Skip to content
Development
Skill

/cloudflare

Build and deploy on Cloudflare's edge platform. Use when creating Workers, Pages, D1 databases, R2 storage, AI inference, or KV storage. Triggers on Cloudflare, Workers, Cloudflare Pages, D1, R2, KV, Cloudflare AI, Durable Objects, edge computing.

From plugin
ai-agents-skills
28039 skills
Install
$ npx -y skills add hoodini/ai-agents-skills --skill cloudflare --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/cloudflare

Context preview

The summary Claude sees to decide when to auto-load this skill.

Build and deploy on Cloudflare's edge platform. Use when creating Workers, Pages, D1 databases, R2 storage, AI inference, or KV storage. Triggers on Cloudflare, Workers, Cloudflare Pages, D1, R2, KV, Cloudflare AI, Durable Objects, edge computing.

SKILL.md

cloudflare.SKILL.md
name: cloudflare
description: Build and deploy on Cloudflare's edge platform. Use when creating Workers, Pages, D1 databases, R2 storage, AI inference, or KV storage. Triggers on Cloudflare, Workers, Cloudflare Pages, D1, R2, KV, Cloudflare AI, Durable Objects, edge computing.

Cloudflare Platform

Build globally distributed applications on Cloudflare's edge network.

Quick Start

# Install Wrangler CLI
npm install -g wrangler

# Login
wrangler login

# Create new Worker
wrangler init my-worker

# Deploy
wrangler deploy

Workers

Basic Worker

// src/index.ts
export default {
  async fetch(request: Request, env: Env, ctx: ExecutionContext): Promise<Response> {
    const url = new URL(request.url);
    
    if (url.pathname === '/api/hello') {
      return Response.json({ message: 'Hello from the edge!' });
    }
    
    return new Response('Not Found', { status: 404 });
  },
};

wrangler.toml Configuration

name = "my-worker"
main = "src/index.ts"
compatibility_date = "2024-01-01"

[vars]
ENVIRONMENT = "production"

# KV Namespace
[[kv_namespaces]]
binding = "MY_KV"
id = "abc123"

# D1 Database
[[d1_databases]]
binding = "DB"
database_name = "my-database"
database_id = "def456"

# R2 Bucket
[[r2_buckets]]
binding = "BUCKET"
bucket_name = "my-bucket"

# AI
[ai]
binding = "AI"

# Durable Objects
[[durable_objects.bindings]]
name = "COUNTER"
class_name = "Counter"

[[migrations]]
tag = "v1"
new_classes = ["Counter"]

Request Routing

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const url = new URL(request.url);
    const { pathname } = url;
    
    // Router pattern
    const routes: Record<string, () => Promise<Response>> = {
      '/api/users': () => handleUsers(request, env),
      '/api/posts': () => handlePosts(request, env),
    };
    
    const handler = routes[pathname];
    if (handler) {
      return handler();
    }
    
    // Wildcard matching
    if (pathname.startsWith('/api/users/')) {
      const userId = pathname.split('/')[3];
      return handleUser(userId, request, env);
    }
    
    return new Response('Not Found', { status: 404 });
  },
};

KV Storage

interface Env {
  MY_KV: KVNamespace;
}

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const url = new URL(request.url);
    
    // Set value
    await env.MY_KV.put('key', 'value', {
      expirationTtl: 3600, // 1 hour
      metadata: { created: Date.now() },
    });
    
    // Get value
    const value = await env.MY_KV.get('key');
    
    // Get with metadata
    const { value: data, metadata } = await env.MY_KV.getWithMetadata('key');
    
    // List keys
    const list = await env.MY_KV.list({ prefix: 'user:' });
    
    // Delete
    await env.MY_KV.delete('key');
    
    return Response.json({ value });
  },
};

D1 Database (SQLite)

interface Env {
  DB: D1Database;
}

// Create tables (run once via wrangler d1 execute)
// wrangler d1 execute my-database --file=./schema.sql

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    // Query
    const { results } = await env.DB.prepare(
      'SELECT * FROM users WHERE id = ?'
    ).bind(1).all();
    
    // Insert
    const { meta } = await env.DB.prepare(
      'INSERT INTO users (name, email) VALUES (?, ?)'
    ).bind('Alice', 'alice@example.com').run();
    
    // Batch operations
    const batch = await env.DB.batch([
      env.DB.prepare('INSERT INTO logs (action) VALUES (?)').bind('login'),
      env.DB.prepare('UPDATE users SET last_login = ? WHERE id = ?').bind(Date.now(), 1),
    ]);
    
    // First result only
    const user = await env.DB.prepare(
      'SELECT * FROM users WHERE email = ?'
    ).bind('alice@example.com').first();
    
    return Response.json({ results, insertId: meta.last_row_id });
  },
};

Schema Example

-- schema.sql
CREATE TABLE IF NOT EXISTS users (
  id INTEGER PRIMARY KEY AUTOINCREMENT,
  name TEXT NOT NULL,
  email TEXT UNIQUE NOT NULL,
  created_at DATETIME DEFAULT CURRENT_TIMESTAMP
);

CREATE TABLE IF NOT EXISTS posts (
  id INTEGER PRIMARY KEY AUTOINCREMENT,
  user_id INTEGER NOT NULL,
  title TEXT NOT NULL,
  content TEXT,
  FOREIGN KEY (user_id) REFERENCES users(id)
);

R2 Object Storage

interface Env {
  BUCKET: R2Bucket;
}

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const url = new URL(request.url);
    const key = url.pathname.slice(1);
    
    switch (request.method) {
      case 'PUT': {
        // Upload file
        const body = await request.arrayBuffer();
        await env.BUCKET.put(key, body, {
          httpMetadata: {
            contentType: request.headers.get('content-type') || 'application/octet-stream',
          },
          customMetadata: {
            uploadedBy: 'api',
          },
        });
        return new Response('Uploaded', { status: 201 });
      }
      
      case 'GET': {
        // Download file
        const object = await env.BUCKET.get(key);
        if (!object) {
          return new Response('Not Found', { status: 404 });
        }
        
        const headers = new Headers();
        object.writeHttpMetadata(headers);
        headers.set('etag', object.httpEtag);
        
        return new Response(object.body, { headers });
      }
      
      case 'DELETE': {
        await env.BUCKET.delete(key);
        return new Response('Deleted');
      }
      
      default:
        return new Response('Method Not Allowed', { status: 405 });
    }
  },
};

// List objects
async function listObjects(env: Env, prefix?: string) {
  const listed = await env.BUCKET.list({
    prefix,
    limit: 100,
  });
  return listed.objects.map(obj => ({
    key: obj.key,
    size: obj.size,
    uploaded: obj.uploaded,
  }));
}

Cloudflare AI

interface Env {
  A
Read more
Ships withai-agents-skills

🧠 AI Agent Skills Repository - A curated collection of specialized skills for AI coding agents (Claude Code, GitHub Copilot, Cursor, Windsurf). Created by Yuval Avidani using GitHub Copilot via VS Code Insiders.

Get the whole plugin
Stats
280
Stars
63
Forks
Maintained
Maintenance
Python
Language
2mo ago
Last commit
8mo ago
Created

Repo: hoodini/ai-agents-skills

Other skills on ai-agents-skills.