Name: netlify-ai-gateway
Rating: 75.2 (1 reviews)
Author: netlify

netlify-ai-gateway

Reference for Netlify AI Gateway — the managed proxy that routes calls to OpenAI, Anthropic, and Google Gemini SDKs without provider API keys. Use this skill any time the user wants to add AI on a Netlify site (chat, completion, reasoning, image generation, image-to-image edit/stylize), choose or change a model, wire up the OpenAI / Anthropic / @google/genai SDK, decide which provider to use for an image-gen feature (it's Gemini-only on the gateway), or debug "model not found" / "API key missing" against the gateway. Required reading before pinning a model — the gateway exposes a curated subset, not every provider model.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

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 executable code and clear, checkpointed workflows. Its only real weakness is conciseness: the large inline dated model list and verification date are time-sensitive content that will bloat and stale the skill.

Suggestions

Move the dated version strings and 'Verified 2026-04-30' note into a clearly-marked deprecated/old-patterns section, or pull the full model registry into a referenced file so the body stays lean.

Trim dated model variants (e.g. the '-2026-03-05' snapshots) to just the canonical names unless a dated pin is load-bearing, reducing staleness risk.

Consider extracting the Available Models table into references/available-models.md and signaling it from the body, improving progressive disclosure and keeping the core skill terse.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean, but the inline Available Models list carries many dated version numbers (e.g. 'gpt-5.4-2026-03-05', 'gpt-5.4-pro-2026-03-05') and a 'Verified 2026-04-30' date — time-sensitive information not placed in a deprecated/old-patterns section, which the rubric penalizes.	2 / 3
Actionability	Provides fully executable TypeScript examples with 'npm install' commands for OpenAI, Anthropic, @google/genai, Netlify Functions, text-to-image, and image-to-image — copy-paste ready.	3 / 3
Workflow Clarity	The Setup section gives a clear numbered sequence (enable AI, deploy to production, install SDK) with an explicit first-deploy checkpoint, and Errors & Troubleshooting supplies error→cause→fix feedback loops.	3 / 3
Progressive Disclosure	Single-file skill with well-organized sections and one clearly-signaled external reference ('see netlify-blobs/SKILL.md'); no nested references and no bundle files to mismanage.	3 / 3
	Total	11 / 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 specific, trigger-rich, and clearly answers both what the skill does and when to use it, all in third person. It is a strong, low-conflict trigger description with no notable weaknesses.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'routes calls to OpenAI, Anthropic, and Google Gemini SDKs without provider API keys', 'add AI on a Netlify site (chat, completion, reasoning, image generation, image-to-image edit/stylize)', 'choose or change a model', 'wire up the...SDK', and 'debug "model not found" / "API key missing"'.	3 / 3
Completeness	Explicitly states what ('managed proxy that routes calls to...SDKs without provider API keys') and when ('Use this skill any time the user wants to add AI on a Netlify site...'), satisfying both halves with explicit triggers.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'add AI on a Netlify site', 'image-to-image edit/stylize', 'choose or change a model', and 'debug "model not found" / "API key missing"' — matching the rubric's good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Tightly scoped to the Netlify AI Gateway with provider-specific and feature-specific triggers ('Gemini-only on the gateway'), making it unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
Commit: a1d397b

Reviewed: about 19 hours 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.