Skip to main content
prompt GP ChatGPT

Cloudflare Worker taste — ChatGPT, Claude.ai prompt: what it does

Cloudflare Worker taste — a prompt for ChatGPT and Claude.ai that sets engineering standards for Cloudflare Workers development. It enforces architectural principles for coding, secret management, and deployment.

CC0-1.0 ★ 178,201 updated 2026-10-24

Open on GitHub

What Cloudflare Worker taste does

This prompt provides a set of engineering guidelines for building Cloudflare Workers with an edge-first focus. It instructs the AI to prioritize wrangler for local development and secret management, while keeping wrangler.toml or wrangler.json as the source of truth for bindings.

The guidelines cover TypeScript typing, request validation, error handling, and caching strategies. It emphasizes keeping Workers focused on single tasks and offloading heavy computations to queues or workflows rather than keeping them inside the isolate. Using this prompt ensures that AI-generated code and architectural advice adhere to Cloudflare best practices.

What it helps with

  • Enforce Cloudflare Workers development standards
  • Manage secrets and environment variables correctly
  • Decouple logic into single-purpose functions
  • Configure caching and error handling

Example prompts for the agent

  • "Review my code against Cloudflare Worker taste: [code]"
  • "Write an API handler for Cloudflare Workers following the Cloudflare Worker taste guidelines"

How to install Cloudflare Worker taste

How to use

Paste the text at the start of a chat or into project instructions

Questions about Cloudflare Worker taste

What does Cloudflare Worker taste do?

It is a set of rules for AI that enforces edge-first architectural standards when writing Cloudflare Workers code.

How to install Cloudflare Worker taste in Claude Code?

Save the prompt content into .claude/commands/prompts.csv.md in your project root.

What is required to use this prompt?

An active ChatGPT or Claude.ai account and wrangler installed for local development.

Source text

prompts.csv · CC0-1.0
# Cloudflare Worker taste of an edge-first platform engineer
- Prefer Wrangler for local dev, secrets, and deploys; keep `wrangler.toml` (or `wrangler.json`) as the source of truth for bindings. Confidence: 0.95
- Write Workers in TypeScript with the official workers-types, and enable `strict` in `tsconfig`. Confidence: 0.90
- Keep each Worker focused on one job: edge API, rewrite, auth gate or queue consumer; split unrelated work into separate Workers. Confidence: 0.85
- Put durable state in KV, Durable Objects, D1 or R2 through bindings; never pretend the Worker isolate is a long-lived server. Confidence: 0.90
- Load secrets with `wrangler secret` and read them from `env`; do not commit API keys or `.dev.vars` with real values. Confidence: 0.95
- Validate every request early: method, path, auth header and a size limit before parsing the body. Confidence: 0.90
- Return explicit status codes and small JSON error bodies; avoid throwing uncaught exceptions that become opaque 500s. Confidence: 0.85
- Use `waitUntil` for non-critical work such as analytics or cache warming so the client response is not blocked. Confidence: 0.80
- Prefer the Cache API or Cache Rules for GETs that are safe to reuse, and set Cache-Control deliberately on every response. Confidence: 0.85
- Test with `wrangler dev` and Miniflare-compatible unit tests; cover routing, auth failures and binding edge cases. Confidence: 0.85
- Pin compatibility date in Wrangler config and bump it on purpose after reading the runtime changelog. Confidence: 0.85
- Use Durable Objects when you need strong consistency per key (rooms, counters, locks); use KV for eventually consistent reads. Confidence: 0.85
- Stream large responses and uploads when possible; avoid buffering whole files in memory inside the isolate. Confidence: 0.80
- Log with structured JSON fields (request id, route, status, duration) and ship them to your observability sink. Confidence: 0.80
- Gate production deploys behind a staging route or environment, and smoke-test the worker URL before shifting traffic. Confidence: 0.85
- Keep CPU-heavy work short; move bulk transforms and ML to Queues, Workflows or an origin service. Confidence: 0.85
- Prefer fetch to first-party Cloudflare services over stuffing large SDKs into the Worker bundle. Confidence: 0.75
- Review the bundle size on every change; drop unused deps and avoid Node polyfills you do not need. Confidence: 0.80
- Document every binding and its purpose at the top of the Worker entry file so onboarding does not require tribal knowledge. Confidence: 0.75
- Treat cron Triggers and Queue consumers as first-class entrypoints with the same validation and logging standards as HTTP. Confidence: 0.80

© f · CC0-1.0 · f/prompts.chat

Similar prompts

All prompts for Backend and APIs →

From the same set218

The whole set →
Kafka Streaming taste Kafka Streaming taste is a prompt for ChatGPT, Claude.ai, and Claude Code that defines Kafka streaming architecture and design rules. GP ChatGPT ★ 178,201repo stars Helm Chart taste The Helm Chart taste ChatGPT prompt sets criteria for designing Helm charts. It helps review templates, security settings, and chart tests before release. GP ChatGPT ★ 178,201repo stars Prisma ORM taste Prisma ORM taste — a prompt for ChatGPT and Claude Code establishes pragmatic guidelines for database workflows with Prisma ORM. Directs model schema design, migrations, and query patterns. GP ChatGPT ★ 178,201repo stars GitHub Actions taste The GitHub Actions taste ChatGPT prompt sets out practices for building CI with GitHub Actions. It covers checks, releases, and deployment safeguards. GP ChatGPT ★ 178,201repo stars Playwright E2E taste The Playwright E2E taste prompt for ChatGPT sets conventions for Playwright end-to-end tests. It covers core user journeys and test isolation, from local runs to CI. GP ChatGPT ★ 178,201repo stars Next.js App taste Next.js App taste — a prompt for ChatGPT and Claude.ai that enforces pragmatic Next.js App Router conventions. It steers code generation toward Server Components, safe caching, and strict data validation. GP ChatGPT ★ 178,201repo stars Data Visualization taste The Data Visualization taste ChatGPT prompt guides clear data visualization. It helps choose a chart type, format its elements, and check accessibility. GP ChatGPT ★ 178,201repo stars Load Testing taste The Load Testing taste prompt for ChatGPT sets performance testing standards and reliability engineering principles. It is applied when designing load test scenarios and analyzing backend capacity. GP ChatGPT ★ 178,201repo stars

Project sponsors

Companies that keep this analytics open