cloudflare-agent-skills

Build Cloudflare Agents SDK applications for autonomous multi-step tool use, AIChatAgent chat agents, Durable Object-backed state, tools, scheduling, callable methods, WebSockets, SQL state, and constrained agent behavior. Use when RAG or Workflows are not enough.

Choose Cloudflare Developer Platform primitives and architecture shapes before writing code. Use for Cloudflare Workers, Durable Objects, D1, R2, Queues, Workflows, Containers, Realtime, Workers AI, Vectorize, AI Search, Agents, cost, limits, and migration decisions.

Decide when to use Cloudflare Containers instead of Workers and design container-backed workloads, native binaries, long-running processes, image processing, larger runtime shapes, and Worker frontends. Use as an escape hatch when Workers constraints do not fit.

Optimize Cloudflare Developer Platform costs for Workers CPU vs wall time, D1 operations, KV reads/writes, R2 storage/egress, Durable Object hotspots, Queues, Workflows, Workers AI tokens, and architecture-level trade-offs. Use during design and production reviews.

Write Cloudflare D1 code and schemas for SQLite-backed relational data, prepared statements, bindings, migrations, typed queries, tenant boundaries, indexes, pagination, and idempotent writes. Use when Workers need SQL data on Cloudflare.

Build Cloudflare Durable Objects for stateful coordination, one-per-entity actors, strong consistency, private SQLite-backed storage, RPC methods, WebSockets, alarms, sessions, rooms, rate limits, and collaborative state. Use when Workers code needs serialized state or race-free coordination.

Build full-stack Cloudflare apps with Workers, static assets, SSR, API routes, SPA/hybrid rendering, cache headers, and binding-backed data. Use when implementing frontend-plus-backend applications on Cloudflare Workers.

Use Cloudflare KV for eventually consistent global cache/config and Hyperdrive for existing Postgres/MySQL access from Workers. Use when deciding cache-aside patterns, TTLs, invalidation, external DB connectivity, and Node-compatible database drivers.

Develop and test Cloudflare Workers locally with wrangler dev, Miniflare-compatible bindings, fixtures, integration tests, remote validation, and CI checks. Use when building local development workflows for Workers, D1, Durable Objects, KV, R2, Queues, or Workflows.

Plan incremental migrations to Cloudflare from AWS, Azure, GCP, server-based apps, or existing databases using strangler patterns, service boundaries, R2 offload, Workers frontdoors, Hyperdrive, queues, workflows, shadow reads, rollback, and observability.

Design multi-tenant Cloudflare applications with tenant isolation, D1 row/database boundaries, Durable Object-per-tenant patterns, R2 key prefixes, KV cache keys, authz, noisy-neighbor controls, and migration paths. Use for SaaS and platform code.

Add production observability to Cloudflare Workers apps with structured logs, request IDs, metrics, traces, Durable Object/Queue/Workflow visibility, error handling, and incident debugging. Use before deploying or debugging Cloudflare applications.

Apply Cloudflare reference architecture patterns for CRUD SaaS, collaboration, async exports, AI assistants, RAG, media, webhook ingestion, and migration. Use to turn requirements into an implementation pattern and primitive map.

Check Cloudflare Developer Platform hard limits and runtime constraints before implementation: Worker memory/CPU/body/protocol constraints, D1 size/query limits, Durable Object hotspots, KV consistency, Queue message size/order, R2 object flows, and product availability. Use to prevent invalid designs.

Use Cloudflare Queues for asynchronous background work, producers, consumers, batching, retries, idempotent message handling, delayed processing, fan-out, and decoupling request latency. Use when Worker code should do something later without needing strict ordering.

Write Cloudflare R2 object-storage code for uploads, downloads, metadata, streaming, signed access patterns, large files, generated exports, public assets, and D1/R2 metadata separation. Use when Workers handle blobs or egress-sensitive storage.

Build retrieval augmented generation on Cloudflare with AI Search, Vectorize, Workers AI embeddings, chunking, metadata filters, citations, ingestion pipelines, reranking, and grounded answer generation. Use when implementing RAG, semantic search, or document QA.

Build realtime Cloudflare applications using Durable Objects with WebSockets for data realtime and Cloudflare Realtime/WebRTC for audio and video. Use for chat rooms, multiplayer, collaboration, presence, live dashboards, and media-session routing.

Secure and deploy Cloudflare Workers applications with secrets, least-privilege bindings, authz, tenant isolation, input validation, CORS, preview/prod separation, migrations, rollout, and rollback practices. Use before shipping Cloudflare code.

Choose the right Cloudflare storage primitive: D1, R2, KV, Durable Object storage, Hyperdrive, Vectorize, AI Search, cache, or external databases. Use before modeling data, writing migrations, or deciding consistency/cost trade-offs.

Write Cloudflare Workers AI and AI Gateway code for model inference, prompts, streaming, token budgets, model selection, observability, and fallback design. Use when adding LLM, embeddings, summarization, classification, or generation to Workers.

Write Cloudflare Workers code for stateless HTTP handlers, APIs, SSR, streaming responses, service orchestration, bindings, async I/O, global-scope initialization, and ctx.waitUntil. Use for Worker fetch handlers and edge runtime TypeScript patterns.

Implement Cloudflare Workflows for durable execution, ordered multi-step jobs, retries, checkpointing, sleeps, long-running processes, imports, billing flows, AI pipelines, and sagas. Use when a Worker needs reliable progress over multiple steps instead of manual retry state.

Configure Cloudflare Workers projects with wrangler.jsonc, bindings, environment variables, secrets, compatibility flags, and generated TypeScript Env types. Use whenever code needs D1, R2, KV, Durable Objects, Queues, Workflows, Workers AI, Vectorize, Hyperdrive, assets, or service bindings.