cloudflare

Guides development across Cloudflare Workers, storage, AI, networking, and security products.

Updated Mar 25, 2026
One-click install
npx skills add https://github.com/lettucebo/Skills --skill cloudflare-lettucebo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cloudflare
Source: https://github.com/lettucebo/Skills/tree/main/skills/cloudflare/cloudflare
Command: npx skills add https://github.com/lettucebo/Skills --skill cloudflare-lettucebo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Choosing and correctly configuring the right Cloudflare product is difficult because the platform spans dozens of services with overlapping capabilities, and pre-trained knowledge of APIs, limits, and pricing is often outdated. This Skill routes any Cloudflare task to the right product reference and prioritizes retrieval from live Cloudflare docs over stale knowledge. ## Core Features & Use Cases - Decision trees for product selection: Route tasks like running code, storing data, AI inference, networking, security, media, analytics, and infrastructure-as-code to the correct Cloudflare product. - Deep per-product references: Progressive-disclosure reference files for Workers, Pages, D1, KV, R2, Durable Objects, Workers AI, Vectorize, Agents SDK, AI Gateway, WAF, DDoS, Turnstile, Terraform, Pulumi, and more. - Retrieval-first guidance: Directs the agent to fetch current docs, Wrangler config schemas, and Workers types before citing limits, pricing, or API signatures. - Use Case: When asked to build a RAG chatbot on Cloudflare, the Skill routes you to Workers AI for embeddings, Vectorize for the vector database, and AI Gateway for caching, with configuration and code patterns for each. ## Quick Start Ask the agent to help you build or configure any Cloudflare product, such as setting up a Worker with a D1 database, and it will load the relevant references and current documentation.

Frequently Asked Questions about cloudflare

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I choose between Cloudflare Workers, Pages, and Durable Objects?▼

Use Workers for serverless functions at the edge, Pages for full-stack web apps with Git deploys, and Durable Objects for stateful coordination or real-time workloads. The Skill's decision trees route each compute need to the right product with setup references.

What Cloudflare storage should I use for my application?▼

Use KV for key-value config and sessions, D1 for relational SQLite data, R2 for S3-compatible object storage, Queues for async messaging, and Vectorize for embeddings. Durable Objects storage fits strongly-consistent per-entity state.

How do I build a RAG application on Cloudflare?▼

Combine Workers AI for embeddings and LLM inference with Vectorize as the vector database, accessed through a Worker binding. Optionally add AI Gateway for caching, rate limiting, and analytics across AI providers.

Can I manage Cloudflare resources with Terraform or Pulumi?▼

Yes, the Skill includes references for the Cloudflare Terraform provider (v5) and Pulumi, covering provider setup, authentication with API tokens, resource configuration, and importing existing resources with cf-terraforming.

Why does the Skill prefer fetching Cloudflare docs over built-in knowledge?▼

Cloudflare limits, pricing, type signatures, and configuration options change frequently, so pre-trained knowledge is often outdated. The Skill directs retrieval from developers.cloudflare.com, Wrangler config schemas, and Workers types for accuracy.

When should I use Smart Placement for a Worker?▼

Enable Smart Placement when a Worker with a fetch handler makes multiple round trips to geographically concentrated backend infrastructure. Avoid it for static content, pure edge logic, or Workers without significant backend calls.