Name: netlify-ai-gateway
Rating: 70.39999999999999 (1 reviews)
Author: netlify

netlify-ai-gateway

Use OpenAI, Anthropic, Google Gemini, or OpenRouter models from Netlify Functions or Edge Functions without managing provider API keys or accounts — the gateway injects credentials automatically. Reach for this when you add an AI chatbot or completion endpoint, generate images or text with Gemini/GPT/Claude, summarize form submissions with AI, build an LLM-backed API route, stream a long AI generation, or wire up any server-side AI provider call on Netlify. Covers provider SDK setup, injected env vars, model availability, rate limits, credit costs, streaming for long generations, and local dev with netlify dev or the Vite plugin.

Quality

85%

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

75%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.

A solid, code-rich skill body with executable examples for every provider and a clear deploy sequence. The main gaps are a missing streaming code example (despite streaming being mandated) and redundancy between the 'Never do these' list and the appended house-rules section.

Suggestions

Add a concrete streaming example (SDK streaming + ReadableStream) and/or a background-function pattern — the body mandates streaming in two places but shows no streaming code, and a self-identified GAP comment confirms this gap.

Remove or de-duplicate the appended 'Netlify house rules' section, which restates the 'Never do these' warnings verbatim and adds ~25 redundant tokens; keep a single canonical guardrail list.

Consider moving the per-provider SDK code blocks or the full env-var/constraints reference into a bundled reference file so SKILL.md stays a lean overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	Mostly lean and code-driven with purposeful prose, but the appended 'Netlify house rules' section restates the top 'Never do these' warnings (browser-callable, runtime-only credentials, 60s timeout, dynamic model list), adding redundant tokens; not 5 because of that duplication, not 3 because the core body is efficient.	4 / 5
Actionability	Provides copy-paste-ready executable code for every provider SDK with install commands, a full Function example, an env-var table, a vite.config snippet, and deploy commands; held to 4 rather than 5 because streaming is mandated ('Never leave a slow generation unstreamed') yet no streaming code example is present — a noted GAP.	4 / 5
Workflow Clarity	The 'Enable & deploy' section gives a clear numbered sequence (credit plan → netlify init → deploy --prod → don't disable AI Features) with guardrails in 'Never do these'; not 5 because there are no explicit validation checkpoints or error-recovery feedback loops, though the operation is not destructive/batch so no cap applies.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections (Function example, Provider SDKs, Injected env vars, Local dev, Enable & deploy, Constraints & gotchas, Reference) with one-level-deep external doc links in the Reference section; not 5 because all content is inlined in a ~170-line SKILL.md with no bundle files, and the appended house-rules section is a structural oddity rather than a separate file.	4 / 5
	Total	16 / 20 Passed

Description

95%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: it states concrete capabilities, enumerates natural trigger phrases, and explicitly covers both what and when. The only weakness is second-person voice ('when you add…'), which costs one specificity point under the voice guideline.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'add an AI chatbot or completion endpoint, generate images or text', 'summarize form submissions with AI', 'build an LLM-backed API route', 'stream a long AI generation' — plus a coverage list (SDK setup, env vars, rate limits, credit costs), which is comprehensive; reduced from 5 to 4 for second-person voice ('Reach for this when you add…') per the voice penalty.	4 / 5
Completeness	Explicitly answers both what ('Use OpenAI, Anthropic, Google Gemini, or OpenRouter models from Netlify Functions or Edge Functions without managing provider API keys') and when ('Reach for this when you add an AI chatbot…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including synonyms and provider names users actually say — 'AI chatbot', 'completion endpoint', 'generate images or text with Gemini/GPT/Claude', 'summarize form submissions with AI', 'LLM-backed API route', 'stream a long AI generation'.	5 / 5
Distinctiveness Conflict Risk	Clear niche — server-side AI provider calls on Netlify Functions/Edge Functions with injected credentials — with distinct triggers tied to Netlify, giving minimal conflict risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: netlify/context-and-tools
Path: codex/skills/netlify-ai-gateway/SKILL.md
Commit: 47848e2

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.