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

92%

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

85%Weight 40%Scale 1-3

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

The body is highly actionable with concrete commands and a well-sequenced, validated review workflow, and it uses progressive disclosure effectively via two real, clearly-labeled reference files. Its main weakness is conciseness: the inline Rules Quick Reference and Anti-Patterns tables largely restate content that lives in references/rules.md.

Suggestions

Trim or collapse the Rules Quick Reference and Anti-Patterns tables, since references/rules.md already holds all rules with examples and anti-patterns; keep only the most critical gotchas inline and defer the rest to the reference file.

Consider moving the 'FIRST: Fetch Latest References' bash snippet into references/review.md alongside the existing retrieval section to avoid restating the same npm pack/tar command in both places.

Dimension	Reasoning	Score
Conciseness	The body is dense and avoids explaining known concepts, but the Rules Quick Reference and Anti-Patterns tables duplicate content already covered in the dedicated references/rules.md and references/review.md files, adding tokens that compete with those reference files.	2 / 3
Actionability	Provides copy-paste-ready, specific guidance throughout: a concrete npm pack/tar retrieval command, exact config rules ('Set compatibility_date to today', 'Enable the nodejs_compat flag'), and tooling commands ('npx tsc --noEmit', 'lint for no-floating-promises').	3 / 3
Workflow Clarity	The 8-step Review Workflow is clearly sequenced and includes an explicit validation checkpoint (step 7 'Validate with tools: npx tsc --noEmit, lint for no-floating-promises') with a retrieve-before-flagging feedback loop in the Principles.	3 / 3
Progressive Disclosure	Well-signaled one-level-deep references to the verified references/rules.md and references/review.md files, each described by purpose and re-pointed to from within the workflow steps, giving clear navigation off the overview body.	3 / 3
	Total	11 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 description that states concrete capabilities, includes an explicit 'Load when' trigger clause, and occupies a clear Cloudflare-Workers niche unlikely to conflict with other skills. It uses correct third-person voice with no over-claiming or padding.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Reviews and authors Cloudflare Workers code', 'writing new Workers, reviewing Worker code, configuring wrangler.jsonc') rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Reviews and authors Cloudflare Workers code against production best practices') and when ('Load when writing new Workers, reviewing Worker code...') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms a user would say ('writing new Workers', 'reviewing Worker code', 'configuring wrangler.jsonc', 'Workers anti-patterns') with good variation, not just jargon.	3 / 3
Distinctiveness Conflict Risk	The 'Cloudflare Workers' niche plus specific triggers (wrangler.jsonc, streaming, floating promises, global state) make it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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: 11c74d6

Reviewed: 17 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.