claude-cto-team

🥈Silver

Claude CTO Team provides AI-powered technical leadership for planning and executing projects. Operations teams benefit from automated technical guidance, roadmap development, and workflow optimization. Integrates with Claude Code and Python-based workflows.

82100Updated 1mo ago

Intermediate30min to implementautomation

Saves ~180 min per use

Quick InstallView Source

git clone https://github.com/alirezarezvani/claude-cto-team.git

Works with:

Claude

Overview

About This Skill

How to Use

1. **Define the Project Scope:** Clearly outline the project name, goals, constraints (e.g., budget, team size), and priority areas (e.g., scalability, security). Use bullet points for clarity. - *Tip:* Include specific metrics (e.g., "support 5,000 users") to guide the AI’s recommendations. 2. **Customize the Prompt:** Replace [PLACEHOLDERS] in the template with your project details. For example, swap [PROJECT_NAME] with "AI-Powered Customer Support Chatbot" and [TEAM_SIZE] with "5 engineers." - *Tip:* Mention existing tools (e.g., "currently using AWS") to ensure compatibility. 3. **Iterate with Feedback:** Review the AI’s output and refine the prompt. Ask follow-ups like: - "How would this architecture change if we used GCP instead of AWS?" - "Suggest a more cost-effective alternative for the data pipeline." - *Tip:* Use Claude Code to prototype parts of the architecture (e.g., FastAPI endpoints) and validate feasibility. 4. **Integrate into Workflows:** Use the roadmap and tech stack as a living document. Update it quarterly or after major milestones. - *Tip:* Share the output with stakeholders (e.g., engineers, product managers) to align expectations and gather input. 5. **Automate Repetitive Tasks:** For ongoing projects, create scripts to automate parts of the workflow. For example: - Use Python to generate Terraform templates from the proposed AWS resources. - Set up GitHub Actions to run security scans (e.g., Trivy) on the proposed tech stack. - *Tip:* Store the AI’s recommendations in a version-controlled repo (e.g., GitHub) for traceability.

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/alirezarezvani/claude-cto-team

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Act as the Claude CTO Team. Analyze the technical requirements for [PROJECT_NAME] and propose a high-level architecture, tech stack, and implementation roadmap. Include estimated timelines, potential risks, and mitigation strategies. Focus on scalability, security, and cost-efficiency. Assume the team has [TEAM_SIZE] engineers and [BUDGET_RANGE] budget. Suggest specific tools and frameworks (e.g., Python libraries, cloud services) that align with the project goals. Prioritize [PRIORITY_AREAS] and avoid [CONSTRAINTS].

Example Output

### Technical Leadership Proposal for 'EcoTrack Green Fleet Management'

**Project Overview:** EcoTrack is a SaaS platform enabling logistics companies to optimize fuel consumption and reduce carbon emissions by tracking vehicle performance, suggesting route adjustments, and generating sustainability reports. The MVP must support 1,000 concurrent users and integrate with third-party telematics devices (e.g., Geotab, Samsara).

**Proposed Architecture:**
- **Frontend:** React.js with TypeScript, hosted on Vercel. Uses D3.js for real-time fuel efficiency dashboards.
- **Backend:** FastAPI (Python) microservices deployed on AWS ECS with PostgreSQL for relational data (user accounts, fleet metadata) and MongoDB for time-series vehicle telemetry. Redis for caching frequent queries (e.g., route optimization results).
- **Data Pipeline:** Apache Kafka for ingesting telematics data, processed by PySpark for anomaly detection (e.g., sudden fuel spikes) before storage in MongoDB. Batch processing for monthly sustainability reports using AWS Glue.
- **DevOps:** Infrastructure as Code (Terraform) for AWS resources, GitHub Actions for CI/CD, and Prometheus/Grafana for monitoring. Cost-optimized with AWS Spot Instances for non-critical workloads.

**Tech Stack Rationale:**
- FastAPI was chosen for its async support (critical for real-time telematics ingestion) and Python’s rich ecosystem (e.g., Pandas for data analysis, Scikit-learn for predictive modeling).
- MongoDB’s flexible schema accommodates varying telematics device formats, while PostgreSQL ensures ACID compliance for financial transactions (e.g., subscription billing).
- Kafka decouples data producers (telematics devices) from consumers (analytics, dashboards), improving scalability.

**Roadmap (6 Months):**
- **Month 1-2 (MVP):** Core API (user/auth, fleet/vehicle CRUD), basic telematics ingestion, and a React dashboard showing live fuel efficiency metrics. Budget: $15K (AWS, Vercel, third-party APIs).
- **Month 3-4 (Scaling):** Add route optimization (using OR-Tools), anomaly detection (PyOD library), and initial integrations with Geotab/Samsara. Budget: $20K (additional AWS resources, external consultants).
- **Month 5-6 (Polish):** Multi-tenant support, automated sustainability reporting, and performance testing (Locust). Budget: $10K (optimization, security audits).

**Risks & Mitigations:**
1. **Telematics Integration Delays:** Risk of vendor API changes breaking integrations. Mitigation: Implement a circuit breaker pattern in FastAPI and mock third-party APIs during development.
2. **Cost Overruns:** Unpredictable AWS bills from high-volume data processing. Mitigation: Set up AWS Budgets alerts and use Lambda for sporadic workloads.
3. **Data Privacy:** Handling sensitive GPS/vehicle data. Mitigation: Encrypt data at rest (AWS KMS) and in transit (TLS 1.3), and implement role-based access control (RBAC) in PostgreSQL.

**Recommended Tools:**
- **Local Development:** Docker Compose for PostgreSQL/MongoDB, FastAPI’s auto-reload for backend, and Storybook for React components.
- **Testing:** Pytest for backend unit tests, Cypress for E2E frontend tests, and Locust for load testing.
- **Monitoring:** AWS CloudWatch for logs, Sentry for error tracking, and Grafana for dashboards.

**Next Steps:**
1. Validate the architecture with a proof-of-concept (PoC) focusing on telematics ingestion and basic dashboards.
2. Prioritize security reviews (OWASP Top 10) before Month 3.
3. Allocate 20% of Month 4 budget for performance tuning based on PoC results.