Name: ai-gateway
Rating: 90.4 (1 reviews)
Author: vercel

ai-gateway

Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.

1.58x

Quality

—

Does it follow best practices?

Impact

100%

1.58x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

77%

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, executable code and well-sequenced workflows, but it is too long for one file and includes marketing/time-sensitive padding that could be trimmed or split. Progressive disclosure suffers from the monolithic structure with no external reference files.

Suggestions

Trim or remove the marketing-style "Key Benefits" and "Pricing" sections, or move verbatim pricing/date details into a separate reference file, to reduce verbosity and time-sensitive content.

Split detailed reference material (routing options, cache-control strategies, audit logging, Claude Code compatibility, error handling templates) into separate files under references/ and link to them from a concise overview, improving progressive disclosure.

Move the "added March 5, 2026" date and other version-specific details into a clearly marked changelog or deprecated-section so they don't penalize conciseness as they age.

Dimension	Reasoning	Score
Conciseness	The ~570-line body is mostly useful but carries marketing-style padding ("Key Benefits", "Pricing" fluff) and time-sensitive content ("added March 5, 2026") outside any deprecated section, which the rubric penalizes.	2 / 3
Actionability	Abundant executable TypeScript/bash snippets (generateText, gateway(), providerOptions, error handling switch, streaming, image generation) with real model slugs that are copy-paste ready.	3 / 3
Workflow Clarity	Multi-step processes (authentication setup, auth priority order, error handling template, decision tree) are clearly sequenced, with the gateway.getAvailableModels() checkpoint and status-code feedback loops; operations are call-based rather than destructive.	3 / 3
Progressive Disclosure	All content lives in a single 570-line file with no bundle reference files (references/, scripts/, assets/ absent); detailed reference material (routing tables, caching, audit logging, Claude Code compat) that should be split out is inline.	2 / 3
	Total	10 / 12 Passed

Description

100%

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

The description is concise, third person, and explicitly covers both the capability set and the trigger conditions. It lists concrete actions and natural trigger terms with a clear niche. No changes needed.

Dimension	Reasoning	Score
Specificity	"configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API" lists multiple specific concrete actions within the AI Gateway domain.	3 / 3
Completeness	It clearly answers what ("Vercel AI Gateway expert guidance" plus the enumerated capabilities) and when ("Use when configuring model routing, provider failover, cost tracking...").	3 / 3
Trigger Term Quality	Natural terms users would say ("model routing", "provider failover", "cost tracking", "multiple AI providers") are covered well alongside an explicit "Use when..." trigger.	3 / 3
Distinctiveness Conflict Risk	Scoped specifically to the Vercel AI Gateway with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (666 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	12 / 16 Passed

Repository: vercel/vercel-plugin
Commit: 5f3f0ad

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.