skills/cloudflare-workers/SKILL.md
Cloudflare Workers edge computing platform with D1, R2, KV, Durable Objects, Queues, and Workers AI. MANDATORY TRIGGERS: cloudflare workers, cloudflare worker, wrangler, cloudflare d1, cloudflare r2, cloudflare kv, durable objects, workers ai, cloudflare queues, cloudflare pages functions, WorkerEntrypoint, miniflare. Also trigger when user wants to deploy serverless functions to Cloudflare edge, build full-stack apps on Cloudflare, use SQLite at the edge, store objects with S3-compatible API, or run AI models on Cloudflare. When in doubt about whether to use this skill for edge computing or Cloudflare tasks, use it.
npx skillsauth add abhisheksharma-17/skills-graph cloudflare-workersInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Build full-stack applications on Cloudflare's global edge network — serverless compute, databases, storage, queues, and AI in one platform.
Source: developers.cloudflare.com | CLI: wrangler | License: BSD-3-Clause
| Reference | File | Read When |
|-----------|------|-----------|
| Overview & Setup | references/00-overview.md | Getting started, Wrangler CLI, project scaffolding, C3, deployment |
| Workers Fundamentals | references/01-workers-fundamentals.md | Fetch handler, Request/Response, ExecutionContext, routing, env bindings |
| Configuration | references/02-configuration.md | wrangler.toml / wrangler.jsonc, bindings, compatibility dates, environments |
| KV Storage | references/03-kv-storage.md | Key-value store: get, put, delete, list, metadata, TTL, caching |
| D1 Database | references/04-d1-database.md | SQLite database: prepare, batch, exec, migrations, sessions, Time Travel |
| R2 Object Storage | references/05-r2-object-storage.md | S3-compatible storage: get, put, delete, list, multipart uploads |
| Durable Objects | references/06-durable-objects.md | Stateful edge compute: storage, alarms, WebSocket hibernation, SQL |
| Queues | references/07-queues.md | Message queues: producer/consumer, batching, retries, dead-letter |
| Workers AI | references/08-workers-ai.md | AI inference: text generation, embeddings, image, speech, Vectorize |
| Service Bindings & RPC | references/09-service-bindings-rpc.md | Inter-Worker communication, WorkerEntrypoint, named entrypoints, RPC |
| Pages & Static Assets | references/10-pages-static-assets.md | Pages Functions, static assets, _routes.json, middleware |
| Testing | references/11-testing.md | Vitest integration, @cloudflare/vitest-pool-workers, Miniflare |
| Deployment & CI/CD | references/12-deployment-cicd.md | wrangler deploy, environments, secrets, GitHub Actions, rollbacks |
# Create a new Workers project
npm create cloudflare@latest my-app
# Or install Wrangler globally
npm install -g wrangler
# Login to Cloudflare
wrangler login
development
High-throughput LLM inference and serving engine with PagedAttention, continuous batching, and OpenAI-compatible API. MANDATORY TRIGGERS: vLLM, vllm, LLM serving, LLM inference engine, PagedAttention. Also trigger when the user wants to serve LLMs in production, deploy models with tensor parallelism, use speculative decoding, quantize models for inference, build OpenAI-compatible API servers, or optimize LLM throughput and latency. When in doubt about whether to use this skill for LLM serving tasks, use it.
tools
Type-safe Python agent framework for building production-grade GenAI applications with Pydantic validation, structured outputs, and dependency injection. MANDATORY TRIGGERS: pydantic-ai, pydantic_ai, PydanticAI, pydantic ai agent. Also trigger when the user wants to build type-safe AI agents in Python, create structured LLM outputs with Pydantic models, implement dependency injection for agents, use tools/capabilities with LLMs, or build multi-agent systems with Python type safety. When in doubt about whether to use this skill for Python AI agent tasks, use it.
development
Durable execution platform for building fault-tolerant workflows, long-running processes, and resilient distributed applications. MANDATORY TRIGGERS: temporal, temporal.io, temporalio, durable execution, workflow orchestration engine. Also trigger when the user wants to build fault-tolerant workflows, implement saga patterns, create long-running distributed processes, orchestrate microservices with retries and timeouts, or build durable AI agent pipelines. When in doubt about whether to use this skill for workflow orchestration or durable execution tasks, use it.
tools
AI framework for building RAG pipelines, agents, workflows, and data-augmented LLM applications with 300+ integrations. MANDATORY TRIGGERS: llamaindex, llama-index, llama_index, LlamaIndex, VectorStoreIndex, SimpleDirectoryReader, LlamaHub, LlamaParse. Also trigger when the user wants to build RAG applications with LlamaIndex, create document indexing pipelines, build agentic workflows with tool calling, implement structured data extraction from documents, or connect LLMs to custom data sources. When in doubt about whether to use this skill for RAG, document indexing, or LLM data augmentation tasks, use it.