domino-ai-gateway

Access external LLM providers through Domino AI Gateway - a secure proxy with centralized API key management, usage monitoring, and compliance. Supports OpenAI, AWS Bedrock, Azure OpenAI, Anthropic, and more. Use when calling LLMs from Domino, configuring AI Gateway endpoints, or monitoring LLM usage and costs.

1.70x

Quality

75%

Does it follow best practices?

Impact

97%

1.70x

Average score across 3 eval scenarios

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

63%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.

The body is highly actionable and well-sequenced, with executable code for every integration path and a useful error-recovery section. Its weaknesses are token efficiency (redundant Description/Activation sections and generic best-practices padding) and the absence of any progressive disclosure — everything lives in one inline file.

Suggestions

Delete the 'Description' and 'Activation' sections, which duplicate the frontmatter description and its trigger conditions verbatim.

Remove or drastically shorten the generic 'Best Practices' code (retry/backoff, logging, streaming) — these are standard OpenAI-client patterns Claude already knows; keep only the gateway-specific detail (endpoint names as the model identifier).

Move stable, bulky reference material (provider table, log format JSON, troubleshooting error catalog) into one-level-deep reference files under references/ and signal them from a concise overview section in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The 'Description' and 'Activation' sections duplicate the frontmatter almost verbatim, and the 'Best Practices' code (retry with exponential backoff, logging, streaming) teaches generic OpenAI patterns Claude already knows. Core gateway usage and API content is tight, so this lands on anchor 3 — mostly efficient with unnecessary sections that should be trimmed.	3 / 5
Actionability	Provides copy-paste-ready code for the OpenAI-compatible client, LangChain, and direct API calls, plus a curl command for the swagger spec and numbered UI steps. Minor gaps (placeholder 'your-domino.com' base URLs, 'sk-...' key placeholder) keep it at anchor 4 rather than 5.	4 / 5
Workflow Clarity	Endpoint creation has a clear numbered UI sequence and an equivalent API call; troubleshooting maps concrete error messages (401, 429, model-not-found) to remedies, and the API Reference section mandates verifying paths against the swagger before writing calls — a real validation checkpoint. No destructive/batch operations, so no cap applies; only minor validation gaps keep it below 5.	4 / 5
Progressive Disclosure	There are no bundle files — the entire ~310-line body is inline, including material that clearly belongs in separate references (log format spec, best practices, troubleshooting, full provider table). Section headers are well-organized, so it is above anchor 2's 'minimal structure', but inline content that should be split places it at anchor 3.	3 / 5
	Total	14 / 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 description: concrete capabilities, an explicit 'Use when...' trigger clause with three concrete scenarios, third-person voice, and a distinct Domino-scoped niche. Only minor gaps in capability and synonym coverage keep specificity and trigger terms below full marks.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Access external LLM providers', 'configuring AI Gateway endpoints', 'monitoring LLM usage and costs', 'centralized API key management' — with only minor gaps (e.g., cost limits and log retrieval covered in the body are absent). Fits anchor 4; not 5 because coverage is not fully comprehensive, not 3 because it goes well beyond 1-2 actions.	4 / 5
Completeness	Clearly answers both: what — 'a secure proxy with centralized API key management, usage monitoring, and compliance' — and when — explicit 'Use when calling LLMs from Domino, configuring AI Gateway endpoints, or monitoring LLM usage and costs.' Matches the anchor-5 example structure exactly.	5 / 5
Trigger Term Quality	Includes natural phrases users would say — 'calling LLMs', 'monitoring LLM usage and costs', 'AI Gateway endpoints' — plus provider names (OpenAI, AWS Bedrock, Azure OpenAI, Anthropic). Not 5 because some natural synonyms (e.g., 'chat models', specific model names like GPT-4/Gemini, Vertex AI/Cohere listed only in the body) are missing from the description itself.	4 / 5
Distinctiveness Conflict Risk	'Domino AI Gateway' names a clear niche and triggers are scoped 'from Domino', so conflict risk with generic LLM-calling skills is minimal. Distinct provider and product terms give it unique trigger vocabulary.	5 / 5
	Total	18 / 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: dominodatalab/domino-claude-plugin
Path: skills/ai-gateway/SKILL.md
Commit: 92a240b

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.