Cloudflare

Skill yigityildiz0/universal-ai-skill-library/skills/common/cloudflare

Design, implement, or troubleshoot applications on current Cloudflare products using project configuration and official documentation. Use for Workers.From its SKILL.md

Install

npx -y skills add yigityildiz0/universal-ai-skill-library --skill cloudflare

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

22 days oldThe repository was created 22 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

2.0 KB, 364 tokens by cl100k_base, as published. Nobody here has run it

Cloudflare Engineering

Discover

Inspect repository instructions, wrangler configuration, package/lock versions, bindings, environments, routes/domains, migrations, secrets references, compatibility date/flags, tests, and deployment history. Verify behavior from current official Cloudflare docs and installed CLI help; product APIs and compatibility rules change.

Route by requirement

stateless request logic: Workers;
static/full-stack deployment: Pages or the project's current Workers framework path;
relational data: D1 with migrations and transaction limits;
objects/blobs: R2;
cache/config-like key-value: KV with consistency tradeoffs;
strongly coordinated per-entity state: Durable Objects;
asynchronous delivery: Queues;
durable multi-step jobs: Workflows when currently supported;
AI inference/gateway: only the configured authorized provider/model and current product support.

Do not choose a product by convenience alone. Compare consistency, region, limits, pricing, latency, retention, and operational ownership.

Safety

Keep secrets in documented secret stores, not config/source/logs. Validate untrusted requests, enforce auth at the boundary, limit CPU/memory/body/concurrency, use idempotency for retried effects, and avoid leaking platform metadata. AI Gateway fallback/routing must not silently change provider, model, region, privacy, or cost.

Do not run global installs, @latest, DNS/domain changes, migrations, secret writes, deployments, or production data operations without authorization.

Verify

Run config parsing, typecheck/lint/tests, local emulator/dev checks, binding/migration validation, failure/limit tests, and a bounded staging smoke test. Report installed versions, compatibility date, environment, bindings, commands, observed platform limits, deployment steps, rollback, and any unverified production behavior.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.