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.

Quality

74%

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

Fix and improve this skill with Tessl

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

Quality

Content

65%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 comprehensive executable examples, but it is a large monolithic file with redundant sections and time-sensitive detail that should be split into one-level-deep reference files and tightened for token efficiency.

Suggestions

Split stable-but-bulk sections (Audit Logging, Claude Code Compatibility, Pricing/Latest Model Availability) into one-level-deep reference files linked from SKILL.md to improve progressive disclosure and reduce base context cost.

Remove redundant decision aids — collapse 'Key Benefits', 'When to Use AI Gateway', and the 'Gateway vs Direct Provider' decision tree into a single concise section.

Move time-sensitive pricing and model-add dates into a clearly labeled 'deprecated/old patterns' or separate changelog file so they do not penalize conciseness and signal staleness explicitly.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code and tables, but overlapping sections ('Key Benefits', 'When to Use AI Gateway', 'Gateway vs Direct decision tree') and time-sensitive info (pricing table, 'added March 5, 2026') not in a deprecated section add avoidable tokens, fitting the 'mostly efficient but some unnecessary explanation' anchor.	3 / 5
Actionability	Abundant copy-paste-ready, executable TypeScript (generateText, gateway(), providerOptions, APICallError handling) and curl commands covering the common cases across routing, auth, caching, rate limiting, and errors, matching the top anchor.	5 / 5
Workflow Clarity	Setup and auth present numbered sequences (vercel link -> env pull; OIDC steps 1-4) but lack explicit validation checkpoints, fitting 'steps listed but validation gaps'; no destructive ops trigger the cap, but checkpoints are genuinely absent.	3 / 5
Progressive Disclosure	Well-organized section headers, but a ~570-line monolith with no reference files; audit logging, Claude Code compatibility, and pricing/model-availability content that could be split into separate files is all inlined, fitting 'some structure but content that should be separate is inline'.	3 / 5
	Total	14 / 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, concise description that clearly states both what the skill does and when to use it with concrete trigger phrases. Minor room to improve distinctiveness against the related ai-sdk skill and trim 'expert guidance' fluff.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities ('configuring model routing, provider failover, cost tracking, or managing multiple AI providers'), matching the 'several specific actions; minor gaps' anchor; not 5 because 'expert guidance' is mild fluff and coverage is not exhaustive.	4 / 5
Completeness	Explicitly states what it does ('Vercel AI Gateway expert guidance ... through a unified API') and gives an explicit 'Use when' clause with concrete trigger phrases, matching the top anchor for both what and when.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('model routing', 'provider failover', 'cost tracking', 'multiple AI providers', 'unified API') — good coverage but missing common synonyms, fitting the 'good keyword coverage; a few natural terms missing' anchor.	4 / 5
Distinctiveness Conflict Risk	Names the specific product 'Vercel AI Gateway' (clear niche) but 'managing multiple AI providers through a unified API' overlaps with the related ai-sdk skill (chainTo confirms), so minor overlap risk keeps it at 4 rather than 5.	4 / 5
	Total	17 / 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 (672 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: joelhooks/joelclaw
Path: skills/ai-gateway/SKILL.md
Commit: 7094ced

Reviewed: 3 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.