Generated banner for Cloudflare
Generated logo for Cloudflare

Cloudflare

OpenAIOfficialCreated by CloudflareDistributed by OpenAI

  • Skill
  • Tool integration
  • Cloud and DevOps
  • Apache-2.0
  • Medium risk

From the author

Comprehensive Cloudflare platform skill covering Workers, Pages, storage (KV, D1, R2), AI (Workers AI, Vectorize, Agents SDK), networking (Tunnel, Spectrum), security (WAF, DDoS), and infrastructure-as-code (Terraform, Pulumi). Use for any Cloudflare development task. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
— the description by Cloudflare

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The Cloudflare platform skill provides a centralized resource for developers building on Cloudflare's edge network. It covers the full ecosystem, including compute (Workers, Pages), storage (KV, D1, R2), AI integration (Workers AI, Agents SDK), networking, and security. The skill emphasizes a retrieval-first approach, directing users to official Cloudflare documentation and configuration schemas to ensure accuracy regarding API signatures, limits, and pricing.

What it does

  • Provides decision trees to help select the right Cloudflare product for specific compute, storage, or networking needs.
  • Offers structured references for the Cloudflare Agents SDK, including lifecycle hooks and state management.
  • Guides users on integrating AI models and vector databases into edge applications.
  • Outlines methods for managing infrastructure-as-code using Terraform or Pulumi.
  • Facilitates access to product-specific documentation for security, media, and analytics services.
  • Maintains a directory of developer tools like Wrangler and Miniflare for local development and testing.

When to use it

  • When starting a new project on the Cloudflare platform and needing to choose the appropriate architecture.
  • When implementing stateful AI agents using the Cloudflare Agents SDK.
  • When configuring edge compute, storage bindings, or networking rules.
  • When troubleshooting API limits, configuration errors, or deployment issues.
  • When integrating AI models or vector search into existing edge applications.

Advantages

  • Consolidates a vast ecosystem into a navigable, task-oriented structure.
  • Promotes the use of official, up-to-date documentation over potentially stale training data.
  • Simplifies complex architectural decisions through clear, logic-based decision trees.
  • Provides specific code patterns for advanced features like Durable Objects and AI agents.
  • Supports modern infrastructure-as-code workflows for consistent deployments.

Usage examples

“I need to build a stateful AI chat agent on Cloudflare. How do I start?”
The agent will guide you to use the AIChatAgent class from the Agents SDK, explain how to manage message history, and provide a template for integrating AI models.
“Which storage solution should I use for relational data in my Worker?”
The agent will point you to D1 for SQLite-based relational storage or Hyperdrive for connecting to existing Postgres/MySQL databases.
“How do I expose my local development server to the internet via Cloudflare?”
The agent will provide instructions on using Cloudflare Tunnel to securely connect your local service to the Cloudflare edge.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/openai/cloudflare/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip cloudflare.zip -d .agents/skills

Documentation by Cloudflare

Cloudflare Platform Skill

Consolidated skill for building on the Cloudflare platform. Use decision trees below to find the right product, then load detailed references.

Your knowledge of Cloudflare APIs, types, limits, and pricing may be outdated. Prefer retrieval over pre-training — the references in this skill are starting points, not source of truth.

Retrieval Sources

Fetch the latest information before citing specific numbers, API signatures, or configuration options. Do not rely on baked-in knowledge or these reference files alone.

SourceHow to retrieveUse for
Cloudflare docsSearch https://developers.cloudflare.com/ directlyLimits, pricing, API reference, compatibility dates/flags
Workers typesnpm pack @cloudflare/workers-types or check node_modulesType signatures, binding shapes, handler types
Wrangler config schemanode_modules/wrangler/config-schema.jsonConfig fields, binding shapes, allowed values
Product changelogshttps://developers.cloudflare.com/changelog/Recent changes to limits, features, deprecations

When a reference file and the docs disagree, trust the docs. This is especially important for: numeric limits, pricing tiers, type signatures, and configuration options.

Quick Decision Trees

"I need to run code"
Need to run code?
├─ Serverless functions at the edge → workers/
├─ Full-stack web app with Git deploys → pages/
├─ Stateful coordination/real-time → durable-objects/
├─ Long-running multi-step jobs → workflows/
├─ Run containers → containers/
├─ Multi-tenant (customers deploy code) → workers-for-platforms/
├─ Scheduled tasks (cron) → cron-triggers/
├─ Lightweight edge logic (modify HTTP) → snippets/
├─ Process Worker execution events (logs/observability) → tail-workers/
└─ Optimize latency to backend infrastructure → smart-placement/
"I need to store data"
Need storage?
├─ Key-value (config, sessions, cache) → kv/
├─ Relational SQL → d1/ (SQLite) or hyperdrive/ (existing Postgres/MySQL)
├─ Object/file storage (S3-compatible) → r2/
├─ Message queue (async processing) → queues/
├─ Vector embeddings (AI/semantic search) → vectorize/
├─ Strongly-consistent per-entity state → durable-objects/ (DO storage)
├─ Secrets management → secrets-store/
├─ Streaming ETL to R2 → pipelines/
└─ Persistent cache (long-term retention) → cache-reserve/
"I need AI/ML"
Need AI?
├─ Run inference (LLMs, embeddings, images) → workers-ai/
├─ Vector database for RAG/search → vectorize/
├─ Build stateful AI agents → agents-sdk/
├─ Gateway for any AI provider (caching, routing) → ai-gateway/
└─ AI-powered search widget → ai-search/
"I need networking/connectivity"
Need networking?
├─ Expose local service to internet → tunnel/
├─ TCP/UDP proxy (non-HTTP) → spectrum/
├─ WebRTC TURN server → turn/
├─ Private network connectivity → network-interconnect/
├─ Optimize routing → argo-smart-routing/
├─ Optimize latency to backend (not user) → smart-placement/
└─ Real-time video/audio → realtimekit/ or realtime-sfu/
"I need security"
Need security?
├─ Web Application Firewall → waf/
├─ DDoS protection → ddos/
├─ Bot detection/management → bot-management/
├─ API protection → api-shield/
├─ CAPTCHA alternative → turnstile/
└─ Credential leak detection → waf/ (managed ruleset)
"I need media/content"
Need media?
├─ Image optimization/transformation → images/
├─ Video streaming/encoding → stream/
├─ Browser automation/screenshots → browser-rendering/
└─ Third-party script management → zaraz/
"I need analytics/metrics data"
Need analytics?
├─ Query across all Cloudflare products (HTTP, Workers, DNS, etc.) → graphql-api/
├─ Custom high-cardinality metrics from Workers → analytics-engine/
├─ Client-side (RUM) performance data → web-analytics/
├─ Workers Logs and real-time debugging → observability/
└─ Raw logs (Logpush to external tools) → Cloudflare docs
"I need infrastructure-as-code"
Need IaC? → pulumi/ (Pulumi), terraform/ (Terraform), or api/ (REST API)

Product Index

Compute & Runtime
ProductReference
Workersreferences/workers/
Pagesreferences/pages/
Pages Functionsreferences/pages-functions/
Durable Objectsreferences/durable-objects/
Workflowsreferences/workflows/
Containersreferences/containers/
Workers for Platformsreferences/workers-for-platforms/
Cron Triggersreferences/cron-triggers/
Tail Workersreferences/tail-workers/
Snippetsreferences/snippets/
Smart Placementreferences/smart-placement/
Storage & Data
ProductReference
KVreferences/kv/
D1references/d1/
R2references/r2/
Queuesreferences/queues/
Hyperdrivereferences/hyperdrive/
DO Storagereferences/do-storage/
Secrets Storereferences/secrets-store/
Pipelinesreferences/pipelines/
R2 Data Catalogreferences/r2-data-catalog/
R2 SQLreferences/r2-sql/
AI & Machine Learning
ProductReference
Workers AIreferences/workers-ai/
Vectorizereferences/vectorize/
Agents SDKreferences/agents-sdk/
AI Gatewayreferences/ai-gateway/
AI Searchreferences/ai-search/
Networking & Connectivity
ProductReference
Tunnelreferences/tunnel/
Spectrumreferences/spectrum/
TURNreferences/turn/
Network Interconnectreferences/network-interconnect/
Argo Smart Routingreferences/argo-smart-routing/
Workers VPCreferences/workers-vpc/
Security
ProductReference
WAFreferences/waf/
DDoS Protectionreferences/ddos/
Bot Managementreferences/bot-management/
API Shieldreferences/api-shield/
Turnstilereferences/turnstile/
Media & Content
ProductReference
Imagesreferences/images/
Streamreferences/stream/
Browser Renderingreferences/browser-rendering/
Zarazreferences/zaraz/
Real-Time Communication
ProductReference
RealtimeKitreferences/realtimekit/
Realtime SFUreferences/realtime-sfu/
Developer Tools
ProductReference
Wranglerreferences/wrangler/
Miniflarereferences/miniflare/
C3references/c3/
Observabilityreferences/observability/
GraphQL Analytics APIreferences/graphql-api/
Analytics Enginereferences/analytics-engine/
Web Analyticsreferences/web-analytics/
Sandboxreferences/sandbox/
Workerdreferences/workerd/
Workers Playgroundreferences/workers-playground/
Infrastructure as Code
ProductReference
Pulumireferences/pulumi/
Terraformreferences/terraform/
APIreferences/api/
Other Services
ProductReference
Email Routingreferences/email-routing/
Email Workersreferences/email-workers/
Static Assetsreferences/static-assets/
Bindingsreferences/bindings/
Cache Reservereferences/cache-reserve/

Files

references/smart-placement/gotchas.md

Smart Placement Gotchas

Common Errors

"INSUFFICIENT_INVOCATIONS"

Cause: Not enough traffic for Smart Placement to analyze Solution:

  • Ensure Worker receives consistent global traffic

  • Wait longer (analysis takes up to 15 minutes)

  • Send test traffic from multiple global locations

  • Check Worker has fetch event handler

"UNSUPPORTED_APPLICATION"

Cause: Smart Placement made Worker slower rather than faster Reasons:

  • Worker doesn't make backend calls (runs faster at edge)

  • Backend calls are cached (network latency to user more important)

  • Backend service has good global distribution

  • Worker serves static assets or Pages content

Solutions:

  • Disable Smart Placement: { "placement": { "mode": "off" } }

  • Review whether Worker actually benefits from Smart Placement

  • Consider caching strategy to reduce backend calls

  • For Pages/Assets Workers, use separate backend Worker with Smart Placement

"No request duration metrics"

Cause: Smart Placement not enabled, insufficient time passed, insufficient traffic, or analysis incomplete Solution:

  • Ensure Smart Placement enabled in config

  • Wait 15+ minutes after deployment

  • Verify Worker has sufficient traffic

  • Check placement_status is SUCCESS

"cf-placement header missing"

Cause: Smart Placement not enabled, beta feature removed, or Worker not analyzed yet Solution: Verify Smart Placement enabled, wait for analysis (15min), check if beta feature still available

Pages/Assets + Smart Placement Performance Degradation

Problem: Static assets load 2-5x slower when Smart Placement enabled with run_worker_first = true.

Cause: Smart Placement routes ALL requests (including static assets like HTML, CSS, JS, images) to remote locations. Static content should ALWAYS be served from edge closest to user.

Solution: Split into separate Workers OR disable Smart Placement:

// ❌ BAD - Assets routed away from user
{
  "name": "pages-app",
  "placement": { "mode": "smart" },
  "assets": { "run_worker_first": true }
}

// ✅ GOOD - Assets at edge, API optimized
// frontend/wrangler.jsonc
{
  "name": "frontend",
  "assets": { "run_worker_first": true }
  // No placement field - stays at edge
}

// backend/wrangler.jsonc
{
  "name": "backend-api",
  "placement": { "mode": "smart" }
}

This is one of the most common and impactful Smart Placement misconfigurations.

Monolithic Full-Stack Worker

Problem: Frontend and backend logic in single Worker with Smart Placement enabled.

Cause: Smart Placement optimizes for backend latency but increases user-facing response time.

Solution: Split into two Workers:

// frontend/wrangler.jsonc
{
  "name": "frontend",
  "placement": { "mode": "off" },  // Explicit: stay at edge
  "services": [{ "binding": "BACKEND", "service": "backend-api" }]
}

// backend/wrangler.jsonc
{
  "name": "backend-api",
  "placement": { "mode": "smart" },
  "d1_databases": [{ "binding": "DB", "database_id": "xxx" }]
}

Local Development Confusion

Issue: Smart Placement doesn't work in wrangler dev.

Explanation: Smart Placement only activates in production deployments, not local development.

Solution: Test Smart Placement in staging environment: wrangler deploy --env staging

Baseline Traffic & Analysis Time

Note: Smart Placement routes 1% of requests WITHOUT optimization for comparison (expected).

Analysis time: Up to 15 minutes. During analysis, Worker runs at edge. Monitor placement_status.

RPC Methods Not Affected (Critical Limitation)

Problem: Enabled Smart Placement on backend but RPC calls still slow.

Cause: Smart Placement ONLY affects fetch handlers. RPC methods (Service Bindings with WorkerEntrypoint) are NEVER affected.

Why: RPC bypasses fetch handler - Smart Placement can only route fetch requests.

Solution: Convert to fetch-based Service Bindings:

// ❌ RPC - Smart Placement has NO EFFECT
export class BackendRPC extends WorkerEntrypoint {
  async getData() {
    // ALWAYS runs at edge
    return await this.env.DATABASE.prepare('SELECT * FROM table').all();
  }
}

// ✅ Fetch - Smart Placement WORKS
export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    // Runs close to DATABASE when Smart Placement enabled
    const data = await env.DATABASE.prepare('SELECT * FROM table').all();
    return Response.json(data);
  }
}

Requirements

  • Wrangler 2.20.0+ required

  • Consistent multi-region traffic needed for analysis

  • Only affects fetch handlers - RPC methods and named entrypoints not affected

Limits

Resource/LimitValueNotes
Analysis timeUp to 15 minutesAfter enabling
Baseline traffic1%Routed without optimization
Min Wrangler version2.20.0+Required
Traffic requirementMulti-regionConsistent needed

Disabling Smart Placement

{ "placement": { "mode": "off" } }  // Explicit disable
// OR remove "placement" field entirely (same effect)

Both behaviors identical - Worker runs at edge closest to user.

When NOT to Use Smart Placement

  • Workers serving only static content or cached responses

  • Workers without significant backend communication

  • Pure edge logic (auth checks, redirects, simple transformations)

  • Workers without fetch event handlers

  • Pages/Assets Workers with run_worker_first = true

  • Workers using RPC methods instead of fetch handlers

These scenarios won't benefit and may perform worse with Smart Placement.

Requirements and compatibility

Written for: OpenAI Codex

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Security

What our scanner noticed· Medium risk

  • Possible data-exfiltration endpoints
  • Instructions that use the network
  • Downloads piped into a shell

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
Cloudflare
Publisher
OpenAI (Official)
Distributed by
OpenAI
Source
openai/plugins · plugins/cloudflare/skills/cloudflare · commit d420d13
Licence
Apache License 2.0 (redistribution allowed)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Cloudflare or OpenAI.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download cloudflare.zip