agentleFS
lsjwzhlsjwzh/MultiCC/skills/cloudflare-platform-skills/SKILL.md

cloudflare-platform-skills

Skill15 starsChanged 7 days agoMITView on GitHub

Index of official Cloudflare platform skills (Durable Objects, Workers, Agents SDK, wrangler, sandbox SDK) to fetch and read before touching Cloudflare surface. Load when working on Cloudflare Workers, Durable Objects, wrangler, KV, R2, D1, Vectorize, Containers, or the agents SDK.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    When a task touches Cloudflare platform surface — Workers, Durable Objects, wrangler, the sandbox SDK, the Agents SDK — the authoritative …

    line 8
  2. Distinctive:

    If a skill isn't already available in your environment, fetch it from the URL listed and load it manually.

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Cloudflare platform skills index

When a task touches Cloudflare platform surface — Workers, Durable Objects, wrangler, the sandbox SDK, the Agents SDK — the authoritative guidance lives in the cloudflare/skills repository. This file is an index: open the relevant skill below when its trigger applies and read its SKILL.md before starting work.

If a skill isn't already available in your environment, fetch it from the URL listed and load it manually. The fallback for everything is the official Cloudflare documentation at https://developers.cloudflare.com.

Adapted from the cloudflare skill in https://github.com/cloudflare/computer (MIT license — see the LICENSE file next to this skill).

Primary skills

These three cover most Cloudflare platform work:

SkillLoad when
durable-objectsWriting or reviewing Durable Object code: RPC methods, SQLite storage, alarms, WebSockets, hibernation.
workers-best-practicesWriting or reviewing Worker code: streaming, floating promises, global state, bindings, secrets, observability, wrangler.jsonc configuration.
agents-sdkBuilding on the Cloudflare Agents SDK: stateful agents, Workflows integration, scheduled tasks, MCP servers.

Other skills

Load these when their trigger applies:

SkillLoad when
wranglerRunning wrangler commands: deploy, dev, secrets, bindings for KV, R2, D1, Vectorize, Hyperdrive, Queues, Workflows, Containers.
cloudflareGeneral Cloudflare platform questions outside the more specific skills above — KV, R2, D1, Vectorize, networking, security, infrastructure-as-code.
sandbox-sdkBuilding or reviewing sandboxed-execution code paths, e.g. containers running computerd for @cloudflare/computer.
web-perfProfiling page load, Core Web Vitals, or render-blocking issues.
cloudflare-email-serviceWorking with Cloudflare Email Routing or the Email Workers binding.

How to use this index

  • Storage, RPC, alarms in a DO → durable-objects (plus workers-best-practices for the surrounding Worker glue).
  • Deploys, secrets, bindings → wrangler before running wrangler commands or editing wrangler.jsonc.
  • Building on @cloudflare/computer → load the companion cloudflare-computer skill alongside durable-objects.
  • Crossing two surfaces (e.g. a Worker that wakes a Durable Object that talks to a container) → load both relevant skills before starting. The skills are small; loading two is cheaper than fixing an architectural mistake.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.