scriptoriumadmin/claude-skills
1
0
Fork 0
mirror of https://github.com/alirezarezvani/claude-skills.git synced 2026-10-06 02:50:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
claude-skills/engineering-team/TEAM_STRUCTURE_GUIDE.md
Ben Fairless 66ea9621dd
fix(models): remove retired model IDs and stale pricing, flip G7 blocking 
Clears every reference the new G7 lint flags, then makes it blocking so the
class cannot drift back. audit/engineering-agentic-2026-07 marked the
senior-ml-engineer half of this STILL-OPEN.

Deleted rather than updated:

  - agent-designer/agent_evaluator.py's _define_cost_benchmarks() held
    per-token prices for gpt-4, gpt-3.5-turbo and claude-3 at 2024 rates. The
    result was assigned to self.cost_benchmarks and never read by anything, so
    the method is gone. Cost analysis uses the cost_usd the caller supplies per
    execution log, which is the only figure that can be accurate

Made model-agnostic, following the precedent already set by
senior-prompt-engineer/scripts/prompt_optimizer.py's --price-per-mtok:

  - senior-ml-engineer SKILL.md and llm_integration_guide.md drop both 2024
    price tables and the context-window table (which claimed GPT-4 = 8,192).
    calculate_cost() takes rates as parameters; count_tokens() takes an
    encoding name, since encodings outlive model IDs and
    encoding_for_model() raises KeyError on anything unmapped
  - OpenAIProvider loses its default model, so the caller must pass one
  - llm-cost-optimizer's routing table names tiers, not models

Pinned to current IDs where an example genuinely needs one: SKILL_PIPELINE.md
(claude-opus-4-6 -> claude-opus-5), prompt-governance (claude-sonnet-4-5 ->
claude-sonnet-5), agent-designer README. Both dual-publish copies of the CAIO
pricing move together, so G4 stays green.

TEAM_STRUCTURE_GUIDE.md documented `prompt_optimizer.py --model gpt-4 --task
classification`. That contract no longer exists: there is no --task flag and
`prompt` is a required positional. Replaced with a runnable invocation.

Four references stay, with reasons in the allowlist: two litreview examples
where the retired model is the subject of the literature being reviewed, one
dated Computer Use citation, and the embedding benchmark already labelled a
2024 snapshot.

Assisted-by: Claude Code:claude-opus-5
2026-08-03 08:55:36 +08:00

629 lines
15 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# 🚀 World-Class Engineering & AI/ML/Data Team Skills
Complete set of **14 senior-level skills** for building exceptional engineering and AI/data teams.
---
## 🎯 **Complete Team Structure**
### **Engineering Team (9 Roles)**
| Role | Skill Package | Primary Focus |
|------|---------------|---------------|
| **Senior Software Architect** | `skills/senior-architect/` | System design, architecture decisions, tech stack |
| **Senior Frontend Engineer** | `skills/senior-frontend/` | React, Next.js, UI/UX, performance |
| **Senior Backend Engineer** | `skills/senior-backend/` | APIs, databases, business logic |
| **Senior Fullstack Engineer** | `skills/senior-fullstack/` | End-to-end development |
| **Senior QA/Test Engineer** | `skills/senior-qa/` | Quality assurance, test automation |
| **Senior DevOps Engineer** | `skills/senior-devops/` | CI/CD, infrastructure, deployment |
| **Senior SecOps Engineer** | `skills/senior-secops/` | Security operations, compliance |
| **Code Reviewer** | `skills/code-reviewer/` | Code quality, standards, reviews |
| **Senior Security Engineer** | `skills/senior-security/` | Security architecture, pentesting |
### **AI/ML/Data Team (5 Roles)**
| Role | Skill Package | Primary Focus |
|------|---------------|---------------|
| **Senior Data Scientist** | `skills/senior-data-scientist/` | Statistical modeling, experimentation, analytics |
| **Senior Data Engineer** | `skills/senior-data-engineer/` | Data pipelines, ETL, data infrastructure |
| **Senior ML/AI Engineer** | `skills/senior-ml-engineer/` | MLOps, model deployment, LLM integration |
| **Senior Prompt Engineer** | `skills/senior-prompt-engineer/` | LLM optimization, RAG, agentic AI |
| **Senior Computer Vision Engineer** | `skills/senior-computer-vision/` | Image/video AI, object detection, vision systems |
---
## 🏗️ **Recommended Team Compositions**
### **Startup Team (5-10 people)**
**Minimum Viable Team:**
1. **Senior Fullstack Engineer** (×2) - Build everything
2. **Senior Data Scientist** - Analytics & insights
3. **Senior DevOps Engineer** - Deploy & scale
4. **Senior ML Engineer** - AI/ML features
**Why this works:**
- Fullstack engineers handle frontend & backend
- Data scientist provides insights
- DevOps ensures reliability
- ML engineer adds AI capabilities
---
### **Scale-Up Team (10-25 people)**
**Growing Team:**
1. **Senior Architect** (×1) - System design & tech strategy
2. **Senior Frontend Engineer** (×2) - User experience
3. **Senior Backend Engineer** (×3) - APIs & business logic
4. **Senior Data Engineer** (×2) - Data infrastructure
5. **Senior Data Scientist** (×2) - Analytics & modeling
6. **Senior ML Engineer** (×2) - ML in production
7. **Senior QA Engineer** (×1) - Quality assurance
8. **Senior DevOps Engineer** (×1) - Infrastructure
9. **Senior SecOps Engineer** (×1) - Security
**Why this works:**
- Clear separation of concerns
- Specialized expertise
- Dedicated quality & security
- Scalable data infrastructure
---
### **Enterprise Team (25-50+ people)**
**Complete Team:**
**Engineering:**
1. **Senior Architect** (×2) - System & solution architecture
2. **Senior Frontend Engineer** (×4-6) - Web & mobile UI
3. **Senior Backend Engineer** (×6-8) - Microservices
4. **Senior Fullstack Engineer** (×2-3) - Rapid prototyping
5. **Senior QA Engineer** (×3-4) - Test automation
6. **Senior DevOps Engineer** (×3-4) - Platform engineering
7. **Senior SecOps Engineer** (×2) - Security operations
8. **Senior Security Engineer** (×2) - Security architecture
9. **Code Reviewer** (×2) - Quality gatekeeping
**AI/ML/Data:**
1. **Senior Data Scientist** (×4-6) - Experimentation & modeling
2. **Senior Data Engineer** (×4-6) - Data platform
3. **Senior ML Engineer** (×4-6) - ML platform & deployment
4. **Senior Prompt Engineer** (×2-3) - LLM optimization
5. **Senior Computer Vision Engineer** (×2-3) - Vision AI
**Why this works:**
- Multiple teams per domain
- Deep specialization
- Redundancy for reliability
- Research & innovation capacity
---
## 💡 **Skill Selection Guide**
### **When to Use Each Skill**
#### **System Design & Architecture**
→ Use `skills/senior-architect/`
- Designing new systems
- Making tech stack decisions
- Creating architecture diagrams
- Evaluating trade-offs
#### **Frontend Development**
→ Use `skills/senior-frontend/`
- Building React/Next.js apps
- UI/UX implementation
- Performance optimization
- State management
#### **Backend Development**
→ Use `skills/senior-backend/`
- Designing APIs (REST/GraphQL)
- Database optimization
- Authentication/authorization
- Microservices
#### **Full-Stack Development**
→ Use `skills/senior-fullstack/`
- Building complete features
- Rapid prototyping
- Startup MVP development
- Code quality analysis
#### **Testing & QA**
→ Use `skills/senior-qa/`
- Test strategy design
- Test automation
- Coverage analysis
- Quality metrics
#### **DevOps & Infrastructure**
→ Use `skills/senior-devops/`
- CI/CD pipelines
- Infrastructure as code
- Deployment automation
- Container orchestration
#### **Security Operations**
→ Use `skills/senior-secops/`
- Security scanning
- Vulnerability management
- Compliance checking
- Incident response
#### **Code Reviews**
→ Use `skills/code-reviewer/`
- PR reviews
- Code quality checks
- Standards enforcement
- Mentoring feedback
#### **Security Architecture**
→ Use `skills/senior-security/`
- Security design
- Penetration testing
- Threat modeling
- Cryptography
#### **Data Science**
→ Use `skills/senior-data-scientist/`
- Statistical modeling
- A/B testing
- Causal inference
- Feature engineering
- Business analytics
#### **Data Engineering**
→ Use `skills/senior-data-engineer/`
- Data pipelines
- ETL/ELT design
- Data modeling
- Data quality
- Stream processing
#### **ML/AI Engineering**
→ Use `skills/senior-ml-engineer/`
- Model deployment
- MLOps
- LLM integration
- RAG systems
- Model monitoring
#### **Prompt Engineering**
→ Use `skills/senior-prompt-engineer/`
- LLM optimization
- Prompt patterns
- Agent design
- RAG optimization
- AI evaluation
#### **Computer Vision**
→ Use `skills/senior-computer-vision/`
- Object detection
- Image segmentation
- Video analysis
- Vision models
- Real-time inference
---
## 🎓 **Tech Stack Coverage**
### **Engineering Stack**
**Frontend:**
- React 18+
- Next.js 14+ (App Router)
- TypeScript
- Tailwind CSS
- React Native
- Flutter
- Swift (iOS)
- Kotlin (Android)
**Backend:**
- Node.js + Express
- GraphQL (Apollo)
- Go (Gin/Echo)
- Python (FastAPI)
- PostgreSQL
- Prisma ORM
**Infrastructure:**
- Docker
- Kubernetes
- Terraform
- AWS/GCP/Azure
- GitHub Actions
- CircleCI
### **AI/ML/Data Stack**
**Data Processing:**
- Python
- SQL
- Spark
- Airflow
- dbt
- Kafka
- Databricks
**ML Frameworks:**
- PyTorch
- TensorFlow
- Scikit-learn
- XGBoost
- Transformers
- LangChain
- LlamaIndex
**MLOps:**
- MLflow
- Weights & Biases
- Kubeflow
- SageMaker
- Vertex AI
**Data Storage:**
- PostgreSQL
- Snowflake
- BigQuery
- Redshift
- Pinecone (vector DB)
- Redis
**Computer Vision:**
- OpenCV
- YOLO
- Segment Anything (SAM)
- CLIP
- Stable Diffusion
---
## 🚀 **Quick Start Guide**
### **1. Choose Your Team Size**
- **Startup (< 10)**: Fullstack + Data + ML + DevOps
- **Scale-up (10-25)**: Add specialists (Frontend, Backend, Data Eng)
- **Enterprise (25+)**: Complete teams with redundancy
### **2. Pick Relevant Skills**
Each skill lives in this repo under `skills/<name>/` — use it in place or copy the folder.
### **3. Extract and Explore**
```bash
# Open a skill folder
cd skills/senior-ml-engineer
# Read the documentation
cat SKILL.md
# Check reference guides
ls references/
# Try the scripts
python scripts/model_deployment_pipeline.py --help
```
### **4. Customize for Your Needs**
Each skill is a starting point:
- Update scripts for your workflows
- Add your patterns to references
- Customize for your tech stack
- Share learnings with team
---
## 🔄 **Workflow Examples**
### **Workflow 1: New AI Product Feature**
```bash
# 1. Design system architecture
cd senior-architect
python scripts/architecture_diagram_generator.py --type system --output docs/
# 2. Build data pipeline
cd ../senior-data-engineer
python scripts/pipeline_orchestrator.py --input raw/ --output processed/
# 3. Train ML model
cd ../senior-ml-engineer
python scripts/model_deployment_pipeline.py --train --config model_config.yaml
# 4. Optimize prompts
cd ../senior-prompt-engineer
python scripts/prompt_optimizer.py classification_prompt.txt --analyze --model claude
# 5. Deploy with DevOps
cd ../senior-devops
python scripts/deployment_manager.py --service ml-api --environment production
```
### **Workflow 2: Complete Application Development**
```bash
# 1. Architecture design
cd senior-architect
python scripts/project_architect.py my-app --pattern microservices
# 2. Backend API
cd ../senior-backend
python scripts/api_scaffolder.py my-app-api --type graphql
# 3. Frontend
cd ../senior-frontend
python scripts/frontend_scaffolder.py my-app-web --framework nextjs
# 4. Testing
cd ../senior-qa
python scripts/test_suite_generator.py ../my-app --coverage
# 5. CI/CD
cd ../senior-devops
python scripts/pipeline_generator.py my-app --platform github
```
### **Workflow 3: Data Science Project**
```bash
# 1. Design experiment
cd senior-data-scientist
python scripts/experiment_designer.py --hypothesis "feature X improves conversion" --power 0.8
# 2. Feature engineering
python scripts/feature_engineering_pipeline.py --input data/raw --output data/features
# 3. Build data pipeline
cd ../senior-data-engineer
python scripts/pipeline_orchestrator.py --schedule daily --destination warehouse
# 4. Deploy model
cd ../senior-ml-engineer
python scripts/model_deployment_pipeline.py --model ./models/best.pkl --endpoint /api/predict
```
---
## 📊 **Senior-Level Expectations**
Each skill embodies world-class senior-level practices:
### **Technical Excellence**
- Production-grade code quality
- Scalable architecture design
- Performance optimization
- Security best practices
- Comprehensive testing
### **Leadership**
- Mentor junior engineers
- Drive technical decisions
- Establish coding standards
- Code review excellence
- Knowledge sharing
### **Strategic Thinking**
- Align with business goals
- Evaluate trade-offs
- Plan for scale
- Manage technical debt
- Innovation mindset
### **Collaboration**
- Cross-functional teamwork
- Stakeholder communication
- Consensus building
- Documentation
- Remote-friendly practices
### **Production Operations**
- High availability (99.9%+)
- Monitoring & alerting
- Incident response
- Performance optimization
- Cost optimization
---
## 🎯 **Performance Benchmarks**
### **System Performance**
**Latency Targets:**
- P50: < 50ms
- P95: < 100ms
- P99: < 200ms
- P99.9: < 500ms
**Throughput Targets:**
- Requests/second: > 1,000
- Concurrent users: > 10,000
- Data processed: > 1TB/day
**Availability:**
- Uptime: 99.9%
- Error rate: < 0.1%
- MTTR: < 15 minutes
### **ML/AI Performance**
**Model Metrics:**
- Training time: Optimized
- Inference latency: < 100ms P95
- Accuracy: Domain-specific targets
- Drift detection: < 24 hours
**Data Quality:**
- Completeness: > 99%
- Accuracy: > 99.5%
- Timeliness: Real-time to daily
- Consistency: Validated
---
## 🛡️ **Security & Compliance**
All skills include:
- **Authentication & Authorization**: OAuth2, OIDC, RBAC
- **Data Protection**: Encryption at rest & in transit
- **Privacy**: PII handling, GDPR/CCPA compliance
- **Vulnerability Management**: Regular scanning & patching
- **Audit Logging**: Comprehensive activity tracking
- **Security Testing**: Penetration testing, SAST, DAST
---
## 📚 **Continuous Learning**
### **Staying Current**
Each skill encourages:
- Reading research papers
- Following industry blogs
- Attending conferences
- Contributing to open source
- Experimenting with new tech
- Sharing knowledge
### **Knowledge Sharing**
- Tech talks & demos
- Documentation
- Code reviews as learning
- Pair programming
- Mentoring sessions
---
## 🔧 **Customization Guide**
### **Adapting Skills**
1. **Update Scripts**
- Add company-specific logic
- Integrate with your tools
- Customize templates
- Add validation rules
2. **Enhance References**
- Add your patterns
- Document decisions
- Include examples
- Share lessons learned
3. **Team Standards**
- Coding conventions
- Git workflow
- Review process
- Deployment procedures
---
## 💼 **Hiring & Team Building**
### **Using Skills for Hiring**
1. **Job Descriptions**: Use skill requirements
2. **Technical Interviews**: Assess skill areas
3. **Code Challenges**: Based on skill patterns
4. **Onboarding**: Skills as training material
### **Team Development**
1. **Skill Gaps**: Identify and address
2. **Training Plans**: Based on skill content
3. **Mentorship**: Use patterns and practices
4. **Career Paths**: Senior → Lead → Principal
---
## 📈 **Success Metrics**
### **Engineering Metrics**
- **Velocity**: Story points/sprint
- **Quality**: Defect rate, test coverage
- **Reliability**: Uptime, MTTR
- **Performance**: Latency, throughput
- **Security**: Vulnerabilities, incidents
### **AI/ML Metrics**
- **Model Performance**: Accuracy, precision, recall
- **Data Quality**: Completeness, accuracy
- **Pipeline Reliability**: Success rate, latency
- **Business Impact**: Revenue, engagement, conversion
- **Cost Efficiency**: $/prediction, resource usage
---
## 🎉 **Summary**
You now have **14 world-class skills** covering:
### **Engineering (9 Skills)**
✅ Architecture & Design
✅ Frontend & Backend Development
✅ Full-Stack Development
✅ Quality Assurance & Testing
✅ DevOps & Infrastructure
✅ Security Operations & Engineering
✅ Code Review & Standards
### **AI/ML/Data (5 Skills)**
✅ Data Science & Analytics
✅ Data Engineering & Pipelines
✅ ML/AI Engineering & MLOps
✅ Prompt Engineering & LLMs
✅ Computer Vision & Visual AI
Each skill includes:
- **Comprehensive SKILL.md** with quick start
- **3 reference guides** with advanced patterns
- **3 production-grade scripts** for automation
- **World-class practices** from industry leaders
- **Senior-level expectations** and responsibilities
---
## 🚀 **Next Steps**
1. **Review team structure** recommendations
2. **Download skills** matching your team size
3. **Extract and explore** SKILL.md files
4. **Customize scripts** for your workflows
5. **Integrate into** development process
6. **Share with team** and iterate
---
## 💡 **Key Principles**
Remember these core principles:
1. **Production First**: Always design for production
2. **Quality Always**: Never compromise on quality
3. **Security Built-In**: Security is not optional
4. **Performance Matters**: Optimize intelligently
5. **Collaborate**: Work across teams
6. **Mentor**: Share knowledge generously
7. **Innovate**: Stay current and experiment
8. **Document**: Write it down
9. **Automate**: Eliminate toil
10. **Measure**: You can't improve what you don't measure
---
**Build World-Class Teams! 🎯**
These skills are your foundation for engineering and AI/ML excellence. Use them to build, grow, and scale exceptional teams that deliver outstanding products.
Reference in a new issue View git blame Copy permalink