Name: ai-gateway
Rating: 75.97 (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.

1.54x

Quality

79%

Does it follow best practices?

Impact

85%

1.54x

Average score across 2 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ai-gateway/SKILL.md

Quality

Content

71%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 with excellent executable examples, but it is over-long and monolithic: redundant summary sections and detail-heavy reference material are inlined in SKILL.md rather than split into one-level-deep bundle files.

Suggestions

Consolidate or remove redundant summary sections ('Key Benefits', 'When to Use AI Gateway' table) that restate the Overview and the Gateway-vs-Direct Decision Tree.

Move detail-heavy reference material (audit logging, pricing, the full supported-providers list, Claude Code compatibility) into separate bundle files under references/ and link to them one level deep, leaving SKILL.md as a lean overview.

Group time-sensitive version/date information (model slugs, 'Latest Model Availability' dates) into a single clearly labeled current/deprecated section so stale entries are easy to find and update.

Dimension	Reasoning	Score
Conciseness	Most content is library-specific rather than general knowledge Claude already has, but the ~570-line body has clear redundancy — 'Key Benefits' restates the Overview, the 'When to Use AI Gateway' table restates the Decision Tree, and version/date-laden sections (e.g. 'Latest Model Availability') are scattered rather than consolidated into a deprecated/old-patterns section.	3 / 5
Actionability	Dense with copy-paste-ready, executable examples covering the common cases — generateText with plain provider/model strings, gateway() routing with providerOptions, OIDC setup via vercel env pull, rate-limit/budget error handling, and Claude Code env-var configuration.	5 / 5
Workflow Clarity	Setup and auth are clearly sequenced (vercel link → enable in dashboard → vercel env pull) and error handling is concrete with status-code switches, but there are no explicit validation checkpoints; this is acceptable since the operations are non-destructive.	4 / 5
Progressive Disclosure	Good section headers and external doc links provide structure, but everything is inlined into one monolithic file — audit logging details, pricing, full provider lists, and Claude Code compatibility are content that clearly belongs in separate reference files, and no bundle files are provided.	3 / 5
	Total	15 / 20 Passed

Description

87%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 cleanly states both the capability and concrete usage triggers with low conflict risk. The only weakness is slightly incomplete action coverage relative to the full body.

Dimension	Reasoning	Score
Specificity	Names the domain ('Vercel AI Gateway') and several concrete actions — 'configuring model routing, provider failover, cost tracking, or managing multiple AI providers' — but omits capabilities covered in the body (OIDC auth, image generation, audit logging), so it is not fully comprehensive.	4 / 5
Completeness	Explicitly answers both 'what' ('Vercel AI Gateway expert guidance... through a unified API') and 'when' ('Use when configuring model routing, provider failover, cost tracking...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural developer-facing phrases like 'model routing', 'provider failover', 'cost tracking', and 'multiple AI providers' that a user would plausibly say, but lacks synonyms or file/extension-style variations that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	'Vercel AI Gateway' is a specific, well-scoped niche and the triggers (unified API, provider failover, model routing) are gateway-specific, giving minimal overlap risk with adjacent skills.	5 / 5
	Total	18 / 20 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
Path: skills/ai-gateway/SKILL.md
Commit: 93a4de9

Reviewed: 6 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.