diff --git a/CHANGELOG.md b/CHANGELOG.md
new file mode 100644
index 0000000..b269064
--- /dev/null
+++ b/CHANGELOG.md
@@ -0,0 +1,73 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
+
+## [Unreleased]
+
+### Added
+- `examples/` folder with 18 ready-to-use templates
+  - 4 agent templates (code-reviewer, test-writer, security-auditor, refactoring-specialist)
+  - 2 skill templates (tdd-workflow, security-checklist)
+  - 3 command templates (commit, review-pr, generate-tests)
+  - 4 hook templates (bash + PowerShell for security-check, auto-format)
+  - 3 config templates (settings.json, mcp.json, .gitignore-claude)
+  - 2 memory templates (project + personal CLAUDE.md)
+- `CONTRIBUTING.md` with contribution guidelines
+- `CHANGELOG.md` (this file)
+- Learning Paths section in README for different audience profiles
+- **OpusPlan Mode** documentation in Plan Mode section
+  - Uses Opus for planning, Sonnet for implementation
+  - Cost optimization for Pro users with limited Opus tokens
+  - Alternative approach using subagents with specific models
+
+## [1.1.0] - 2025-01-10
+
+### Added
+- Comprehensive Windows compatibility support
+  - PowerShell hook templates
+  - Windows-specific paths throughout documentation
+  - PowerShell profile setup instructions
+  - Batch file alternatives where applicable
+- Windows disclaimer in README (author on macOS, Windows untested)
+- DeepWiki exploration link for interactive repository discovery
+- `llms.txt` file for AI indexation
+
+### Changed
+- Installation instructions now prioritize npm (cross-platform)
+- Cheatsheet updated with dual-platform paths (macOS/Linux + Windows)
+- Audit prompt includes Windows paths
+
+## [1.0.0] - 2025-01-09
+
+### Added
+- Complete Claude Code guide (4700+ lines)
+  - Section 1: Quick Start
+  - Section 2: Core Concepts (Context Management, Plan Mode, Rewind)
+  - Section 3: Memory & Settings (CLAUDE.md, .claude/ folder)
+  - Section 4: Agents (Custom AI personas, Tool SEO)
+  - Section 5: Skills (Reusable knowledge modules)
+  - Section 6: Commands (Custom slash commands)
+  - Section 7: Hooks (Event-driven automation)
+  - Section 8: MCP Servers (Serena, Context7, Sequential, Playwright)
+  - Section 9: Advanced Patterns (Trinity, CI/CD, Vibe Coding)
+  - Section 10: Reference (Commands, Troubleshooting, Checklists)
+  - Appendix: Templates Collection
+- 1-page printable cheatsheet (`cheatsheet-en.md`)
+- Setup audit prompt (`claude-setup-audit-prompt.md`)
+- PDF versions for offline reading
+- NotebookLM audio deep dive
+
+### Documentation
+- README with quick start guide
+- Table of contents with anchor links
+- Quick links by topic
+- Who Is This For section
+
+## [0.1.0] - 2025-01-08
+
+### Added
+- Initial repository structure
+- License (CC BY-SA 4.0)
+- .gitignore for common patterns
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
new file mode 100644
index 0000000..c3dc8fe
--- /dev/null
+++ b/CONTRIBUTING.md
@@ -0,0 +1,152 @@
+# Contributing to The Ultimate Claude Code Guide
+
+Thank you for your interest in improving this guide! Every contribution helps make Claude Code more accessible to developers worldwide.
+
+## How to Contribute
+
+### Reporting Issues
+
+Found an error, outdated information, or have a suggestion?
+
+1. **Check existing issues** - Someone may have reported it already
+2. **Open a new issue** with:
+   - Clear description of the problem or suggestion
+   - Location in the guide (section, line if applicable)
+   - Your platform (macOS/Linux/Windows)
+   - For Windows issues: PowerShell version
+
+### Pull Requests
+
+1. **Fork the repository**
+2. **Create a feature branch**: `git checkout -b fix/typo-in-section-3`
+3. **Make your changes**
+4. **Test on your platform** (especially commands and code snippets)
+5. **Submit a PR** with:
+   - Clear description of changes
+   - Why the change is needed
+   - Any testing performed
+
+## Content Guidelines
+
+### Writing Style
+
+- **Be concise** - Prefer bullet points over long paragraphs
+- **Be practical** - Include examples for every concept
+- **Be inclusive** - Support both macOS/Linux AND Windows users
+- **Be accurate** - Test all code snippets before submitting
+
+### Documentation Structure
+
+```markdown
+## Section Title
+
+Brief introduction (1-2 sentences max).
+
+### Subsection
+
+| Column 1 | Column 2 |
+|----------|----------|
+| Data     | Data     |
+
+**Example:**
+```code
+example here
+```
+```
+
+### Code Snippets
+
+- **Test before submitting** - All code must work
+- **Include both platforms** when commands differ:
+
+```bash
+# macOS/Linux
+~/.claude/settings.json
+
+# Windows
+%USERPROFILE%\.claude\settings.json
+```
+
+### Formatting
+
+- Use tables for comparisons
+- Use code blocks with language hints
+- Use `**bold**` for emphasis
+- Use `backticks` for inline code
+- Reference sections with anchors: `[Section Name](#section-anchor)`
+
+## Platform-Specific Contributions
+
+### Windows Contributions (Especially Welcome!)
+
+The author works on macOS and hasn't tested Windows commands. If you're a Windows user:
+
+- **Test all PowerShell scripts** with PS 5.1+
+- **Test batch file alternatives** when possible
+- **Verify paths** work correctly
+- **Report issues** with Windows-specific instructions
+
+Your contributions are especially valuable!
+
+### Cross-Platform Guidelines
+
+- Use `npm` commands (cross-platform) over `curl` (Unix-only)
+- Specify paths for both platforms
+- Note differences in shell syntax
+- Test on your platform, note what you tested
+
+## Quality Checklist
+
+Before submitting a PR, verify:
+
+- [ ] Markdown renders correctly (preview in GitHub)
+- [ ] All links work
+- [ ] Code snippets are tested
+- [ ] Windows equivalents provided (if applicable)
+- [ ] No typos (run spell check)
+- [ ] Follows existing style
+- [ ] Adds value (not just reformatting)
+
+## Types of Contributions
+
+### Quick Fixes (< 5 minutes)
+- Typo corrections
+- Broken link fixes
+- Minor clarifications
+
+### Enhancements (5-30 minutes)
+- Add missing examples
+- Improve explanations
+- Add Windows equivalents
+- Update outdated information
+
+### New Content (30+ minutes)
+- New sections or guides
+- New example templates
+- Translations
+- Comprehensive rewrites
+
+## Not Accepted
+
+- Marketing language or promotional content
+- Unverified or speculative information
+- Breaking changes to structure without discussion
+- Large changes without prior issue discussion
+
+## Recognition
+
+Contributors are recognized through:
+
+- **Git history** - Your commits are permanently attributed
+- **GitHub contributors** - Visible on the repository page
+
+For significant contributions, we may add you to a "Contributors" section.
+
+## Questions?
+
+- Open an issue for general questions
+- Reach out on [LinkedIn](https://www.linkedin.com/in/florian-bruniaux-43408b83/) for direct contact
+
+---
+
+Thank you for helping improve this guide!
diff --git a/README.md b/README.md
index aa35d8b..e14575b 100644
--- a/README.md
+++ b/README.md
@@ -142,9 +142,42 @@ claude
 
 ---
 
+## Learning Paths
+
+Choose your path based on experience and goals:
+
+### Junior Developer (45 min to productivity)
+1. [Quick Start](./english-ultimate-claude-code-guide.md#1-quick-start-day-1) - Installation & first workflow
+2. [Essential Commands](./english-ultimate-claude-code-guide.md#13-essential-commands) - The 7 commands you need
+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) - Create your first CLAUDE.md
+5. [Cheatsheet](./cheatsheet-en.md) - Print and keep nearby
+
+### Senior Developer (40 min to mastery)
+1. [Core Concepts](./english-ultimate-claude-code-guide.md#2-core-concepts) - Mental model & context zones
+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-driven automation
+5. [CI/CD Integration](./english-ultimate-claude-code-guide.md#93-cicd-integration) - Pipeline automation
+
+### Power User (2 hours for full mastery)
+1. Read the [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. [The Trinity Pattern](./english-ultimate-claude-code-guide.md#91-the-trinity) - Advanced workflows
+4. [Audit your setup](./claude-setup-audit-prompt.md) - Optimize your configuration
+5. Explore [examples/](./examples/) - Ready-to-use templates
+
+### Non-Technical / Product Manager (20 min overview)
+1. [What's Inside](#whats-inside) - Understand the scope
+2. [The Golden Rules](#the-golden-rules) - Key principles
+3. [Core Concepts](./english-ultimate-claude-code-guide.md#2-core-concepts) - High-level overview
+4. [Context Management](./english-ultimate-claude-code-guide.md#22-context-management) - Why it matters
+
+---
+
 ## Contributing
 
-Found an error? Have a suggestion? Open an issue or PR.
+Found an error? Have a suggestion? See [CONTRIBUTING.md](./CONTRIBUTING.md) for guidelines.
 
 ---
 
diff --git a/english-ultimate-claude-code-guide.md b/english-ultimate-claude-code-guide.md
index 820c1c0..4f06331 100644
--- a/english-ultimate-claude-code-guide.md
+++ b/english-ultimate-claude-code-guide.md
@@ -687,6 +687,67 @@ Claude: [Executes the plan]
 
 **Result**: 76% fewer tokens with better results because the plan is validated before execution.
 
+### OpusPlan Mode
+
+**Concept**: Use Opus for planning (superior reasoning) and Sonnet for implementation (cost-efficient).
+
+**Why OpusPlan?**
+- **Cost optimization**: Opus tokens cost more than Sonnet
+- **Best of both worlds**: Opus-quality planning + Sonnet-speed execution
+- **Token savings**: Planning is typically shorter than implementation
+
+**Activation**:
+```
+/model opusplan
+```
+
+Or in `~/.claude/settings.json`:
+```json
+{
+  "model": "opusplan"
+}
+```
+
+**How It Works**:
+1. In **Plan Mode** (`/plan` or `Shift+Tab` twice) → Uses **Opus**
+2. In **Act Mode** (normal execution) → Uses **Sonnet**
+3. Automatic switching based on mode
+
+**Recommended Workflow**:
+```
+1. /model opusplan        → Enable OpusPlan
+2. Shift+Tab × 2          → Enter Plan Mode (Opus)
+3. Describe your task     → Get Opus-quality planning
+4. Shift+Tab              → Exit to Act Mode (Sonnet)
+5. Execute the plan       → Sonnet implements efficiently
+```
+
+**Alternative Approach with Subagents**:
+
+You can also control model usage per agent:
+
+```yaml
+# .claude/agents/planner.md
+---
+name: planner
+model: opus
+tools: Read, Grep, Glob
+---
+# Strategic Planning Agent
+```
+
+```yaml
+# .claude/agents/implementer.md
+---
+name: implementer
+model: haiku
+tools: Write, Edit, Bash
+---
+# Fast Implementation Agent
+```
+
+**Pro Users Note**: OpusPlan is particularly valuable for Pro subscribers with limited Opus tokens. It lets you leverage Opus reasoning for critical planning while preserving tokens for more sessions.
+
 ## 2.4 Rewind
 
 Rewind is Claude Code's undo mechanism.
diff --git a/examples/README.md b/examples/README.md
new file mode 100644
index 0000000..ed43084
--- /dev/null
+++ b/examples/README.md
@@ -0,0 +1,79 @@
+# Claude Code Examples
+
+Ready-to-use templates for Claude Code configuration.
+
+## Structure
+
+| Folder | Description |
+|--------|-------------|
+| [`agents/`](./agents/) | Custom AI personas for specialized tasks |
+| [`skills/`](./skills/) | Reusable knowledge modules |
+| [`commands/`](./commands/) | Custom slash commands |
+| [`hooks/`](./hooks/) | Event-driven automation scripts |
+| [`config/`](./config/) | Configuration file templates |
+| [`memory/`](./memory/) | CLAUDE.md memory file templates |
+
+## Quick Start
+
+1. Copy the template you need
+2. Customize for your project
+3. Place in the correct location (see paths below)
+
+## File Locations
+
+| Type | Project Location | Global Location |
+|------|------------------|-----------------|
+| Agents | `.claude/agents/` | `~/.claude/agents/` |
+| Skills | `.claude/skills/` | `~/.claude/skills/` |
+| Commands | `.claude/commands/` | `~/.claude/commands/` |
+| Hooks | `.claude/hooks/` | `~/.claude/hooks/` |
+| Config | `.claude/` | `~/.claude/` |
+| Memory | `./CLAUDE.md` or `.claude/CLAUDE.md` | `~/.claude/CLAUDE.md` |
+
+> **Windows**: Replace `~/.claude/` with `%USERPROFILE%\.claude\`
+
+## Templates Index
+
+### Agents
+| File | Purpose | Model |
+|------|---------|-------|
+| [code-reviewer.md](./agents/code-reviewer.md) | Thorough code review | Sonnet |
+| [test-writer.md](./agents/test-writer.md) | TDD/BDD test generation | Sonnet |
+| [security-auditor.md](./agents/security-auditor.md) | Security vulnerability detection | Sonnet |
+| [refactoring-specialist.md](./agents/refactoring-specialist.md) | Clean code refactoring | Sonnet |
+
+### Skills
+| File | Purpose |
+|------|---------|
+| [tdd-workflow.md](./skills/tdd-workflow.md) | Test-Driven Development process |
+| [security-checklist.md](./skills/security-checklist.md) | OWASP Top 10 security checks |
+
+### Commands
+| File | Trigger | Purpose |
+|------|---------|---------|
+| [commit.md](./commands/commit.md) | `/commit` | Conventional commit messages |
+| [review-pr.md](./commands/review-pr.md) | `/review-pr` | PR review workflow |
+| [generate-tests.md](./commands/generate-tests.md) | `/generate-tests` | Test generation |
+
+### Hooks
+| File | Event | Purpose |
+|------|-------|---------|
+| [security-check.*](./hooks/) | PreToolUse | Block secrets in commands |
+| [auto-format.*](./hooks/) | PostToolUse | Auto-format after edits |
+
+### Config
+| File | Purpose |
+|------|---------|
+| [settings.json](./config/settings.json) | Hooks configuration |
+| [mcp.json](./config/mcp.json) | MCP servers setup |
+| [.gitignore-claude](./config/.gitignore-claude) | Git ignore patterns |
+
+### Memory
+| File | Purpose |
+|------|---------|
+| [CLAUDE.md.project-template](./memory/CLAUDE.md.project-template) | Team project memory |
+| [CLAUDE.md.personal-template](./memory/CLAUDE.md.personal-template) | Personal global memory |
+
+---
+
+*See the [main guide](../english-ultimate-claude-code-guide.md) for detailed explanations.*
diff --git a/examples/agents/code-reviewer.md b/examples/agents/code-reviewer.md
new file mode 100644
index 0000000..07dfc45
--- /dev/null
+++ b/examples/agents/code-reviewer.md
@@ -0,0 +1,71 @@
+---
+name: code-reviewer
+description: Use for thorough code review with quality, security, and performance checks
+model: sonnet
+tools: Read, Grep, Glob
+---
+
+# Code Review Agent
+
+You are a senior code reviewer focused on code quality, security, and maintainability.
+
+## Review Checklist
+
+For every code review, analyze:
+
+### Correctness
+- [ ] Logic is sound and handles edge cases
+- [ ] Error handling is comprehensive
+- [ ] No obvious bugs or regressions
+
+### Security (OWASP Top 10)
+- [ ] No injection vulnerabilities (SQL, XSS, Command)
+- [ ] Authentication/authorization properly implemented
+- [ ] Sensitive data not exposed
+- [ ] No hardcoded secrets or credentials
+
+### Performance
+- [ ] No N+1 queries or unnecessary loops
+- [ ] Appropriate data structures used
+- [ ] No memory leaks or resource exhaustion risks
+
+### Maintainability
+- [ ] Code is readable and self-documenting
+- [ ] Functions are single-purpose
+- [ ] No excessive complexity (cyclomatic complexity)
+- [ ] DRY principle followed
+
+### Testing
+- [ ] Adequate test coverage for new code
+- [ ] Edge cases tested
+- [ ] Tests are meaningful, not just for coverage
+
+## Output Format
+
+Structure your review as:
+
+```markdown
+## Summary
+[1-2 sentence overall assessment]
+
+## Critical Issues
+[Must fix before merge - security, bugs, data loss risks]
+
+## Improvements
+[Recommended changes for better quality]
+
+## Minor Suggestions
+[Style, naming, documentation improvements]
+
+## Positives
+[What's done well - be specific]
+```
+
+Always reference specific lines: `file.ts:45-50`
+
+## Review Style
+
+- Be constructive, not critical
+- Explain WHY, not just WHAT
+- Suggest alternatives when pointing out issues
+- Acknowledge good patterns when you see them
diff --git a/examples/agents/refactoring-specialist.md b/examples/agents/refactoring-specialist.md
new file mode 100644
index 0000000..9993103
--- /dev/null
+++ b/examples/agents/refactoring-specialist.md
@@ -0,0 +1,121 @@
+---
+name: refactoring-specialist
+description: Use for clean code refactoring following SOLID principles and best practices
+model: sonnet
+tools: Read, Write, Edit, MultiEdit, Grep, Glob
+---
+
+# Refactoring Specialist Agent
+
+You are a clean code advocate focused on improving code quality through systematic refactoring.
+
+## Refactoring Principles
+
+### SOLID Principles
+- **S**ingle Responsibility: One reason to change
+- **O**pen/Closed: Open for extension, closed for modification
+- **L**iskov Substitution: Subtypes must be substitutable
+- **I**nterface Segregation: Prefer small, specific interfaces
+- **D**ependency Inversion: Depend on abstractions
+
+### Code Smells to Address
+- Long methods (>20 lines)
+- Large classes (>200 lines)
+- Duplicate code
+- Feature envy
+- Data clumps
+- Primitive obsession
+- Long parameter lists
+- Switch statements
+- Parallel inheritance hierarchies
+
+## Refactoring Catalog
+
+### Extract Method
+When: Code block does one distinct thing
+```javascript
+// Before
+function processOrder(order) {
+  // validate
+  if (!order.items) throw new Error();
+  if (!order.customer) throw new Error();
+  // calculate
+  let total = 0;
+  for (const item of order.items) {
+    total += item.price * item.quantity;
+  }
+  // save
+  db.save(order);
+}
+
+// After
+function processOrder(order) {
+  validateOrder(order);
+  order.total = calculateTotal(order.items);
+  saveOrder(order);
+}
+```
+
+### Replace Conditional with Polymorphism
+When: Switch/if-else based on type
+```javascript
+// Before
+function getSpeed(vehicle) {
+  switch(vehicle.type) {
+    case 'car': return vehicle.engine * 2;
+    case 'bike': return vehicle.pedals * 5;
+  }
+}
+
+// After
+class Car { getSpeed() { return this.engine * 2; } }
+class Bike { getSpeed() { return this.pedals * 5; } }
+```
+
+### Introduce Parameter Object
+When: Multiple parameters travel together
+```javascript
+// Before
+function createRange(start, end, step, inclusive) {}
+
+// After
+function createRange({ start, end, step = 1, inclusive = false }) {}
+```
+
+## Refactoring Process
+
+1. **Ensure tests exist** - Never refactor without test coverage
+2. **Make one change** - Small, incremental changes
+3. **Run tests** - Verify behavior unchanged
+4. **Commit** - Atomic commits for each refactoring
+5. **Repeat** - Continue until satisfied
+
+## Output Format
+
+```markdown
+## Refactoring Report
+
+### Identified Issues
+1. [Code smell] in [file:line] - [impact]
+
+### Proposed Refactorings
+1. **[Refactoring Name]**
+   - Target: file:line
+   - Reason: [why this improves code]
+   - Risk: Low/Medium/High
+
+### Implementation Order
+1. [Lowest risk first]
+2. [Build on previous changes]
+
+### Test Coverage Required
+- [ ] Tests for [component] before refactoring
+```
+
+## Safety Rules
+
+- Always preserve behavior (no feature changes during refactoring)
+- Run tests after each change
+- Commit frequently
+- Document breaking changes
+- Keep refactoring PRs separate from feature PRs
diff --git a/examples/agents/security-auditor.md b/examples/agents/security-auditor.md
new file mode 100644
index 0000000..a98287a
--- /dev/null
+++ b/examples/agents/security-auditor.md
@@ -0,0 +1,114 @@
+---
+name: security-auditor
+description: Use for security vulnerability detection and OWASP compliance checks
+model: sonnet
+tools: Read, Grep, Glob
+---
+
+# Security Auditor Agent
+
+You are a security specialist focused on identifying vulnerabilities and ensuring secure coding practices.
+
+## OWASP Top 10 Checklist
+
+### A01: Broken Access Control
+- [ ] Authorization checks on all endpoints
+- [ ] CORS properly configured
+- [ ] Directory traversal prevention
+- [ ] IDOR (Insecure Direct Object Reference) prevention
+
+### A02: Cryptographic Failures
+- [ ] Sensitive data encrypted at rest
+- [ ] TLS for data in transit
+- [ ] Strong algorithms (no MD5, SHA1 for passwords)
+- [ ] Proper key management
+
+### A03: Injection
+- [ ] SQL injection prevention (parameterized queries)
+- [ ] XSS prevention (output encoding)
+- [ ] Command injection prevention
+- [ ] LDAP/XML injection prevention
+
+### A04: Insecure Design
+- [ ] Threat modeling considered
+- [ ] Security requirements defined
+- [ ] Principle of least privilege
+
+### A05: Security Misconfiguration
+- [ ] Default credentials changed
+- [ ] Error messages don't expose internals
+- [ ] Security headers present
+- [ ] Unnecessary features disabled
+
+### A06: Vulnerable Components
+- [ ] Dependencies up to date
+- [ ] Known vulnerabilities checked (npm audit)
+- [ ] Only necessary packages included
+
+### A07: Authentication Failures
+- [ ] Strong password requirements
+- [ ] Rate limiting on auth endpoints
+- [ ] Session management secure
+- [ ] MFA consideration
+
+### A08: Data Integrity Failures
+- [ ] Input validation
+- [ ] Deserialization safety
+- [ ] CI/CD pipeline security
+
+### A09: Logging Failures
+- [ ] Security events logged
+- [ ] Log injection prevention
+- [ ] Sensitive data not in logs
+
+### A10: SSRF
+- [ ] URL validation
+- [ ] Whitelist allowed destinations
+- [ ] Network segmentation
+
+## Audit Output Format
+
+```markdown
+## Security Audit Report
+
+### Critical Vulnerabilities
+[Immediate action required]
+
+| Severity | Issue | Location | Remediation |
+|----------|-------|----------|-------------|
+| CRITICAL | ... | file:line | ... |
+
+### High-Risk Issues
+[Fix before production]
+
+### Medium-Risk Issues
+[Address in next sprint]
+
+### Recommendations
+[Best practice improvements]
+
+### Compliant Areas
+[What's done well]
+```
+
+## Common Patterns to Check
+
+```javascript
+// BAD: SQL Injection
+query = `SELECT * FROM users WHERE id = ${userId}`
+
+// GOOD: Parameterized
+query = `SELECT * FROM users WHERE id = $1`, [userId]
+
+// BAD: XSS vulnerable
+element.innerHTML = userInput
+
+// GOOD: Safe
+element.textContent = userInput
+
+// BAD: Hardcoded secret
+const API_KEY = "sk-abc123..."
+
+// GOOD: Environment variable
+const API_KEY = process.env.API_KEY
+```
diff --git a/examples/agents/test-writer.md b/examples/agents/test-writer.md
new file mode 100644
index 0000000..1d9a416
--- /dev/null
+++ b/examples/agents/test-writer.md
@@ -0,0 +1,106 @@
+---
+name: test-writer
+description: Use for generating comprehensive tests following TDD/BDD principles
+model: sonnet
+tools: Read, Write, Edit, Grep, Glob, Bash
+---
+
+# Test Writer Agent
+
+You are a testing specialist focused on creating comprehensive, meaningful tests.
+
+## Testing Philosophy
+
+1. **Tests document behavior** - Tests are living documentation
+2. **Test behavior, not implementation** - Focus on what, not how
+3. **One concept per test** - Each test should verify one thing
+4. **Arrange-Act-Assert** - Clear test structure
+
+## Test Generation Process
+
+### 1. Analyze the Code
+- Identify public interfaces
+- Find edge cases and boundaries
+- Detect error scenarios
+- Understand dependencies
+
+### 2. Create Test Plan
+Before writing tests, outline:
+```
+## Test Plan for [Component]
+
+### Happy Path
+- [ ] Basic functionality works
+
+### Edge Cases
+- [ ] Empty input
+- [ ] Maximum values
+- [ ] Minimum values
+
+### Error Handling
+- [ ] Invalid input
+- [ ] Network failures
+- [ ] Timeout scenarios
+
+### Integration Points
+- [ ] Database interactions
+- [ ] External API calls
+```
+
+### 3. Write Tests
+Follow the project's testing framework conventions.
+
+## Test Templates
+
+### Unit Test (Jest/Vitest)
+```typescript
+describe('ComponentName', () => {
+  describe('methodName', () => {
+    it('should [expected behavior] when [condition]', () => {
+      // Arrange
+      const input = createTestInput();
+
+      // Act
+      const result = component.methodName(input);
+
+      // Assert
+      expect(result).toEqual(expectedOutput);
+    });
+
+    it('should throw error when [invalid condition]', () => {
+      // Arrange
+      const invalidInput = createInvalidInput();
+
+      // Act & Assert
+      expect(() => component.methodName(invalidInput))
+        .toThrow(ExpectedError);
+    });
+  });
+});
+```
+
+### Integration Test
+```typescript
+describe('Feature Integration', () => {
+  beforeAll(async () => {
+    // Setup: database, mocks, etc.
+  });
+
+  afterAll(async () => {
+    // Cleanup
+  });
+
+  it('should complete full workflow', async () => {
+    // Test complete user journey
+  });
+});
+```
+
+## Best Practices
+
+- Use descriptive test names (`should_return_empty_when_no_items`)
+- Avoid test interdependence
+- Mock external dependencies
+- Use factories for test data
+- Keep tests fast (< 100ms for unit tests)
+- Don't test private methods directly
diff --git a/examples/commands/commit.md b/examples/commands/commit.md
new file mode 100644
index 0000000..d29101c
--- /dev/null
+++ b/examples/commands/commit.md
@@ -0,0 +1,68 @@
+# Conventional Commit
+
+Generate a conventional commit message for staged changes.
+
+## Instructions
+
+1. Run `git diff --cached` to see staged changes
+2. Analyze the nature of changes
+3. Generate a commit message following the format below
+
+## Commit Format
+
+```
+<type>(<scope>): <subject>
+
+[optional body]
+
+[optional footer]
+```
+
+### Types
+- `feat`: New feature
+- `fix`: Bug fix
+- `docs`: Documentation only
+- `style`: Formatting, missing semicolons, etc.
+- `refactor`: Code change that neither fixes nor adds feature
+- `perf`: Performance improvement
+- `test`: Adding missing tests
+- `chore`: Maintenance tasks
+
+### Rules
+- Subject: imperative mood, no period, max 50 chars
+- Body: explain WHAT and WHY, not HOW
+- Footer: breaking changes, issue references
+
+## Examples
+
+```
+feat(auth): add password reset functionality
+
+Implement password reset flow with email verification.
+Users can now request a reset link and set new password.
+
+Closes #123
+```
+
+```
+fix(api): prevent race condition in order processing
+
+Add mutex lock to ensure orders are processed sequentially.
+This fixes duplicate charge issues reported by users.
+
+Fixes #456
+```
+
+```
+refactor(cart): extract pricing logic to separate module
+
+No functional changes. Improves testability and
+separates concerns for future discount feature.
+```
+
+## Execution
+
+After analyzing staged changes, suggest a commit message.
+Ask for confirmation before executing `git commit -m "..."`.
+
+$ARGUMENTS
diff --git a/examples/commands/generate-tests.md b/examples/commands/generate-tests.md
new file mode 100644
index 0000000..3795a41
--- /dev/null
+++ b/examples/commands/generate-tests.md
@@ -0,0 +1,88 @@
+# Generate Tests
+
+Generate comprehensive tests for specified code.
+
+## Instructions
+
+1. Read the target file(s)
+2. Identify testable units (functions, classes, methods)
+3. Generate tests following project conventions
+4. Ensure high coverage of edge cases
+
+## Test Generation Process
+
+### 1. Analyze Target
+- Identify public interfaces
+- Understand dependencies
+- Note edge cases and boundaries
+
+### 2. Detect Test Framework
+Check for:
+- `jest.config.js` → Jest
+- `vitest.config.ts` → Vitest
+- `pytest.ini` → pytest
+- `mocha` in package.json → Mocha
+
+### 3. Generate Tests
+Follow the detected framework conventions.
+
+## Test Categories
+
+### Happy Path
+Normal expected behavior with valid input.
+
+### Edge Cases
+- Empty inputs
+- Null/undefined values
+- Boundary values (0, -1, MAX_INT)
+- Single item vs multiple items
+
+### Error Cases
+- Invalid input types
+- Missing required parameters
+- Network/IO failures
+- Timeout scenarios
+
+### Integration Points
+- Database interactions
+- External API calls
+- File system operations
+
+## Output Format
+
+```typescript
+describe('[ComponentName]', () => {
+  describe('[methodName]', () => {
+    // Happy path
+    it('should [expected behavior] when [condition]', () => {
+      // Arrange
+      // Act
+      // Assert
+    });
+
+    // Edge cases
+    it('should handle empty input', () => {});
+    it('should handle null values', () => {});
+
+    // Error cases
+    it('should throw when [invalid condition]', () => {});
+  });
+});
+```
+
+## Conventions
+
+- One assertion per test (when practical)
+- Descriptive test names
+- AAA pattern (Arrange-Act-Assert)
+- No test interdependence
+- Mock external dependencies
+
+## Usage
+
+```
+/generate-tests src/utils/calculator.ts
+/generate-tests src/services/
+```
+
+$ARGUMENTS
diff --git a/examples/commands/review-pr.md b/examples/commands/review-pr.md
new file mode 100644
index 0000000..726bf04
--- /dev/null
+++ b/examples/commands/review-pr.md
@@ -0,0 +1,79 @@
+# Review Pull Request
+
+Perform a comprehensive code review of a pull request.
+
+## Instructions
+
+1. Get PR information: `gh pr view $ARGUMENTS --json title,body,files,additions,deletions`
+2. Review each changed file
+3. Provide structured feedback
+
+## Review Checklist
+
+### Code Quality
+- [ ] Code is readable and well-organized
+- [ ] Functions are appropriately sized
+- [ ] No code duplication
+- [ ] Meaningful variable/function names
+
+### Functionality
+- [ ] Logic is correct
+- [ ] Edge cases handled
+- [ ] Error handling is comprehensive
+- [ ] No obvious bugs
+
+### Security
+- [ ] No hardcoded secrets
+- [ ] Input validation present
+- [ ] No injection vulnerabilities
+- [ ] Authorization checks in place
+
+### Testing
+- [ ] Tests added for new code
+- [ ] Existing tests still pass
+- [ ] Edge cases tested
+
+### Documentation
+- [ ] Code is self-documenting or commented
+- [ ] README updated if needed
+- [ ] API changes documented
+
+## Output Format
+
+```markdown
+## PR Review: #[number] - [title]
+
+### Summary
+[1-2 sentence overview]
+
+### Approval Status
+[ ] Approved
+[ ] Approved with suggestions
+[ ] Changes requested
+
+### Findings
+
+#### Critical (Must Fix)
+- [ ] [Issue description] - `file:line`
+
+#### Suggestions (Should Consider)
+- [ ] [Improvement] - `file:line`
+
+#### Nitpicks (Optional)
+- [ ] [Minor suggestion] - `file:line`
+
+### Positive Highlights
+- [What's done well]
+
+### Questions
+- [Clarifications needed]
+```
+
+## Usage
+
+```
+/review-pr 123
+/review-pr https://github.com/owner/repo/pull/123
+```
+
+$ARGUMENTS
diff --git a/examples/config/.gitignore-claude b/examples/config/.gitignore-claude
new file mode 100644
index 0000000..9181cee
--- /dev/null
+++ b/examples/config/.gitignore-claude
@@ -0,0 +1,18 @@
+# Claude Code - Git Ignore Patterns
+# Add these to your project's .gitignore
+
+# Local settings (personal preferences)
+.claude/settings.local.json
+
+# Local memory (personal notes, not for team)
+.claude/CLAUDE.md
+
+# MCP server data (if using Serena memory)
+.serena/
+
+# Temporary Claude files
+.claude/tmp/
+.claude/cache/
+
+# Debug logs
+claude-debug.log
diff --git a/examples/config/mcp.json b/examples/config/mcp.json
new file mode 100644
index 0000000..829890c
--- /dev/null
+++ b/examples/config/mcp.json
@@ -0,0 +1,33 @@
+{
+  "mcpServers": {
+    "serena": {
+      "command": "uvx",
+      "args": ["serena", "--project-root", "."],
+      "description": "Codebase indexation and session memory"
+    },
+    "context7": {
+      "command": "npx",
+      "args": ["-y", "@upstash/context7-mcp"],
+      "description": "Library documentation lookup"
+    },
+    "sequential": {
+      "command": "npx",
+      "args": ["-y", "@anthropic/sequential-thinking-mcp"],
+      "description": "Structured multi-step reasoning"
+    },
+    "playwright": {
+      "command": "npx",
+      "args": ["-y", "@anthropic/playwright-mcp"],
+      "description": "Browser automation and testing"
+    },
+    "postgres": {
+      "command": "npx",
+      "args": [
+        "-y",
+        "@modelcontextprotocol/server-postgres",
+        "postgresql://user:password@localhost:5432/database"
+      ],
+      "description": "PostgreSQL database queries"
+    }
+  }
+}
diff --git a/examples/config/settings.json b/examples/config/settings.json
new file mode 100644
index 0000000..926ce14
--- /dev/null
+++ b/examples/config/settings.json
@@ -0,0 +1,16 @@
+{
+  "hooks": {
+    "PreToolUse": [
+      {
+        "matcher": "Bash",
+        "command": ".claude/hooks/security-check.sh"
+      }
+    ],
+    "PostToolUse": [
+      {
+        "matcher": "Write|Edit",
+        "command": ".claude/hooks/auto-format.sh"
+      }
+    ]
+  }
+}
diff --git a/examples/hooks/bash/auto-format.sh b/examples/hooks/bash/auto-format.sh
new file mode 100644
index 0000000..90370dd
--- /dev/null
+++ b/examples/hooks/bash/auto-format.sh
@@ -0,0 +1,48 @@
+#!/bin/bash
+# PostToolUse hook - Auto-format files after editing
+# Place in: .claude/hooks/auto-format.sh
+# Register in: .claude/settings.json
+
+INPUT=$(cat)
+TOOL=$(echo "$INPUT" | jq -r '.tool_name')
+
+# Only run after Write or Edit operations
+if [[ "$TOOL" == "Write" || "$TOOL" == "Edit" ]]; then
+    FILE=$(echo "$INPUT" | jq -r '.tool_input.file_path // .tool_input.path')
+
+    if [[ -z "$FILE" || "$FILE" == "null" ]]; then
+        exit 0
+    fi
+
+    # Get file extension
+    EXT="${FILE##*.}"
+
+    case "$EXT" in
+        js|jsx|ts|tsx|json|css|scss|md|html|vue)
+            # Format with Prettier if available
+            if command -v npx &> /dev/null && [[ -f "node_modules/.bin/prettier" ]]; then
+                npx prettier --write "$FILE" 2>/dev/null
+            fi
+            ;;
+        py)
+            # Format with Black if available
+            if command -v black &> /dev/null; then
+                black "$FILE" 2>/dev/null
+            fi
+            ;;
+        go)
+            # Format with gofmt
+            if command -v gofmt &> /dev/null; then
+                gofmt -w "$FILE" 2>/dev/null
+            fi
+            ;;
+        rs)
+            # Format with rustfmt
+            if command -v rustfmt &> /dev/null; then
+                rustfmt "$FILE" 2>/dev/null
+            fi
+            ;;
+    esac
+fi
+
+exit 0
diff --git a/examples/hooks/bash/security-check.sh b/examples/hooks/bash/security-check.sh
new file mode 100644
index 0000000..166fb59
--- /dev/null
+++ b/examples/hooks/bash/security-check.sh
@@ -0,0 +1,47 @@
+#!/bin/bash
+# PreToolUse hook - Block commands containing secrets
+# Place in: .claude/hooks/security-check.sh
+# Register in: .claude/settings.json
+
+INPUT=$(cat)
+TOOL=$(echo "$INPUT" | jq -r '.tool_name')
+
+if [[ "$TOOL" == "Bash" ]]; then
+    COMMAND=$(echo "$INPUT" | jq -r '.tool_input.command')
+
+    # Check for common secret patterns
+    PATTERNS=(
+        "password="
+        "PASSWORD="
+        "secret="
+        "SECRET="
+        "api_key="
+        "API_KEY="
+        "apikey="
+        "token="
+        "TOKEN="
+        "aws_access_key"
+        "AWS_ACCESS_KEY"
+        "aws_secret"
+        "AWS_SECRET"
+        "private_key"
+        "PRIVATE_KEY"
+    )
+
+    for PATTERN in "${PATTERNS[@]}"; do
+        if echo "$COMMAND" | grep -qi "$PATTERN"; then
+            echo "{\"decision\": \"block\", \"reason\": \"Potential secret detected: $PATTERN\"}"
+            exit 2
+        fi
+    done
+
+    # Check for hardcoded credentials in common formats
+    # API keys (typically long alphanumeric strings)
+    if echo "$COMMAND" | grep -qE "(sk-[a-zA-Z0-9]{20,}|pk_[a-zA-Z0-9]{20,}|[a-f0-9]{32,})"; then
+        echo "{\"decision\": \"block\", \"reason\": \"Potential API key or hash detected\"}"
+        exit 2
+    fi
+fi
+
+# Allow the command
+exit 0
diff --git a/examples/hooks/powershell/auto-format.ps1 b/examples/hooks/powershell/auto-format.ps1
new file mode 100644
index 0000000..e931b8a
--- /dev/null
+++ b/examples/hooks/powershell/auto-format.ps1
@@ -0,0 +1,50 @@
+# PostToolUse hook - Auto-format files after editing
+# Place in: .claude\hooks\auto-format.ps1
+# Register in: .claude\settings.json (with -ExecutionPolicy Bypass)
+
+$inputJson = [Console]::In.ReadToEnd() | ConvertFrom-Json
+$tool = $inputJson.tool_name
+
+# Only run after Write or Edit operations
+if ($tool -eq "Write" -or $tool -eq "Edit") {
+    $file = $inputJson.tool_input.file_path
+    if (-not $file) {
+        $file = $inputJson.tool_input.path
+    }
+
+    if (-not $file -or $file -eq "null") {
+        exit 0
+    }
+
+    # Get file extension
+    $ext = [System.IO.Path]::GetExtension($file).TrimStart('.')
+
+    switch ($ext) {
+        { $_ -in @("js", "jsx", "ts", "tsx", "json", "css", "scss", "md", "html", "vue") } {
+            # Format with Prettier if available
+            if (Test-Path "node_modules\.bin\prettier.cmd") {
+                & npx prettier --write $file 2>$null
+            }
+        }
+        "py" {
+            # Format with Black if available
+            if (Get-Command black -ErrorAction SilentlyContinue) {
+                & black $file 2>$null
+            }
+        }
+        "go" {
+            # Format with gofmt
+            if (Get-Command gofmt -ErrorAction SilentlyContinue) {
+                & gofmt -w $file 2>$null
+            }
+        }
+        "rs" {
+            # Format with rustfmt
+            if (Get-Command rustfmt -ErrorAction SilentlyContinue) {
+                & rustfmt $file 2>$null
+            }
+        }
+    }
+}
+
+exit 0
diff --git a/examples/hooks/powershell/security-check.ps1 b/examples/hooks/powershell/security-check.ps1
new file mode 100644
index 0000000..0137619
--- /dev/null
+++ b/examples/hooks/powershell/security-check.ps1
@@ -0,0 +1,45 @@
+# PreToolUse hook - Block commands containing secrets
+# Place in: .claude\hooks\security-check.ps1
+# Register in: .claude\settings.json (with -ExecutionPolicy Bypass)
+
+$inputJson = [Console]::In.ReadToEnd() | ConvertFrom-Json
+$tool = $inputJson.tool_name
+
+if ($tool -eq "Bash") {
+    $command = $inputJson.tool_input.command
+
+    # Check for common secret patterns
+    $patterns = @(
+        "password=",
+        "PASSWORD=",
+        "secret=",
+        "SECRET=",
+        "api_key=",
+        "API_KEY=",
+        "apikey=",
+        "token=",
+        "TOKEN=",
+        "aws_access_key",
+        "AWS_ACCESS_KEY",
+        "aws_secret",
+        "AWS_SECRET",
+        "private_key",
+        "PRIVATE_KEY"
+    )
+
+    foreach ($pattern in $patterns) {
+        if ($command -match [regex]::Escape($pattern)) {
+            Write-Output "{`"decision`": `"block`", `"reason`": `"Potential secret detected: $pattern`"}"
+            exit 2
+        }
+    }
+
+    # Check for hardcoded API keys
+    if ($command -match "(sk-[a-zA-Z0-9]{20,}|pk_[a-zA-Z0-9]{20,}|[a-f0-9]{32,})") {
+        Write-Output "{`"decision`": `"block`", `"reason`": `"Potential API key or hash detected`"}"
+        exit 2
+    }
+}
+
+# Allow the command
+exit 0
diff --git a/examples/memory/CLAUDE.md.personal-template b/examples/memory/CLAUDE.md.personal-template
new file mode 100644
index 0000000..977b2d4
--- /dev/null
+++ b/examples/memory/CLAUDE.md.personal-template
@@ -0,0 +1,68 @@
+# Personal Claude Memory
+
+> This file provides Claude with your personal preferences.
+> Place at: ~/.claude/CLAUDE.md (global, applies to all projects).
+
+## Communication Style
+
+- Be concise and direct
+- Use code examples over explanations
+- Challenge my assumptions when needed
+- Don't over-explain obvious things
+
+## Development Preferences
+
+### Languages & Frameworks
+- Primary: TypeScript, React, Node.js
+- Secondary: Python, Go
+- Preferred test framework: Vitest/Jest
+
+### Code Style
+- Prefer functional programming
+- Use early returns
+- Keep functions small
+- Meaningful variable names over comments
+
+### Tools
+- Editor: VS Code
+- Terminal: iTerm2 / Windows Terminal
+- Version control: Git
+
+## Workflow Preferences
+
+### When Writing Code
+- Always include type definitions
+- Add error handling
+- Write tests for critical paths
+- Use async/await over callbacks
+
+### When Reviewing
+- Focus on logic and security first
+- Style suggestions are secondary
+- Point out potential edge cases
+
+### When Debugging
+- Show me the investigation process
+- Explain your reasoning
+- Suggest multiple solutions if applicable
+
+## Common Shortcuts
+
+- `cc` → `claude`
+- `gcm` → `git commit -m`
+- `gp` → `git push`
+
+## Pet Peeves
+
+- Don't add unnecessary comments
+- Don't over-engineer simple solutions
+- Don't ignore error handling
+- Don't use `any` in TypeScript
+
+## Learning Goals
+
+- [Current focus areas for learning]
+
+## Notes
+
+- [Any other personal notes for Claude]
diff --git a/examples/memory/CLAUDE.md.project-template b/examples/memory/CLAUDE.md.project-template
new file mode 100644
index 0000000..4899b30
--- /dev/null
+++ b/examples/memory/CLAUDE.md.project-template
@@ -0,0 +1,71 @@
+# Project Memory - [Project Name]
+
+> This file provides Claude with persistent context about your project.
+> Place at: ./CLAUDE.md (project root) for team conventions.
+
+## Project Overview
+
+**Name**: [Project Name]
+**Type**: [Web app / API / CLI / Library]
+**Stack**: [e.g., TypeScript, Next.js, Prisma, PostgreSQL]
+
+## Architecture
+
+```
+src/
+├── app/          # Next.js app router
+├── components/   # React components
+├── lib/          # Shared utilities
+├── services/     # Business logic
+└── types/        # TypeScript types
+```
+
+## Conventions
+
+### Code Style
+- Use TypeScript strict mode
+- Prefer `const` over `let`
+- Use named exports
+- Maximum function length: 30 lines
+
+### Naming
+- Files: `kebab-case.ts`
+- Components: `PascalCase.tsx`
+- Functions: `camelCase`
+- Constants: `SCREAMING_SNAKE_CASE`
+
+### Git
+- Branch format: `type/description` (e.g., `feat/user-auth`)
+- Commit format: Conventional Commits
+- PR required for main branch
+
+## Key Files
+
+- `@src/lib/db.ts` - Database connection
+- `@src/services/auth.ts` - Authentication logic
+- `@docs/api.md` - API documentation
+
+## Testing
+
+- Framework: Vitest
+- Run: `npm test`
+- Coverage target: 80%
+
+## Commands
+
+```bash
+npm run dev      # Development server
+npm run build    # Production build
+npm run test     # Run tests
+npm run lint     # Lint code
+```
+
+## Known Issues
+
+- [Issue description and workaround if any]
+
+## Team Contacts
+
+- **Tech Lead**: [Name]
+- **Backend**: [Name]
+- **Frontend**: [Name]
diff --git a/examples/skills/security-checklist.md b/examples/skills/security-checklist.md
new file mode 100644
index 0000000..2e2f556
--- /dev/null
+++ b/examples/skills/security-checklist.md
@@ -0,0 +1,147 @@
+---
+name: security-checklist
+description: Comprehensive security checklist for web applications
+---
+
+# Security Checklist Skill
+
+## Quick Security Audit
+
+### Authentication
+- [ ] Passwords hashed with bcrypt/argon2 (cost factor >= 10)
+- [ ] Session tokens are cryptographically random
+- [ ] JWT tokens have short expiry (15min access, 7d refresh)
+- [ ] Rate limiting on login endpoints
+- [ ] Account lockout after failed attempts
+
+### Authorization
+- [ ] Every API endpoint checks permissions
+- [ ] No IDOR (Insecure Direct Object References)
+- [ ] Role-based access control implemented
+- [ ] Sensitive operations require re-authentication
+
+### Input Validation
+- [ ] All user input validated server-side
+- [ ] File uploads restricted by type and size
+- [ ] SQL queries use parameterized statements
+- [ ] HTML output encoded to prevent XSS
+
+### Data Protection
+- [ ] Sensitive data encrypted at rest
+- [ ] HTTPS enforced everywhere
+- [ ] Secure cookies (HttpOnly, Secure, SameSite)
+- [ ] No sensitive data in URLs or logs
+
+### Headers & CORS
+- [ ] Content-Security-Policy header set
+- [ ] X-Content-Type-Options: nosniff
+- [ ] X-Frame-Options: DENY (or SAMEORIGIN)
+- [ ] Strict-Transport-Security enabled
+- [ ] CORS properly restricted
+
+## Code Patterns
+
+### SQL Injection Prevention
+```javascript
+// VULNERABLE
+db.query(`SELECT * FROM users WHERE id = ${userId}`);
+
+// SECURE
+db.query('SELECT * FROM users WHERE id = $1', [userId]);
+```
+
+### XSS Prevention
+```javascript
+// VULNERABLE
+element.innerHTML = userInput;
+
+// SECURE
+element.textContent = userInput;
+
+// SECURE (with sanitization)
+element.innerHTML = DOMPurify.sanitize(userInput);
+```
+
+### CSRF Protection
+```javascript
+// Generate token
+const csrfToken = crypto.randomBytes(32).toString('hex');
+session.csrfToken = csrfToken;
+
+// Validate on POST
+if (req.body.csrf !== session.csrfToken) {
+  throw new ForbiddenError('Invalid CSRF token');
+}
+```
+
+### Secrets Management
+```javascript
+// NEVER in code
+const API_KEY = 'sk-abc123...';
+
+// Environment variables
+const API_KEY = process.env.API_KEY;
+
+// Secrets manager (production)
+const secret = await secretsManager.getSecret('api-key');
+```
+
+## Security Headers Example
+
+```javascript
+// Express middleware
+app.use((req, res, next) => {
+  res.setHeader('X-Content-Type-Options', 'nosniff');
+  res.setHeader('X-Frame-Options', 'DENY');
+  res.setHeader('X-XSS-Protection', '1; mode=block');
+  res.setHeader('Strict-Transport-Security', 'max-age=31536000; includeSubDomains');
+  res.setHeader('Content-Security-Policy', "default-src 'self'");
+  next();
+});
+```
+
+## Dependency Security
+
+```bash
+# Check for vulnerabilities
+npm audit
+
+# Auto-fix what's possible
+npm audit fix
+
+# Check outdated packages
+npm outdated
+
+# Update dependencies
+npm update
+```
+
+## Logging Security Events
+
+```javascript
+// Events to log
+logger.security({
+  event: 'login_failed',
+  ip: req.ip,
+  email: req.body.email,
+  reason: 'invalid_password',
+  timestamp: new Date().toISOString()
+});
+
+// Never log
+// - Passwords
+// - Full credit card numbers
+// - Session tokens
+// - Personal data (in production)
+```
+
+## Pre-Deployment Checklist
+
+1. [ ] Run `npm audit` - no critical vulnerabilities
+2. [ ] All secrets in environment variables
+3. [ ] Debug mode disabled
+4. [ ] Error messages don't expose internals
+5. [ ] HTTPS only (HTTP redirects to HTTPS)
+6. [ ] Database credentials rotated
+7. [ ] Logging configured (no sensitive data)
+8. [ ] Backup strategy tested
diff --git a/examples/skills/tdd-workflow.md b/examples/skills/tdd-workflow.md
new file mode 100644
index 0000000..024ea56
--- /dev/null
+++ b/examples/skills/tdd-workflow.md
@@ -0,0 +1,141 @@
+---
+name: tdd-workflow
+description: Test-Driven Development workflow and best practices
+---
+
+# TDD Workflow Skill
+
+## The TDD Cycle
+
+```
+RED → GREEN → REFACTOR
+ ↑__________________|
+```
+
+### 1. RED: Write a Failing Test
+- Write the smallest test that fails
+- Test should fail for the right reason
+- Ensure the test actually runs
+
+### 2. GREEN: Make it Pass
+- Write minimal code to pass the test
+- Don't optimize yet
+- It's okay if the code is ugly
+
+### 3. REFACTOR: Clean Up
+- Improve code structure
+- Remove duplication
+- Keep tests passing
+
+## TDD Best Practices
+
+### Test Naming Convention
+```
+should_[expected behavior]_when_[condition]
+```
+
+Examples:
+- `should_return_empty_array_when_no_items`
+- `should_throw_error_when_invalid_input`
+- `should_calculate_total_when_items_present`
+
+### Test Structure (AAA)
+```typescript
+it('should calculate discount when coupon applied', () => {
+  // Arrange - Set up test data
+  const cart = new Cart();
+  cart.addItem({ price: 100 });
+  const coupon = new Coupon('10OFF', 10);
+
+  // Act - Execute the behavior
+  cart.applyCoupon(coupon);
+
+  // Assert - Verify the result
+  expect(cart.total).toBe(90);
+});
+```
+
+### Test Isolation
+- Each test should be independent
+- No shared state between tests
+- Use `beforeEach` for common setup
+- Clean up in `afterEach`
+
+## TDD Workflow Example
+
+### Feature: Add item to cart
+
+**Step 1: RED**
+```typescript
+describe('Cart', () => {
+  it('should add item to cart', () => {
+    const cart = new Cart();
+    cart.addItem({ id: 1, name: 'Book', price: 29.99 });
+    expect(cart.items).toHaveLength(1);
+  });
+});
+```
+Run test → FAILS (Cart doesn't exist)
+
+**Step 2: GREEN**
+```typescript
+class Cart {
+  items = [];
+
+  addItem(item) {
+    this.items.push(item);
+  }
+}
+```
+Run test → PASSES
+
+**Step 3: REFACTOR**
+```typescript
+class Cart {
+  private _items: CartItem[] = [];
+
+  get items(): ReadonlyArray<CartItem> {
+    return this._items;
+  }
+
+  addItem(item: CartItem): void {
+    this._items.push(item);
+  }
+}
+```
+Run test → Still PASSES
+
+### Next iteration: Calculate total
+Repeat the cycle for each new behavior.
+
+## When to Use TDD
+
+### Good for TDD
+- Business logic
+- Complex algorithms
+- API endpoints
+- State management
+- Utility functions
+
+### Less Suitable
+- UI layout (visual testing better)
+- Database migrations
+- External integrations (use integration tests)
+- Exploratory/prototype code
+
+## Common TDD Mistakes
+
+1. **Writing too much test** - Start with smallest failing test
+2. **Writing too much code** - Only enough to pass
+3. **Skipping refactor** - Technical debt accumulates
+4. **Testing implementation** - Test behavior, not internals
+5. **Ignoring failing tests** - Fix or delete, never skip
+
+## Test Doubles
+
+| Type | Purpose | Example |
+|------|---------|---------|
+| Stub | Return fixed data | `jest.fn().mockReturnValue(42)` |
+| Mock | Verify interactions | `expect(mock).toHaveBeenCalled()` |
+| Spy | Track calls | `jest.spyOn(obj, 'method')` |
+| Fake | Simplified implementation | In-memory database |
diff --git a/llms.txt b/llms.txt
index 10fd6eb..65efe08 100644
--- a/llms.txt
+++ b/llms.txt
@@ -53,7 +53,16 @@ claude-code-ultimate-guide/
 ├── 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)
+├── examples/                           # Ready-to-use templates
+│   ├── agents/                         # Custom AI personas
+│   ├── skills/                         # Knowledge modules
+│   ├── commands/                       # Slash commands
+│   ├── hooks/                          # Event automation (bash + PowerShell)
+│   ├── config/                         # Configuration files
+│   └── memory/                         # CLAUDE.md templates
 └── *.pdf                               # Alternative formats
 ```
 
@@ -112,9 +121,11 @@ CC BY-SA 4.0 - Free to share and adapt with attribution.
 ## How to Use This Guide
 
 1. **New to Claude Code?** Start with README.md Quick Start section
-2. **Want comprehensive learning?** Read english-ultimate-claude-code-guide.md
-3. **Need daily reference?** Print cheatsheet-en.md
-4. **Want to audit your setup?** Use claude-setup-audit-prompt.md
+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
+6. **Need templates?** Browse examples/ folder for ready-to-use configs
 
 ## Keywords