marketing-shibata50/claude-code-ultimate-guide
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docs: reference ai-ecosystem.md everywhere + add quiz questions

Browse source 
- Add AI Ecosystem to README.md Core Documentation table
- Create quiz/questions/15-ai-ecosystem.yaml (10 questions)
- Update question count: 217 → 227

Topics covered: Perplexity, Gemini, Kimi, NotebookLM, v0.dev,
workflow orchestration, cost optimization

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Florian BRUNIAUX 2026-01-19 13:04:07 +01:00
parent 001310bf67
commit dd833bcc07
2 changed files with 286 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

9
README.md
View file

@ -8,7 +8,7 @@
<a href="https://github.com/FlorianBruniaux/claude-code-ultimate-guide/stargazers"><img src="https://img.shields.io/github/stars/FlorianBruniaux/claude-code-ultimate-guide?style=for-the-badge" alt="Stars"/></a>
<a href="#"><img src="https://img.shields.io/badge/Lines-10,500+-blueviolet?style=for-the-badge" alt="Lines"/></a>
<a href="./examples/"><img src="https://img.shields.io/badge/Templates-63-green?style=for-the-badge" alt="Templates"/></a>
<a href="./quiz/"><img src="https://img.shields.io/badge/Quiz-217_questions-orange?style=for-the-badge" alt="Quiz"/></a>
<a href="./quiz/"><img src="https://img.shields.io/badge/Quiz-227_questions-orange?style=for-the-badge" alt="Quiz"/></a>
</p>
<p align="center">
@ -244,7 +244,7 @@ Based on ALL this context, provide:
### 🧠 Knowledge Quiz
Test your Claude Code knowledge with an interactive CLI quiz. **217 curated questions** covering all 14 guide sections, with immediate feedback and documentation links.
Test your Claude Code knowledge with an interactive CLI quiz. **227 curated questions** covering all 14 guide sections, with immediate feedback and documentation links.
```bash
# Quick start
@ -397,6 +397,7 @@ Weak Areas (< 75%):
| **[Data Privacy](./guide/data-privacy.md)** | Data retention and privacy guide | ~10 minutes |
| **[Security Hardening](./guide/security-hardening.md)** | MCP vetting, injection defense, CVEs | ~25 minutes |
| **[Observability](./guide/observability.md)** | Session monitoring and cost tracking | ~15 minutes |
| **[AI Ecosystem](./guide/ai-ecosystem.md)** | Complementary tools (Perplexity, Gemini, Kimi) | ~25 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 |
@ -477,7 +478,7 @@ claude-code-ultimate-guide/
│ ├── ...
│ └── 07-guide-reference.qmd
│
└── quiz/ # 🧠 Interactive knowledge quiz (217 questions)
└── quiz/ # 🧠 Interactive knowledge quiz (227 questions)
```
---
@ -677,7 +678,7 @@ Found an error? Have a suggestion? See [CONTRIBUTING.md](./CONTRIBUTING.md) for
| **Content** | Aggregated | Aggregated | Original |
| **Architecture docs** | ❌ | ❌ | ✅ Unique |
| **Methodologies (TDD/SDD)** | ❌ | ❌ | ✅ Unique |
| **Interactive quiz** | ❌ | ❌ | ✅ 217 questions |
| **Interactive quiz** | ❌ | ❌ | ✅ 227 questions |
| **Machine-readable index** | ❌ | ❌ | ✅ YAML with line numbers |
**Recommended path**:

281
quiz/questions/15-ai-ecosystem.yaml Normal file
View file

@ -0,0 +1,281 @@
category: "AI Ecosystem"
category_id: 15
source_file: "guide/ai-ecosystem.md"
questions:
- id: "15-001"
difficulty: "junior"
profiles: ["junior", "senior", "power"]
question: "What is the main philosophy behind using complementary AI tools with Claude Code?"
options:
a: "Replace Claude Code with better tools"
b: "Augmentation, not replacement - chain the right tool for each step"
c: "Use as many tools as possible simultaneously"
d: "Avoid using Claude Code for coding tasks"
correct: "b"
explanation: |
The philosophy is "augmentation, not replacement."
Claude Code excels at contextual reasoning and implementation, but has gaps:
- No real-time web search with source verification
- No image generation
- No PowerPoint/slide generation
- No audio synthesis
The goal is to chain the right tool for each step of your workflow.
doc_reference:
file: "guide/ai-ecosystem.md"
section: "Introduction"
anchor: "#introduction"
- id: "15-002"
difficulty: "junior"
profiles: ["junior", "senior", "power"]
question: "When should you use Perplexity instead of Claude Code?"
options:
a: "When implementing features in your codebase"
b: "When you need deep research with 100+ verified sources"
c: "When editing multiple files"
d: "When running tests"
correct: "b"
explanation: |
Perplexity excels at research with verified sources.
Use Perplexity for:
- "What's the latest API for X?" (real-time info)
- "Compare 5 libraries for auth" (sourced comparisons)
- Deep Research mode synthesizes 100+ sources
Use Claude Code for:
- Implementation in your codebase
- Contextual code explanation
- Multi-file editing
doc_reference:
file: "guide/ai-ecosystem.md"
section: "1. Perplexity AI"
anchor: "#1-perplexity-ai-research--sourcing"
- id: "15-003"
difficulty: "senior"
profiles: ["senior", "power"]
question: "What is the recommended Research-to-Code pipeline?"
options:
a: "Claude Code -> Perplexity -> Implementation"
b: "Perplexity Deep Research -> Export spec.md -> Claude Code implements"
c: "Google Search -> Copy code -> Paste in project"
d: "Ask Claude Code to search the web first"
correct: "b"
explanation: |
The Research-to-Code pipeline:
1. PERPLEXITY (Deep Research)
- Research best practices with sources
- Output: 2000-word spec with citations
2. Export as spec.md
3. CLAUDE CODE
- "Implement following spec.md"
- Output: Working implementation with tests
This ensures implementation is based on verified, current information.
doc_reference:
file: "guide/ai-ecosystem.md"
section: "Integration Workflow"
anchor: "#integration-workflow"
- id: "15-004"
difficulty: "senior"
profiles: ["senior", "power"]
question: "Which tool is best for converting a UI screenshot to React code?"
options:
a: "Perplexity"
b: "Claude Code directly"
c: "Gemini 2.5 Pro -> then Claude Code for refinement"
d: "NotebookLM"
correct: "c"
explanation: |
Gemini 2.5 Pro excels at visual understanding:
Visual-to-Code Pipeline:
1. GEMINI: Upload screenshot -> Get JSX + Tailwind (90%+ fidelity)
2. CLAUDE CODE: Refine for your project
- Add TypeScript types
- Connect to your components
- Integrate with your state management
Claude Code alone has limited image understanding compared to Gemini.
doc_reference:
file: "guide/ai-ecosystem.md"
section: "2. Google Gemini"
anchor: "#2-google-gemini-visual-understanding"
- id: "15-005"
difficulty: "junior"
profiles: ["junior", "senior", "power"]
question: "Which tool should you use to create PowerPoint presentations from code documentation?"
options:
a: "Claude Code"
b: "Perplexity"
c: "Kimi (Moonshot AI)"
d: "Gemini"
correct: "c"
explanation: |
Kimi (kimi.ai) from Moonshot AI specializes in PPTX generation:
Features:
- Native PPTX export (actual slides, not markdown)
- 128K+ token context (entire codebases)
- Code-aware layouts with syntax highlighting
- Excellent for stakeholder decks from technical content
Workflow: Claude Code generates summary -> Kimi creates presentation
doc_reference:
file: "guide/ai-ecosystem.md"
section: "3. Kimi"
anchor: "#3-kimi-pptx--long-document-generation"
- id: "15-006"
difficulty: "senior"
profiles: ["senior", "power"]
question: "What is NotebookLM's unique feature for developer onboarding?"
options:
a: "Code execution"
b: "Audio Overview - generates podcast-style explanations from docs"
c: "Real-time collaboration"
d: "Git integration"
correct: "b"
explanation: |
NotebookLM's Audio Overview feature:
- Upload 50+ documentation files
- Generates 10-15 minute "podcast"
- Two AI hosts discuss your codebase
- Perfect for onboarding or reviewing large systems
Workflow:
1. Export docs to combined-docs.md
2. Upload to NotebookLM
3. Generate Audio Overview
4. Listen during commute
5. Return to Claude Code with deeper understanding
doc_reference:
file: "guide/ai-ecosystem.md"
section: "4. NotebookLM"
anchor: "#4-notebooklm-synthesis--audio"
- id: "15-007"
difficulty: "power"
profiles: ["power"]
question: "In the complete workflow pipeline, what is the correct order of phases?"
options:
a: "Implementation -> Planning -> Delivery"
b: "Planning (Perplexity/Gemini/NotebookLM) -> Implementation (Claude Code) -> Delivery (Kimi)"
c: "Delivery -> Planning -> Implementation"
d: "All tools simultaneously"
correct: "b"
explanation: |
The complete pipeline has 3 phases:
PLANNING PHASE:
- Perplexity: Deep Research -> spec.md
- Gemini: Diagram Analysis -> mermaid + plan
- NotebookLM: Doc Synthesis -> audio overview
IMPLEMENTATION PHASE:
- Claude Code: Multi-file implementation
- IDE + Copilot: Inline autocomplete
DELIVERY PHASE:
- Claude Code: PR description, release notes
- Kimi: Stakeholder deck (presentation.pptx)
doc_reference:
file: "guide/ai-ecosystem.md"
section: "7. Workflow Orchestration"
anchor: "#7-workflow-orchestration"
- id: "15-008"
difficulty: "junior"
profiles: ["junior", "senior", "power"]
question: "What is v0.dev best used for in the AI ecosystem?"
options:
a: "Backend API development"
b: "Database queries"
c: "Rapid UI prototyping with Shadcn/Tailwind"
d: "Security auditing"
correct: "c"
explanation: |
v0.dev excels at rapid UI prototyping:
- Generates React + Shadcn + Tailwind components
- Live preview in browser
- Quick iteration on UI designs
Workflow:
1. v0: Prompt -> Get component preview
2. Export code
3. Claude Code: Adapt for your project
- Add TypeScript types
- Connect to your APIs
- Integrate with your design system
doc_reference:
file: "guide/ai-ecosystem.md"
section: "6. UI Prototypers"
anchor: "#6-ui-prototypers-v0-bolt-lovable"
- id: "15-009"
difficulty: "senior"
profiles: ["senior", "power"]
question: "How does Claude WebSearch compare to Perplexity Pro for research?"
options:
a: "Claude WebSearch has more sources (100+)"
b: "They are identical in functionality"
c: "Claude WebSearch: 5-10 sources, quick lookups. Perplexity Pro: 100+ sources, comprehensive research"
d: "Perplexity cannot access real-time data"
correct: "c"
explanation: |
Comparison:
| Feature | Claude WebSearch | Perplexity Pro |
|---------|-----------------|----------------|
| Source count | ~5-10 | 100+ (Deep Research) |
| Source verification | Basic | Full citations |
| Best for | Quick lookups | Comprehensive research |
| Cost | Included | $20/month |
Recommendation: Use Claude WebSearch for quick factual checks.
Use Perplexity Deep Research before significant implementations.
doc_reference:
file: "guide/ai-ecosystem.md"
section: "Comparison"
anchor: "#comparison-claude-websearch-vs-perplexity"
- id: "15-010"
difficulty: "power"
profiles: ["power"]
question: "What is the 'Minimal Stack' monthly cost recommendation for AI tools?"
options:
a: "$200+/month - all Pro subscriptions"
b: "$40-70/month - Claude Code + Perplexity Pro, free tiers for rest"
c: "$0 - only free tiers"
d: "$500+/month - enterprise plans"
correct: "b"
explanation: |
Recommended subscription stacks:
Minimal Stack ($40-70/month):
- Claude Code (pay-per-use): $20-50
- Perplexity Pro: $20
- Everything else: Free tiers (NotebookLM, Kimi, Gemini free)
Balanced Stack ($80-110/month):
- Add Gemini Advanced ($20) and Cursor Pro ($20)
Cost optimization tips:
- Use Haiku for simple tasks
- Batch research sessions in Perplexity
- Check context usage regularly (/status)
doc_reference:
file: "guide/ai-ecosystem.md"
section: "8. Cost & Subscription Strategy"
anchor: "#8-cost--subscription-strategy"