vercel-queues

Vercel Queues guidance (public beta) — durable event streaming with topics, consumer groups, retries, and delayed delivery. $0.60/1M ops. Powers Workflow DevKit. Use when building async processing, fan-out patterns, or event-driven architectures.

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.

Highly actionable reference content with excellent executable examples and clear consumer/retry semantics. The main weaknesses are a single monolithic file with no progressive disclosure to bundle files, and time-sensitive specifics embedded in the main body that will age.

Suggestions

Split detailed material (full API reference, limits table, transport details) into one-level-deep reference files under references/ and link to them from a concise SKILL.md overview.

Move or isolate time-sensitive specifics (the Feb 2026 beta date, package version, pricing) so the core guidance stays stable as the library matures.

Add an explicit local-development validation checkpoint (e.g., confirm a send round-trips through the in-process handler) to strengthen the workflow feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly lean — tables and code carry the content with little basic-concept padding — but time-sensitive specifics (Feb 27 2026 date, '@vercel/queue@^0.1.3', pricing) sit in the main body rather than a deprecated/old-patterns section, a minor staleness penalty.	4 / 5
Actionability	Fully executable, copy-paste-ready code for publishing, push consumers, vercel.json triggers, poll consumers, custom-region clients, and transports, covering the common cases.	5 / 5
Workflow Clarity	Consumer setup is clearly sequenced with acknowledge/retry semantics and a give-up policy, plus 'When to Use / When NOT to Use' decision guidance; no explicit validate→fix→retry loop, but the skill is reference-oriented rather than a destructive batch workflow.	4 / 5
Progressive Disclosure	Well-sectioned with headers and tables, but ~195 lines of API reference, limits, and examples are all inlined in a single SKILL.md with no bundle files to offload detail into one-level-deep references.	3 / 5
	Total	16 / 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 description that concisely states what Vercel Queues does and gives explicit 'Use when' triggers with natural keywords. Minor room to add action verbs and a few more synonyms, but it is clear, specific, and distinctive.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'topics, consumer groups, retries, and delayed delivery' — naming the domain plus specific features, with only minor gaps in action-level verbs.	4 / 5
Completeness	Explicitly answers both what ('durable event streaming with topics, consumer groups, retries, and delayed delivery') and when ('Use when building async processing, fan-out patterns, or event-driven architectures') with concrete trigger phrases.	5 / 5
Trigger Term Quality	'Use when building async processing, fan-out patterns, or event-driven architectures' provides good natural keyword coverage a developer would say, missing only a few synonyms.	4 / 5
Distinctiveness Conflict Risk	The Vercel Queues niche is clear and Vercel-scoped, with only minor overlap risk against closely related Workflow/Cron skills it explicitly contrasts.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: openai/plugins
Path: plugins/vercel/skills/vercel-queues/SKILL.md
Commit: 1e28582

Reviewed: 7 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.