workers-best-practices

Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, retrieval-first skill body that defers detail to verified one-level references and provides concrete commands. Its main weaknesses are mild table redundancy and the absence of an explicit error-recovery loop in the review workflow.

Suggestions

Consolidate the Rules Quick Reference and Anti-Patterns to Flag tables (or cross-link them) to remove overlap and trim tokens.

Add an explicit validate-fix-retry loop to the Review Workflow (e.g., "if tsc or lint reports errors, fix and re-run before approving").

Inline one or two short executable code snippets for the highest-frequency rules (streaming, waitUntil) in the body, rather than deferring all examples to references/rules.md.

Dimension	Reasoning	Score
Conciseness	Terse tables and a lean retrieval section respect Claude's competence, but the Rules Quick Reference and Anti-Patterns tables overlap somewhat, and the "Why it matters" rationales are mild padding that could be trimmed.	4 / 5
Actionability	Concrete executable commands appear (npm pack/tar fetch block, `npx tsc --noEmit`, `wrangler types`, `wrangler secret put`), but the per-rule code examples are deferred to references/rules.md, leaving minor gaps in the body itself.	4 / 5
Workflow Clarity	The 8-step Review Workflow is a clear, ordered sequence with an explicit validation checkpoint (step 7: tsc + no-floating-promises lint), but it lacks an explicit validate-fix-retry feedback loop that would reach the top anchor.	4 / 5
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references to references/rules.md and references/review.md (both verified present), keeping detailed examples out of the main file with easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states both capability and load triggers with concrete anti-pattern keywords. Minor gaps in action breadth and ecosystem distinctiveness keep specificity and conflict-risk just below the top anchor.

Dimension	Reasoning	Score
Specificity	"Reviews and authors Cloudflare Workers code against production best practices" names the domain plus two concrete actions and enumerates anti-patterns, but stops short of the multiple distinct actions (extract, fill, merge, convert) shown in the 5 anchor.	4 / 5
Completeness	It explicitly answers both what ("Reviews and authors Cloudflare Workers code against production best practices") and when ("Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc" supplies natural phrases users would say, but lacks synonyms and file extensions that would push it to comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The Cloudflare Workers best-practices niche is clear with distinct triggers, but "configuring wrangler.jsonc" and the broader Cloudflare ecosystem overlap with the sibling wrangler, durable-objects, and workflows skills named in the body.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/cloudflare/skills/workers-best-practices/SKILL.md
Commit: 1dc1958

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.