Name: ai-gateway
Rating: 85.6 (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.

A thorough, highly actionable gateway reference with executable code, feedback loops, and a clear decision tree. Its main weaknesses are length/redundancy and a monolithic structure that keeps reference material inline instead of splitting it into bundled files.

Suggestions

Move stable reference material (provider list, pricing, latest-model availability table, full routing/cache option tables) into a bundled references/ file and keep SKILL.md as a concise overview with one-level-deep links.

Tighten repeated generateText scaffolding: show the providerOptions.gateway block once and reference it, rather than re-emitting the full call in the cache, rate-limit, budget, and error sections.

Consolidate the scattered error-handling snippets into the single complete template and have per-status sections link to it instead of restating the try/catch wrapper.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient and gateway-specific rather than explaining basics Claude knows, but at ~570 lines it carries redundancy (repeated generateText scaffolding across sections, overlapping error-handling examples) and could be tightened, matching the "mostly efficient but could be tightened" anchor rather than the lean anchor.	2 / 3
Actionability	Provides fully executable TypeScript snippets, concrete shell commands (vercel link, vercel env pull, curl), exact model slugs, and copy-paste-ready config blocks, matching the fully-executable anchor.	3 / 3
Workflow Clarity	The auth setup is a numbered sequence and the error-handling sections supply explicit feedback loops (catch 429 with retry-after, 402 fallback, status-code switch template) plus a decision tree, matching the clear-sequence-with-feedback-loops anchor.	3 / 3
Progressive Disclosure	Sections are well-organized but the entire reference (API options, pricing, model availability, provider list, error templates) lives inline in one ~570-line file with no bundle files to offload detail into, matching the "content that should be separate is inline" anchor rather than a one-level-deep reference structure.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 states concrete capabilities and an explicit "Use when" trigger, clearly scoping the skill to Vercel AI Gateway. It could add natural synonyms like "LLM gateway" or "AI proxy" to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API" — matching the anchor for multiple specific concrete actions rather than a single named domain.	3 / 3
Completeness	Explicitly answers what ("Vercel AI Gateway expert guidance" plus the routing/failover/cost actions) and when via a clear "Use when configuring..." clause, satisfying both halves with an explicit trigger.	3 / 3
Trigger Term Quality	Relevant keywords (model routing, provider failover, cost tracking, AI providers) are present and natural for developers, but common variations a user might say (LLM gateway, AI proxy) are absent, matching the "some relevant keywords but missing common variations" anchor.	2 / 3
Distinctiveness Conflict Risk	The "Vercel AI Gateway" niche with provider-routing/failover triggers is clearly scoped and unlikely to fire for unrelated skills, matching the clear-niche anchor.	3 / 3
	Total	11 / 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: a0eb377

Reviewed: 36 minutes 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.