Second 10-agent parallel audit covering all remaining sections:
ultimate-guide.md (ch1-ch11), workflows/ (17 files), quiz/ (12 files),
examples/agents+skills+commands. Source of truth: official Anthropic docs.
Key corrections:
Hook system (+8 missing events):
- Complete 17-event list: PermissionRequest, PostToolUseFailure, SubagentStart,
TeammateIdle, TaskCompleted, WorktreeCreate, WorktreeRemove, SessionEnd
- SessionStart confirmed valid (previous audit wrongly doubted it)
- Hook output format: hookSpecificOutput.permissionDecision (not {"decision":"block"})
- Missing common input fields added: transcript_path, cwd, permission_mode
Agent YAML frontmatter (13 valid fields restored/added):
- Restored: disallowedTools, memory, background, isolation, skills, permissionMode, hooks
- Added new: maxTurns, mcpServers
- Fixed: tools format is comma-separated (not space-separated)
Plan Mode (12 occurrences fixed):
- Ctrl+G = "open plan in text editor" (NOT "enter plan mode")
- Plan Mode = Shift+Tab × 2 (Normal → acceptEdits → plan)
Commands table (10.1) + built-in commands (6.1):
- Added 18+ missing commands: /copy, /doctor, /hooks, /memory, /model,
/config, /permissions, /remote-control, /rename, /resume, /sandbox, etc.
Workflow files:
- agent-teams.md: removed fake --experimental-agent-teams flag
- hooks.yaml + post_edit event → settings.json + PostToolUse (2 files)
- TodoWrite → TaskCreate/TaskUpdate (3 files)
- task-management.md: removed fake "failed" task status
Quiz / examples:
- 01-010: Esc stops mid-action (not Ctrl+C)
- refactoring-specialist.md: removed MultiEdit (not a valid tool)
- ast-grep-patterns.md: name field (not title)
- validate-changes.md, diagnose.md: field name fixes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| questions | ||
| src | ||
| templates | ||
| package-lock.json | ||
| package.json | ||
| README.md | ||
Claude Code Knowledge Quiz
Test your understanding of Claude Code with interactive multiple-choice questions.
Quick Start
# Navigate to quiz directory
cd quiz
# Install dependencies
npm install
# Run the quiz
npm start
# Or run directly
node src/index.js
Features
- 4 User Profiles: Junior, Senior, Power User, Product Manager
- 10 Topic Categories: From Quick Start to Advanced Patterns
- 159 Curated Questions: Practical knowledge, not trivia
- Immediate Feedback: Learn from mistakes with explanations
- Documentation Links: Direct references to guide sections
- Score Tracking: See strengths and weak areas
- Session Persistence: History saved to
~/.claude-quiz/ - Cross-Platform: Works on macOS, Linux, and Windows
Usage
Interactive Mode (Recommended)
npm start
You'll be prompted to:
- Select your profile (Junior/Senior/Power User/PM)
- Choose topics (all or specific sections)
- Answer questions with A/B/C/D
Command Line Options
node src/index.js [options]
Options:
-p, --profile <type> Pre-select profile (junior|senior|power|pm)
-t, --topics <list> Quiz specific sections (1-10, comma-separated)
-c, --count <n> Limit number of questions (1-50)
-d, --dynamic Enable dynamic question generation via claude -p
-h, --help Show help message
-v, --version Show version
Examples
# Interactive mode
npm start
# Senior profile, default topics
node src/index.js -p senior
# Power user, specific topics (Agents, Hooks, MCP)
node src/index.js -p power -t 4,7,8
# Quick 10-question quiz
node src/index.js -c 10
# Junior profile with dynamic generation
node src/index.js -p junior -d
Example Session
Here's what a typical quiz session looks like:
============================================================
CLAUDE CODE KNOWLEDGE QUIZ
Master Claude Code: The Complete Guide
============================================================
? Select your profile: Senior Developer (40 min to mastery)
? Select topics to quiz: Custom selection...
? Select topics (space to toggle, enter to confirm):
◉ [2] Core Concepts
◉ [4] Agents
◉ [7] Hooks
------------------------------------------------------------
Starting quiz: 20 questions for senior profile
------------------------------------------------------------
------------------------------------------------------------
Question 1/20 [Core Concepts]
At what context percentage should you use /compact?
A) 0-50%
B) 50-70%
C) 70-90%
D) Only at 100%
? Your answer: C
✓ CORRECT!
Progress: █░░░░░░░░░░░░░░░░░░░ 1/20 | Score: 1/1 (100%)
------------------------------------------------------------
Question 2/20 [Hooks]
What exit code should a PreToolUse hook return to BLOCK an operation?
A) 0
B) 1
C) 2
D) -1
? Your answer: A
✗ INCORRECT. The correct answer is C) 2
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/guide/ultimate-guide.md#72-creating-hooks
(Line 4164)
Progress: ██░░░░░░░░░░░░░░░░░░ 2/20 | Score: 1/2 (50%)
? Continue to next question? Yes
... (more questions) ...
============================================================
QUIZ COMPLETE
============================================================
Overall Score: 16/20 (80%)
By Category:
Core Concepts 6/7 (86%) [████████░░]
Agents 5/7 (71%) [███████░░░]
Hooks 5/6 (83%) [████████░░]
Weak Areas (< 75%):
- Agents: Review section 4 in the guide
Recommended Reading:
4. guide/ultimate-guide.md#4-agents
Time: 9 minutes 2 seconds
------------------------------------------------------------
? What would you like to do? (Use arrow keys)
❯ Retry wrong questions only
New quiz (different questions)
Exit
Profiles
| Profile | Questions | Focus Areas |
|---|---|---|
| Junior Developer | 15 | Sections 1-3, 6 (essentials) |
| Senior Developer | 20 | Sections 2-4, 7, 9 (architecture, automation) |
| Power User | 25 | All sections |
| Product Manager | 10 | Sections 1-3 (conceptual overview) |
Topics
| # | Topic | Key Concepts |
|---|---|---|
| 1 | Quick Start & Installation | Installation, first workflow, essential commands |
| 2 | Core Concepts | Context management, Plan Mode, interaction loop |
| 3 | Memory & Settings | CLAUDE.md, .claude/ folder, permissions |
| 4 | Agents | Custom agents, specialization, orchestration |
| 5 | Skills | Reusable knowledge, skill composition |
| 6 | Commands | Slash commands, custom commands |
| 7 | Hooks | Event system, security hooks, exit codes |
| 8 | MCP Servers | Context7, Serena, Sequential, plugins |
| 9 | Advanced Patterns | The Trinity, CI/CD, composition |
| 10 | Reference | Shortcuts, troubleshooting, daily workflow |
Quiz Flow
┌─────────────────────────────────────────────┐
│ CLAUDE CODE KNOWLEDGE QUIZ │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ Select Profile (Junior/Senior/Power/PM) │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ Select Topics (All or Specific 1-10) │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ Question 1/20 [Category] │
│ │
│ What is the recommended action when...? │
│ │
│ A) Option A │
│ B) Option B │
│ C) Option C │
│ D) Option D │
└─────────────────────────────────────────────┘
│
┌────────┴────────┐
▼ ▼
┌──────────┐ ┌──────────────────┐
│ CORRECT! │ │ INCORRECT │
│ │ │ Correct: C │
│ │ │ Explanation... │
│ │ │ See: guide#... │
└──────────┘ └──────────────────┘
│ │
└────────┬────────┘
▼
(Next Question)
│
▼
┌─────────────────────────────────────────────┐
│ QUIZ COMPLETE │
│ │
│ Overall Score: 16/20 (80%) │
│ │
│ By Category: │
│ Core Concepts: 6/7 (86%) [████████░░] │
│ Agents: 5/7 (71%) [███████░░░] │
│ Hooks: 5/6 (83%) [████████░░] │
│ │
│ Weak Areas: Agents (review section 4) │
└─────────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────┐
│ [R] Retry wrong questions only │
│ [N] New quiz (different questions) │
│ [E] Exit │
└─────────────────────────────────────────────┘
Session Persistence
Quiz sessions are automatically saved to ~/.claude-quiz/:
~/.claude-quiz/
sessions/
2026-01-12_143052.json # Individual session data
2026-01-12_150623.json
stats.json # Aggregate statistics
Session Data Includes:
- Profile and topics selected
- Questions answered (correct/incorrect/skipped)
- Time taken
- Category breakdown
- Wrong questions with correct answers
Dynamic Question Generation
When the --dynamic flag is enabled and the Claude CLI is installed, the quiz can generate additional questions on-the-fly using claude -p:
node src/index.js -d
This requires:
- Claude CLI installed (
npm install -g @anthropic-ai/claude-code) - Active API key configured
Dynamic questions supplement the static pool when:
- Static pool is exhausted for selected topics
- User requests fresh questions
- Variety is needed for repeated quizzes
Contributing Questions
We welcome question contributions! See templates/question-template.yaml for the format.
Quality Guidelines
Good questions test:
- Practical application ("When should you...")
- Decision-making ("Which approach is best for...")
- Understanding ("Why does Claude...")
- Troubleshooting ("What would you do if...")
Avoid:
- Trivia ("What is the exact command syntax...")
- Pure memorization ("List all keyboard shortcuts...")
- Version-specific details that may change
Submitting Questions
- Fork the repository
- Add questions to the appropriate
questions/XX-category.yamlfile - Follow the template format exactly
- Ensure
doc_referencepoints to valid sections - Submit a PR with description of added questions
Troubleshooting
"No questions available"
- Check that selected topics have questions in
questions/directory - Verify YAML files are valid (use a YAML validator)
- Try selecting different topics or "All topics"
"Cannot find module 'yaml'"
cd quiz
npm install
Quiz hangs on input
- Ensure you're running in an interactive terminal
- Try pressing Enter if stuck
- Use Ctrl+C to exit and restart
License
Same as parent repository: CC BY-SA 4.0
Part of: claude-code-ultimate-guide