer - use PROACTIVELY when reviewing auth code." Clear activation triggers improve agent utilization.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.4 Best Practices"
       anchor: "#explicit-activation-triggers"
diff --git a/quiz/questions/05-skills.yaml b/quiz/questions/05-skills.yaml
index a11cca7..c7a0c4c 100644
--- a/quiz/questions/05-skills.yaml
+++ b/quiz/questions/05-skills.yaml
@@ -1,6 +1,6 @@
 category: "Skills"
 category_id: 5
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "05-001"
@@ -16,7 +16,7 @@ questions:
     explanation: |
       Skills are knowledge packages that agents can inherit. While agents are specialized roles (task-focused), skills are reusable knowledge modules (domain-focused). Multiple agents can inherit the same skill, avoiding duplication. For example, both a code-reviewer and security-auditor agent can inherit the security-guardian skill.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.1 Understanding Skills"
       anchor: "#51-understanding-skills"
 
@@ -33,7 +33,7 @@ questions:
     explanation: |
       Skills live in `.claude/skills/{skill-name}/` directories within your project. Each skill has its own folder containing at minimum a SKILL.md file, with optional reference.md, checklists/, examples/, and scripts/ subdirectories. This organization keeps knowledge modular and reusable.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.2 Creating Skills"
       anchor: "#52-creating-skills"
 
@@ -50,7 +50,7 @@ questions:
     explanation: |
       SKILL.md is the required main file in every skill folder. Optional files include: reference.md (detailed documentation), checklists/ (verification lists), examples/ (code patterns with good/bad examples), and scripts/ (helper scripts). SKILL.md contains the frontmatter and core instructions for the skill.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.2 Creating Skills"
       anchor: "#skill-folder-structure"
 
@@ -67,7 +67,7 @@ questions:
     explanation: |
       The three concepts have distinct purposes: Skills are knowledge modules inherited by agents (like OWASP security knowledge), Agents are specialized roles that Claude delegates tasks to (like a security reviewer), and Commands are process workflows invoked with slash commands (like /tech:commit). They can be combined: agents inherit skills and execute commands.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.1 Understanding Skills"
       anchor: "#skills-vs-agents-vs-commands"
 
@@ -84,7 +84,7 @@ questions:
     explanation: |
       The `context` field controls execution context: 'fork' means isolated context (the skill runs independently), 'inherit' means shared context (the skill shares context with the calling agent). Use fork for skills that need clean state, inherit for skills that need access to conversation history and loaded files.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.2 Creating Skills"
       anchor: "#skillmd-frontmatter"
 
@@ -101,7 +101,7 @@ questions:
     explanation: |
       Skills follow DRY (Don't Repeat Yourself) principles. Without skills, you'd duplicate security knowledge in Agent A, B, and C. With skills, the security-guardian skill is the single source - all agents inherit it, and updates propagate everywhere. This ensures consistency and simplifies maintenance.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.1 Understanding Skills"
       anchor: "#why-skills"
 
@@ -118,7 +118,7 @@ questions:
     explanation: |
       Good skills are: reusable across multiple agents, domain-focused (not too broad), contain reference material and checklists, and include verification steps. Bad skills are: specific to only one agent, too broad in scope, just instructions without reference material, and missing verification checklists.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.1 Understanding Skills"
       anchor: "#what-makes-a-good-skill"
 
@@ -135,7 +135,7 @@ questions:
     explanation: |
       The TDD skill follows: 1) RED - write a failing test for desired behavior BEFORE code, 2) GREEN - write MINIMUM code to make the test pass, 3) REFACTOR - improve implementation while keeping tests green, then repeat. This cycle ensures tests actually verify behavior by requiring failure first, then incremental improvement.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.4 Skill Examples"
       anchor: "#example-2-tdd-skill"
 
@@ -152,7 +152,7 @@ questions:
     explanation: |
       A Security Guardian skill should include detailed checklists for each OWASP Top 10 category: A01 Broken Access Control (check authorization, IDOR, privilege escalation), A02 Cryptographic Failures (hardcoded secrets, TLS, password hashing), A03 Injection (SQL, NoSQL, XSS), etc. Each category should have specific verification items with checkboxes.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.4 Skill Examples"
       anchor: "#example-1-security-guardian-skill"
 
@@ -169,7 +169,7 @@ questions:
     explanation: |
       The `agent` field indicates whether the skill is 'specialist' (domain-focused, deep expertise in one area) or 'general' (broad, applicable across domains). Specialist skills like security-guardian provide deep domain knowledge, while general skills might provide widely-applicable patterns or utilities.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.2 Creating Skills"
       anchor: "#skillmd-frontmatter"
 
@@ -186,7 +186,7 @@ questions:
     explanation: |
       The `allowed-tools` field specifies which tools the skill can use when activated. For example, a security-guardian skill might have `allowed-tools: Read, Grep, Bash` - allowing it to read files, search for patterns, and run security scanning commands, but not modify files. This provides security boundaries for each skill.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.2 Creating Skills"
       anchor: "#skillmd-frontmatter"
 
@@ -203,7 +203,7 @@ questions:
     explanation: |
       A skill directory can contain: SKILL.md (required), reference.md (detailed documentation), checklists/ (verification lists like security.md, performance.md), examples/ (code patterns like good-example.ts, bad-example.ts), and scripts/ (helper scripts like audit.sh). This rich structure supports comprehensive domain knowledge.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.2 Creating Skills"
       anchor: "#skill-folder-structure"
 
@@ -220,7 +220,7 @@ questions:
     explanation: |
       The Security Guardian skill shows argon2 or bcrypt as secure password hashing. BAD examples explicitly listed: md5(password) and sha1(password) - these are cryptographically broken for password storage. Good pattern: `const hashedPassword = await hash(password)` using argon2 library. Always verify password with `await verify(hashedPassword, inputPassword)`.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.4 Skill Examples"
       anchor: "#authentication-patterns"
 
@@ -237,7 +237,7 @@ questions:
     explanation: |
       AAA stands for Arrange, Act, Assert: 1) Arrange - set up test data and preconditions, 2) Act - execute the code being tested, 3) Assert - verify the result matches expectations. Example: Arrange items array, Act by calling calculateTotal(items), Assert that total equals expected value. This structure makes tests readable and maintainable.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.4 Skill Examples"
       anchor: "#test-structure-aaa-pattern"
 
@@ -254,7 +254,7 @@ questions:
     explanation: |
       The zebbern/claude-code-guide repository contains 29 cybersecurity-focused skills covering: penetration testing (SQL injection, XSS, IDOR), security tools (Metasploit, Burp Suite, SQLMap), infrastructure security (AWS, Cloud, Network), and methodologies (ethical hacking, pentest checklists). Important: these should be tested thoroughly and used only with proper authorization.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.5 Community Skill Repositories"
       anchor: "#cybersecurity-skills-repository"
 
@@ -271,7 +271,7 @@ questions:
     explanation: |
       Useful skills include: methodology steps (clear process to follow), checklists (verification items with checkboxes), good/bad code examples (showing correct patterns and anti-patterns), and reference material. This combination provides both theoretical knowledge and practical guidance that agents can apply directly to tasks.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.3 Skill Template"
       anchor: "#53-skill-template"
 
@@ -288,7 +288,7 @@ questions:
     explanation: |
       Reference skills in an agent's frontmatter using the `skills` array: `skills: [security-guardian, tdd]`. This makes the agent inherit all knowledge from those skills. You can reference multiple skills, and the agent combines their expertise. The skill name matches the folder name in `.claude/skills/`.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "4.4 Best Practices"
       anchor: "#skill-composition"
 
@@ -305,6 +305,6 @@ questions:
     explanation: |
       Community cybersecurity skills come with important disclaimers: test thoroughly before using in production assessments, ensure you have proper authorization before penetration testing, review and validate against your organization's security policies, use only in legal contexts with written permission from system owners, and contribute back if you find issues. Verification is essential for any security tooling.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "5.5 Community Skill Repositories"
       anchor: "#important-disclaimer"
diff --git a/quiz/questions/06-commands.yaml b/quiz/questions/06-commands.yaml
index f01188c..587157f 100644
--- a/quiz/questions/06-commands.yaml
+++ b/quiz/questions/06-commands.yaml
@@ -1,6 +1,6 @@
 category: "Commands"
 category_id: 6
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "06-001"
@@ -23,7 +23,7 @@ questions:
       - `.claude/commands/tech/` for development workflows
       - `.claude/commands/product/` for product workflows
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.2 Creating Custom Commands"
       anchor: "#62-creating-custom-commands"
 
@@ -47,7 +47,7 @@ questions:
       - `.claude/commands/tech/pr.md` -> `/tech:pr`
       - `.claude/commands/product/scope.md` -> `/product:scope`
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.2 Creating Custom Commands"
       anchor: "#command-naming"
 
@@ -70,7 +70,7 @@ questions:
       This enables dynamic commands that can adapt based on user input.
       Commands should document how they handle arguments and what happens if none are provided.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.2 Creating Custom Commands"
       anchor: "#variable-interpolation"
 
@@ -96,7 +96,7 @@ questions:
 
       Custom commands from `.claude/commands/` are also listed here.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.1 Slash Commands"
       anchor: "#61-slash-commands"
 
@@ -122,7 +122,7 @@ questions:
 
       This comprehensive structure ensures consistent, reliable command execution.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.3 Command Template"
       anchor: "#63-command-template"
 
@@ -147,7 +147,7 @@ questions:
 
       Use `/execute` to exit Plan Mode when ready to make changes.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.1 Slash Commands"
       anchor: "#built-in-commands"
 
@@ -174,7 +174,7 @@ questions:
 
       This provides consistent, parseable commit history useful for changelogs and releases.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.4 Command Examples"
       anchor: "#example-1-commit-command"
 
@@ -200,7 +200,7 @@ questions:
 
       The command then reframes the problem as: "How might we [action] for [user] so that [outcome]?"
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.4 Command Examples"
       anchor: "#example-3-problem-framer-command"
 
@@ -225,7 +225,7 @@ questions:
       For committed changes, use `git revert` instead.
       The keyboard shortcut `Esc×2` (double-tap Escape) also triggers rewind.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.1 Slash Commands"
       anchor: "#built-in-commands"
 
@@ -250,7 +250,7 @@ questions:
       - Suggests corrective actions
       - Prevents accidental mistakes
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.4 Command Examples"
       anchor: "#example-2-pr-command"
 
@@ -276,7 +276,7 @@ questions:
 
       This thorough process ensures quality PRs with proper context.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "6.4 Command Examples"
       anchor: "#example-2-pr-command"
 
@@ -301,6 +301,6 @@ questions:
 
       This allows you to easily bring specific files into context for Claude to analyze.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.1 Commands Table"
       anchor: "#quick-actions"
diff --git a/quiz/questions/07-hooks.yaml b/quiz/questions/07-hooks.yaml
index 8224b78..82f4dc4 100644
--- a/quiz/questions/07-hooks.yaml
+++ b/quiz/questions/07-hooks.yaml
@@ -1,6 +1,6 @@
 category: "Hooks"
 category_id: 7
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "07-001"
@@ -23,7 +23,7 @@ questions:
       This is critical for security hooks that need to prevent dangerous commands.
       For example, a hook that detects `rm -rf /` should `exit 2` to block execution.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.2 Creating Hooks"
       anchor: "#exit-codes"
 
@@ -48,7 +48,7 @@ questions:
       - **SessionStart/SessionEnd**: Session lifecycle events
       - **Stop**: When user interrupts
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.1 The Event System"
       anchor: "#event-types"
 
@@ -79,7 +79,7 @@ questions:
 
       Hooks typically parse this with: `INPUT=$(cat)` followed by `jq` for JSON extraction.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.2 Creating Hooks"
       anchor: "#hook-input-stdin-json"
 
@@ -107,7 +107,7 @@ questions:
       This hook would trigger for Bash, Edit, or Write tools.
       You can match specific tools or use `.*` to match all tools.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.2 Creating Hooks"
       anchor: "#configuration-fields"
 
@@ -132,7 +132,7 @@ questions:
 
       The context enricher example adds git branch, last commit, and staged/unstaged info.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.3 Hook Templates"
       anchor: "#template-3-userpromptsubmit-context-enricher"
 
@@ -157,7 +157,7 @@ questions:
       Always end your hooks with `exit 0` if you want to allow the operation,
       or `exit 2` to block it.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.2 Creating Hooks"
       anchor: "#exit-codes"
 
@@ -182,7 +182,7 @@ questions:
 
       Safe commands like `git status`, `npm test`, `ls` should be allowed.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.4 Security Hooks"
       anchor: "#recommended-security-rules"
 
@@ -213,7 +213,7 @@ questions:
 
       This allows hooks to provide context that Claude can use in its responses.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.2 Creating Hooks"
       anchor: "#hook-output"
 
@@ -242,7 +242,7 @@ questions:
 
       Rule: "If you can write a regex for it, use a bash script."
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.1 The Event System"
       anchor: "#shell-scripts-vs-ai-agents-when-to-use-what"
 
@@ -267,7 +267,7 @@ questions:
 
       The Auto-Formatter template uses PostToolUse to run Prettier after Edit/Write operations.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.1 The Event System"
       anchor: "#event-types"
 
@@ -296,7 +296,7 @@ questions:
 
       This ensures your hook correctly blocks dangerous commands before deployment.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.4 Security Hooks"
       anchor: "#testing-security-hooks"
 
@@ -323,7 +323,7 @@ questions:
       This bypasses the default execution policy that might block script execution.
       Batch files (.cmd) can also be used as an alternative for simpler hooks.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.3 Hook Templates"
       anchor: "#windows-hook-templates"
 
@@ -349,7 +349,7 @@ questions:
       JSONL is ideal for log files as each line is a valid JSON object,
       making it easy to append and parse.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.5 Hook Examples"
       anchor: "#example-1-activity-logger"
 
@@ -377,6 +377,6 @@ questions:
       This prevents hooks from blocking Claude Code indefinitely.
       For longer operations like formatting, you might increase this to 10000ms.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "7.2 Creating Hooks"
       anchor: "#hook-registration-settingsjson"
diff --git a/quiz/questions/08-mcp-servers.yaml b/quiz/questions/08-mcp-servers.yaml
index 6d9415a..12efd7a 100644
--- a/quiz/questions/08-mcp-servers.yaml
+++ b/quiz/questions/08-mcp-servers.yaml
@@ -1,6 +1,6 @@
 category: "MCP Servers"
 category_id: 8
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "08-001"
@@ -23,7 +23,7 @@ questions:
       - Database queries (Postgres)
       - Browser automation (Playwright)
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.1 What is MCP"
       anchor: "#81-what-is-mcp"
 
@@ -48,7 +48,7 @@ questions:
 
       Use Serena for deep code understanding and symbol-level analysis.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.2 Available Servers"
       anchor: "#serena-semantic-code-analysis"
 
@@ -73,7 +73,7 @@ questions:
       For example, "How does React useEffect work?" should use Context7
       to get the official documentation rather than generic knowledge.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.4 Server Selection Guide"
       anchor: "#server-comparison"
 
@@ -98,7 +98,7 @@ questions:
       Memory is stored in `.serena/memories/` and survives between Claude Code sessions.
       This is crucial for maintaining context on long-running projects.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.2 Available Servers"
       anchor: "#session-memory-workflow"
 
@@ -121,7 +121,7 @@ questions:
 
       The configuration specifies which servers to run and their settings.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.3 Configuration"
       anchor: "#mcpjson-location"
 
@@ -146,7 +146,7 @@ questions:
       The `sequentialthinking` tool provides step-by-step reasoning that is
       ideal for problems requiring systematic investigation.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.4 Server Selection Guide"
       anchor: "#decision-tree"
 
@@ -170,7 +170,7 @@ questions:
 
       This combination leverages each server's strengths for comprehensive development.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.4 Server Selection Guide"
       anchor: "#combining-servers"
 
@@ -198,7 +198,7 @@ questions:
       }
       ```
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.3 Configuration"
       anchor: "#variable-substitution"
 
@@ -222,7 +222,7 @@ questions:
 
       For large codebases (>10k lines), Serena's indexation dramatically improves performance.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.2 Available Servers"
       anchor: "#serena-semantic-code-analysis"
 
@@ -248,7 +248,7 @@ questions:
       - Plugins: `claude plugin install`
       - MCP: Add to `settings.json` MCP config
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.5 Plugin System"
       anchor: "#plugin-vs-mcp-server"
 
@@ -276,7 +276,7 @@ questions:
       - Visual validation
       - Browser debugging
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.2 Available Servers"
       anchor: "#playwright-browser-automation"
 
@@ -304,7 +304,7 @@ questions:
 
       This is quicker than manually editing mcp.json.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.3 Configuration"
       anchor: "#cli-based-mcp-configuration"
 
@@ -334,7 +334,7 @@ questions:
 
       Use mgrep for onboarding to unfamiliar codebases or exploring by intent.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.2 Available Servers"
       anchor: "#mgrep-semantic-search-alternative"
 
@@ -359,6 +359,6 @@ questions:
       - `claude plugin uninstall <name>` - Remove plugin
       - `claude plugin validate <path>` - Validate plugin manifest
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "8.5 Plugin System"
       anchor: "#plugin-commands"
diff --git a/quiz/questions/09-advanced-patterns.yaml b/quiz/questions/09-advanced-patterns.yaml
index 2706584..2ac1de7 100644
--- a/quiz/questions/09-advanced-patterns.yaml
+++ b/quiz/questions/09-advanced-patterns.yaml
@@ -1,6 +1,6 @@
 category: "Advanced Patterns"
 category_id: 9
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "09-001"
@@ -23,7 +23,7 @@ questions:
       Combined, these provide maximum understanding before taking action.
       Use for architecture decisions, complex debugging, and legacy modernization.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.1 The Trinity"
       anchor: "#91-the-trinity"
 
@@ -48,7 +48,7 @@ questions:
 
       Higher levels increase latency and cost - use the smallest level that works.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.1 The Trinity"
       anchor: "#ultrathink-levels"
 
@@ -75,7 +75,7 @@ questions:
 
       Essential for CI/CD integration, automated pipelines, and scripted workflows.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.3 CI/CD Integration"
       anchor: "#headless-mode"
 
@@ -100,7 +100,7 @@ questions:
 
       This enables powerful shell integration for automated code analysis.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.3 CI/CD Integration"
       anchor: "#unix-piping-workflows"
 
@@ -132,7 +132,7 @@ questions:
 
       Typically 3 rounds are recommended for quality work.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.2 Composition Patterns"
       anchor: "#the-rev-the-engine-pattern"
 
@@ -160,7 +160,7 @@ questions:
       git log --oneline -10 | claude -p 'Categorize commits' --output-format json
       ```
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.3 CI/CD Integration"
       anchor: "#output-format-control"
 
@@ -188,7 +188,7 @@ questions:
       - Focus on learning
       - Signal clearly: "This is vibe code, not for production"
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.8 Vibe Coding & Skeleton Projects"
       anchor: "#vibe-coding"
 
@@ -217,7 +217,7 @@ questions:
 
       This prevents wasted CI cycles and review time.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.3 CI/CD Integration"
       anchor: "#verify-gate-pattern"
 
@@ -242,7 +242,7 @@ questions:
 
       Well-crafted todos guide Claude's execution with precision.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.6 Todo as Instruction Mirrors"
       anchor: "#the-mirror-principle"
 
@@ -267,7 +267,7 @@ questions:
 
       The meta-skill: instead of fixing code, fix the system that produces the code.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.10 Continuous Improvement Mindset"
       anchor: "#the-key-question"
 
@@ -292,7 +292,7 @@ questions:
 
       Progression: Skeleton (Day 1) -> MVP (Week 1) -> Full (Month 1)
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.8 Vibe Coding & Skeleton Projects"
       anchor: "#skeleton-projects"
 
@@ -321,7 +321,7 @@ questions:
       # Implement the plan...
       ```
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.13 Cost Optimization Strategies"
       anchor: "#model-selection-matrix"
 
@@ -350,7 +350,7 @@ questions:
 
       The flag bypasses all permission prompts, creating security risks.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.11 Common Pitfalls & Best Practices"
       anchor: "#security-pitfalls"
 
@@ -380,7 +380,7 @@ questions:
       VERIFY: Empty email shows error, invalid format shows error
       ```
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.11 Common Pitfalls & Best Practices"
       anchor: "#effective-prompt-format"
 
@@ -405,7 +405,7 @@ questions:
       Start with simple, low-risk tasks and build up complexity gradually.
       This avoids overwhelm and builds solid fundamentals.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.11 Common Pitfalls & Best Practices"
       anchor: "#learning--adoption-pitfalls"
 
@@ -433,6 +433,6 @@ questions:
       git worktree add ../myproject-feature-a feature-a
       ```
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.12 Git Best Practices & Workflows"
       anchor: "#git-worktrees-for-parallel-development"
diff --git a/quiz/questions/10-reference.yaml b/quiz/questions/10-reference.yaml
index 6a67f46..01ae29f 100644
--- a/quiz/questions/10-reference.yaml
+++ b/quiz/questions/10-reference.yaml
@@ -1,6 +1,6 @@
 category: "Reference"
 category_id: 10
-source_file: "english-ultimate-claude-code-guide.md"
+source_file: "guide/ultimate-guide.md"
 
 questions:
   - id: "10-001"
@@ -22,7 +22,7 @@ questions:
 
       Plan Mode allows safe, read-only exploration before making changes.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.2 Keyboard Shortcuts"
       anchor: "#session-control"
 
@@ -44,7 +44,7 @@ questions:
 
       Use when Claude made a mistake and you want to try a different approach.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.2 Keyboard Shortcuts"
       anchor: "#session-control"
 
@@ -69,7 +69,7 @@ questions:
       This frees up context space while preserving important information.
       Check context usage with `/status`.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.1 Commands Table"
       anchor: "#built-in-commands"
 
@@ -95,7 +95,7 @@ questions:
 
       Proactive compaction at 70% prevents context degradation and maintains performance.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.4 Troubleshooting"
       anchor: "#context-recovery"
 
@@ -119,7 +119,7 @@ questions:
       - `Ctrl+L`: Clear screen (keeps context)
       - `Esc`: Dismiss current suggestion
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.2 Keyboard Shortcuts"
       anchor: "#session-control"
 
@@ -144,7 +144,7 @@ questions:
 
       Wildcards (*) enable flexible permission matching.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.3 Configuration Reference"
       anchor: "#permission-patterns"
 
@@ -170,7 +170,7 @@ questions:
       The root `CLAUDE.md` is committed and shared with the team.
       The `.claude/CLAUDE.md` is personal and should be in `.gitignore`.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.3 Configuration Reference"
       anchor: "#claudemd-locations"
 
@@ -195,7 +195,7 @@ questions:
 
       Use when MCP servers aren't connecting or tools aren't appearing.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.4 Troubleshooting"
       anchor: "#mcp-debugging-techniques"
 
@@ -224,7 +224,7 @@ questions:
       - Special characters (@, #, etc.)
       - More than 64 characters
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.4 Troubleshooting"
       anchor: "#error-1-tool-name-validation-failed"
 
@@ -252,7 +252,7 @@ questions:
 
       Use `/stats` for usage statistics with activity graphs.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.1 Commands Table"
       anchor: "#built-in-commands"
 
@@ -276,7 +276,7 @@ questions:
       This prevents runaway costs in automated pipelines.
       The operation stops if the budget is exceeded.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.3 Configuration Reference"
       anchor: "#cli-flags-reference"
 
@@ -301,7 +301,7 @@ questions:
 
       Example: `!git status` runs git status without Claude interpreting it.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.1 Commands Table"
       anchor: "#quick-actions"
 
@@ -327,7 +327,7 @@ questions:
 
       Combine with `-p` for scripting: `claude -r abc123 -p "check status"`
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.3 Configuration Reference"
       anchor: "#cli-flags-reference"
 
@@ -359,7 +359,7 @@ questions:
 
       This keeps team workflows shared while personal settings stay private.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "9.11 Common Pitfalls & Best Practices"
       anchor: "#recommended-gitignore"
 
@@ -383,7 +383,7 @@ questions:
 
       This ensures you start with fresh code and full context awareness.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.6 Daily Workflow & Checklists"
       anchor: "#daily-workflow-pattern"
 
@@ -408,7 +408,7 @@ questions:
       This is more efficient than loading the entire monorepo.
       Multiple directories can be specified for multi-package projects.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.3 Configuration Reference"
       anchor: "#cli-flags-reference"
 
@@ -434,7 +434,7 @@ questions:
 
       The longer response time reflects deeper analysis.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.4 Troubleshooting"
       anchor: "#sequential-thinking-mcp-issues"
 
@@ -460,6 +460,6 @@ questions:
 
       The external editor allows comfortable editing of complex prompts.
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "10.2 Keyboard Shortcuts"
       anchor: "#input--navigation"
diff --git a/quiz/src/dynamic.js b/quiz/src/dynamic.js
index a5fc594..8241b97 100644
--- a/quiz/src/dynamic.js
+++ b/quiz/src/dynamic.js
@@ -55,7 +55,7 @@ correct: "a"
 explanation: |
   Explanation of why this is correct and what the user should learn.
 doc_reference:
-  file: "english-ultimate-claude-code-guide.md"
+  file: "guide/ultimate-guide.md"
   section: "${categoryName}"
   anchor: "#${categoryId}-${categoryName.toLowerCase().replace(/[^a-z0-9]+/g, '-')}"
 \`\`\`
@@ -91,7 +91,7 @@ Requirements:
     // Add category info
     question.category = categoryName;
     question.category_id = categoryId;
-    question.source_file = 'english-ultimate-claude-code-guide.md';
+    question.source_file = 'guide/ultimate-guide.md';
     question.generated = true;
 
     return question;
diff --git a/quiz/src/questions.js b/quiz/src/questions.js
index b2bcbe5..9787b45 100644
--- a/quiz/src/questions.js
+++ b/quiz/src/questions.js
@@ -27,7 +27,7 @@ export async function loadQuestions(questionsDir) {
             ...q,
             category: parsed.category || 'Unknown',
             category_id: parsed.category_id || 0,
-            source_file: parsed.source_file || 'english-ultimate-claude-code-guide.md'
+            source_file: parsed.source_file || 'guide/ultimate-guide.md'
           }));
           allQuestions.push(...questionsWithCategory);
         }
diff --git a/quiz/src/score.js b/quiz/src/score.js
index 5f3c671..c3b427f 100644
--- a/quiz/src/score.js
+++ b/quiz/src/score.js
@@ -69,7 +69,7 @@ export function displayFinalScore(results, topics) {
     console.log(chalk.blue.bold('Recommended Reading:'));
     for (const area of weakAreas.slice(0, 3)) {
       const anchor = getSectionAnchor(area.id);
-      console.log(chalk.blue(`  ${area.id}. english-ultimate-claude-code-guide.md${anchor}`));
+      console.log(chalk.blue(`  ${area.id}. guide/ultimate-guide.md${anchor}`));
     }
   }
 
diff --git a/quiz/templates/question-template.yaml b/quiz/templates/question-template.yaml
index 1b659df..da1d40e 100644
--- a/quiz/templates/question-template.yaml
+++ b/quiz/templates/question-template.yaml
@@ -47,7 +47,7 @@ questions:
       - 70-90%: Orange (/compact now)
       - 90%+: Red (/clear required)
     doc_reference:
-      file: "english-ultimate-claude-code-guide.md"
+      file: "guide/ultimate-guide.md"
       section: "2.2 Context Management"
       anchor: "#22-context-management"
 
diff --git a/tools/README.md b/tools/README.md
new file mode 100644
index 0000000..f0e307e
--- /dev/null
+++ b/tools/README.md
@@ -0,0 +1,23 @@
+# Interactive Tools
+
+Prompts and utilities for Claude Code setup and optimization.
+
+## Contents
+
+| File | Description | Usage |
+|------|-------------|-------|
+| [audit-prompt.md](./audit-prompt.md) | Comprehensive setup audit with personalized recommendations | `cat audit-prompt.md \| claude` |
+| [onboarding-prompt.md](./onboarding-prompt.md) | Personalized guided tour based on your profile | `cat onboarding-prompt.md \| claude` |
+| [mobile-access.md](./mobile-access.md) | Setup guide for mobile access via ttyd + Tailscale | Step-by-step |
+
+## Quick Audit
+
+For a fast automated scan, use the script instead:
+
+```bash
+curl -sL https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/examples/scripts/audit-scan.sh | bash
+```
+
+---
+
+*Back to [main README](../README.md)*
diff --git a/claude-setup-audit-prompt.md b/tools/audit-prompt.md
similarity index 96%
rename from claude-setup-audit-prompt.md
rename to tools/audit-prompt.md
index 9c86b23..67aca61 100644
--- a/claude-setup-audit-prompt.md
+++ b/tools/audit-prompt.md
@@ -4,7 +4,7 @@
 
 **Author**: [Florian BRUNIAUX](https://github.com/FlorianBruniaux) | Founding Engineer [@Méthode Aristote](https://methode-aristote.fr)
 
-**Reference**: [The Ultimate Claude Code Guide](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/english-ultimate-claude-code-guide.md)
+**Reference**: [The Ultimate Claude Code Guide](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/guide/ultimate-guide.md)
 
 ---
 
@@ -80,7 +80,7 @@ Claude will present findings and ask for validation before making any changes.
 ## Context
 
 Perform a comprehensive audit of my Claude Code configuration against best practices from "The Ultimate Claude Code Guide":
-https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/english-ultimate-claude-code-guide.md
+https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/guide/ultimate-guide.md
 
 ## Instructions
 
@@ -359,7 +359,7 @@ For each ❌ or ⚠️ item, provide:
 ### [Element Name]
 **Current State**: [what exists or doesn't]
 **Why It Matters**: [impact on workflow]
-**Guide Reference**: [Section X.X](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/english-ultimate-claude-code-guide.md#section-anchor)
+**Guide Reference**: [Section X.X](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/guide/ultimate-guide.md#section-anchor)
 ```
 
 **Efficient Guide Reference Lookup**:
@@ -367,19 +367,19 @@ Instead of reading the entire guide, use these line ranges for targeted extracti
 
 ```bash
 # Memory Files best practices
-sed -n '2184,2314p' english-ultimate-claude-code-guide.md
+sed -n '2184,2314p' guide/ultimate-guide.md
 
 # Hooks section
-sed -n '3962,4528p' english-ultimate-claude-code-guide.md
+sed -n '3962,4528p' guide/ultimate-guide.md
 
 # MCP Servers section
-sed -n '4529,5076p' english-ultimate-claude-code-guide.md
+sed -n '4529,5076p' guide/ultimate-guide.md
 
 # Context Management
-sed -n '910,1423p' english-ultimate-claude-code-guide.md
+sed -n '910,1423p' guide/ultimate-guide.md
 
 # Plan Mode
-sed -n '1424,1601p' english-ultimate-claude-code-guide.md
+sed -n '1424,1601p' guide/ultimate-guide.md
 ```
 
 **Suggested Templates**:
@@ -547,8 +547,8 @@ Here's an example of what the audit report looks like:
 
 ## 8. Related Resources
 
-- [The Ultimate Claude Code Guide](./english-ultimate-claude-code-guide.md) - Full reference
-- [Cheatsheet](./cheatsheet-en.md) - Quick daily reference
+- [The Ultimate Claude Code Guide](../guide/ultimate-guide.md) - Full reference
+- [Cheatsheet](../guide/cheatsheet.md) - Quick daily reference
 - [Claude Code Official Docs](https://docs.anthropic.com/en/docs/claude-code) - Anthropic documentation
 
 ---
diff --git a/mobile-access-setup.md b/tools/mobile-access.md
similarity index 100%
rename from mobile-access-setup.md
rename to tools/mobile-access.md
diff --git a/personalized-onboarding-prompt.md b/tools/onboarding-prompt.md
similarity index 94%
rename from personalized-onboarding-prompt.md
rename to tools/onboarding-prompt.md
index 9b2e60d..5d4723a 100644
--- a/personalized-onboarding-prompt.md
+++ b/tools/onboarding-prompt.md
@@ -4,7 +4,7 @@
 
 **Author**: [Florian BRUNIAUX](https://github.com/FlorianBruniaux) | Founding Engineer [@Méthode Aristote](https://methode-aristote.fr)
 
-**Reference**: [The Ultimate Claude Code Guide](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/english-ultimate-claude-code-guide.md)
+**Reference**: [The Ultimate Claude Code Guide](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/guide/ultimate-guide.md)
 
 ---
 
@@ -93,7 +93,7 @@ You are an expert Claude Code instructor. Your mission is to onboard me to Claud
 **After understanding my preferences, read the guide:**
 
 Fetch and read the complete guide from:
-https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/english-ultimate-claude-code-guide.md
+https://raw.githubusercontent.com/FlorianBruniaux/claude-code-ultimate-guide/main/guide/ultimate-guide.md
 
 **Alternative**: If the URL is not accessible, use WebSearch to find the guide content or ask me to provide it.
 
@@ -208,9 +208,9 @@ Tu veux approfondir ou passer au sujet suivant ?
 
 ## 7. Related Resources
 
-- [The Ultimate Claude Code Guide](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/english-ultimate-claude-code-guide.md) - Full reference
-- [Claude Code Setup Audit](./claude-setup-audit-prompt.md) - Analyze your configuration
-- [Quick Reference Cheatsheet](./cheatsheet-en.md) - Commands at a glance
+- [The Ultimate Claude Code Guide](https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/main/guide/ultimate-guide.md) - Full reference
+- [Claude Code Setup Audit](./audit-prompt.md) - Analyze your configuration
+- [Quick Reference Cheatsheet](../guide/cheatsheet.md) - Commands at a glance
 
 ---