cloudflare

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

Updated Aug 2, 2026
One-click install
npx skills add https://github.com/leonardoacosta/agents --skill cloudflare-leonardoacosta
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cloudflare
Source: https://github.com/leonardoacosta/agents/tree/main/skills/cloudflare
Command: npx skills add https://github.com/leonardoacosta/agents --skill cloudflare-leonardoacosta

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Choosing and correctly configuring the right Cloudflare product is difficult across a catalog spanning compute, storage, AI, networking, and security, and stale knowledge of APIs, limits, and pricing causes broken implementations. This Skill routes any Cloudflare task to the correct product reference and enforces retrieval of live documentation over outdated pre-trained knowledge. ## Core Features & Use Cases - Decision Trees: Route tasks like running code, storing data, adding AI, or securing traffic to the right product (Workers, D1, R2, KV, Vectorize, WAF, Tunnel, and more). - Progressive References: Load per-product guides with configuration, API, patterns, and gotchas files so only task-relevant context is consumed. - Retrieval-First Guidance: Directs verification against Cloudflare docs, Wrangler config schemas, and Workers types before citing limits, pricing, or API signatures. - Use Case: When asked to add a serverless SQL database to a Worker, the Skill routes to the D1 reference, provides wrangler.jsonc binding setup, migration commands, and query patterns, then flags plan limits to verify against live docs. ## Quick Start Ask the agent to build or configure any Cloudflare feature, such as creating a Worker with a D1 database binding, and it will select the right product reference and walk you through setup.

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 based on whether you need compute, hosting, or strongly-consistent state.

What Cloudflare storage should I use for my application?

Use KV for high-read key-value data like config and sessions, D1 for relational SQL, R2 for S3-compatible object storage, and Durable Object storage for strongly-consistent per-entity state. The Skill provides a comparison table covering consistency, latency, and write limits.

Does Cloudflare D1 support read replicas and point-in-time recovery?

D1 supports read replicas on paid plans for lower-latency reads, with writes always going to the primary. Time Travel provides point-in-time recovery with 7-day retention on free plans and 30 days on paid plans.

When should I use Cloudflare Snippets instead of Workers?

Use Snippets for simple request or response modifications under 5ms CPU time and 32KB code size, included free on paid plans. Choose Workers when you need bindings like KV or D1, more than 5 subrequests, or complex application logic.

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

Cloudflare limits, pricing, API signatures, and configuration options change frequently, so pre-trained knowledge may be outdated. The Skill directs retrieval from developers.cloudflare.com, Wrangler config schemas, and Workers types before citing specific values.

Can I manage Cloudflare infrastructure with Terraform or Pulumi?

Yes, the Skill includes Terraform and Pulumi references covering provider setup, authentication, resource configuration, and state management. It notes Terraform provider v5 renamed many resources and recommends pinning versions and using remote state.