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/pages/gotchas.md

Gotchas

Functions Not Running

Problem: Function endpoints return 404 or don't execute Causes: _routes.json excludes path; wrong file extension (.jsx/.tsx); Functions dir not at output root Solution: Check _routes.json, rename to .ts/.js, verify build output structure

404 on Static Assets

Problem: Static files not serving Causes: Build output dir misconfigured; Functions catching requests; Advanced mode missing env.ASSETS.fetch() Solution: Verify output dir, add exclusions to _routes.json, call env.ASSETS.fetch() in _worker.js

Bindings Not Working

Problem: env.BINDING undefined or errors Causes: wrangler.jsonc syntax error; wrong binding IDs; missing .dev.vars; out-of-sync types Solution: Validate config, verify IDs, create .dev.vars, run npx wrangler types

Build Failures

Problem: Deployment fails during build Causes: Wrong build command/output dir; Node version incompatibility; missing env vars; 20min timeout; OOM Solution: Check Dashboard → Deployments → Build log; verify settings; add .nvmrc; optimize build

Middleware Not Running

Problem: Middleware doesn't execute Causes: Wrong filename (not _middleware.ts); missing onRequest export; didn't call next() Solution: Rename file with underscore prefix; export handler; call next() or return Response

Headers/Redirects Not Working

Problem: _headers or _redirects not applying Causes: Only work for static assets; Functions override; syntax errors; exceeded limits Solution: Set headers in Response object for Functions; verify syntax; check limits (100 headers, 2,100 redirects)

TypeScript Errors

Problem: Type errors in Functions code Causes: Types not generated; Env interface doesn't match wrangler.jsonc Solution: Run npx wrangler types --path='./functions/types.d.ts'; update Env interface

Local Dev Issues

Problem: Dev server errors or bindings don't work Causes: Port conflict; bindings not passed; local vs HTTPS differences Solution: Use --port=3000; pass bindings via CLI or wrangler.jsonc; account for HTTP/HTTPS differences

Performance Issues

Problem: Slow responses or CPU limit errors Causes: Functions invoked for static assets; cold starts; 10ms CPU limit; large bundle Solution: Exclude static via _routes.json; optimize hot paths; keep bundle < 1MB

Framework-Specific

⚠️ Deprecated Frameworks

Next.js: Official adapter (@cloudflare/next-on-pages) deprecated and unmaintained.

  • Problem: No updates since 2024; incompatible with Next.js 15+; missing App Router features

  • Cause: Cloudflare discontinued official support; community fork exists but limited

  • Solutions:

    1. Recommended: Use Vercel (official Next.js host)

    2. Advanced: Self-host on Workers using custom adapter (complex, unsupported)

    3. Migration: Switch to SvelteKit/Nuxt (similar DX, full Pages support)

Remix: Official adapter (@remix-run/cloudflare-pages) deprecated.

  • Problem: No maintenance from Remix team; compatibility issues with Remix v2+

  • Cause: Remix team deprecated all framework adapters

  • Solutions:

    1. Recommended: Migrate to SvelteKit (similar file-based routing, better DX)

    2. Alternative: Use Astro (static-first with optional SSR)

    3. Workaround: Continue using deprecated adapter (no future support)

✅ Supported Frameworks

SvelteKit:

  • Use @sveltejs/adapter-cloudflare

  • Access bindings via platform.env in server load functions

  • Set platform: 'cloudflare' in svelte.config.js

Astro:

  • Built-in Cloudflare adapter

  • Access bindings via Astro.locals.runtime.env

Nuxt:

  • Set nitro.preset: 'cloudflare-pages' in nuxt.config.ts

  • Access bindings via event.context.cloudflare.env

Qwik, Solid Start:

  • Built-in or official Cloudflare adapters available

  • Check respective framework docs for binding access

Debugging

// Log request details
console.log('Request:', { method: request.method, url: request.url });
console.log('Env:', Object.keys(env));
console.log('Params:', params);

View logs: npx wrangler pages deployment tail --project-name=my-project

Smart Placement Issues

Increased Cold Start Latency

Problem: First requests slower after enabling Smart Placement Cause: Initial optimization period while system learns traffic patterns Solution: Expected behavior during first 24-48 hours; monitor latency trends over time

Inconsistent Response Times

Problem: Latency varies significantly across requests during initial deployment Cause: Smart Placement testing different execution locations to find optimal placement Solution: Normal during learning phase; stabilizes after traffic patterns emerge (1-2 days)

No Performance Improvement

Problem: Smart Placement enabled but no latency reduction observed Cause: Traffic evenly distributed globally, or no data locality constraints Solution: Smart Placement most effective with centralized data (D1/DO) or regional traffic; disable if no benefit

Remote Bindings Issues

Accidentally Modified Production Data

Problem: Local dev with --remote altered production database/KV Cause: Remote bindings connect directly to production resources; writes are real Solution:

  • Use --remote only for read-heavy debugging

  • Create separate preview environments for testing

  • Never use --remote for write operations during development

Remote Binding Auth Errors

Problem: npx wrangler pages dev --remote fails with "Unauthorized" or auth error Cause: Not logged in, session expired, or insufficient account permissions Solution:

  1. Run npx wrangler login to re-authenticate

  2. Verify account has access to project and bindings

  3. Check binding IDs match production configuration

Slow Local Dev with Remote Bindings

Problem: Local dev server slow when using --remote Cause: Every request makes network calls to production bindings Solution: Use local bindings for development; reserve --remote for final validation

Common Errors

"Module not found"

Cause: Dependencies not bundled or build output incorrect Solution: Check build output directory, ensure dependencies bundled

"Binding not found"

Cause: Binding not configured or types out of sync Solution: Verify wrangler.jsonc, run npx wrangler types

"Request exceeded CPU limit"

Cause: Code execution too slow or heavy compute Solution: Optimize hot paths, upgrade to Workers Paid

"Script too large"

Cause: Bundle size exceeds limit Solution: Tree-shake, use dynamic imports, code-split

"Too many subrequests"

Cause: Exceeded 50 subrequest limit Solution: Batch or reduce fetch calls

"KV key not found"

Cause: Key doesn't exist or wrong namespace Solution: Check namespace matches environment

"D1 error"

Cause: Wrong database_id or missing migrations Solution: Verify config, run wrangler d1 migrations list

Limits Reference (Jan 2026)

ResourceFreePaid
Functions Requests100k/dayUnlimited
CPU Time10ms/req30ms/req
Memory128MB128MB
Script Size1MB10MB
Subrequests50/req1,000/req
Deployments500/month5,000/month

Tip: Hitting CPU limit? Optimize hot paths or upgrade to Workers Paid plan.

Full limits

Getting Help

  1. Check Pages Docs

  2. Search Discord #functions

  3. Review Workers Examples

  4. Check framework-specific docs/adapters

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