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.
61
71%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/ai-gateway/SKILL.mdQuality
Discovery
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.
This is a strong skill description that clearly articulates what the skill does (proxy access to LLM providers with key management, monitoring, and compliance), names specific supported providers, and provides explicit trigger guidance. It uses proper third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete capabilities: accessing external LLM providers, centralized API key management, usage monitoring, compliance, and configuring endpoints. It names specific providers (OpenAI, AWS Bedrock, Azure OpenAI, Anthropic) which adds concreteness. | 3 / 3 |
Completeness | Clearly answers both 'what' (access external LLM providers through Domino AI Gateway with key management, monitoring, compliance) and 'when' (explicit 'Use when calling LLMs from Domino, configuring AI Gateway endpoints, or monitoring LLM usage and costs'). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'LLM', 'AI Gateway', 'Domino', 'OpenAI', 'AWS Bedrock', 'Azure OpenAI', 'Anthropic', 'API key', 'usage monitoring', 'costs'. These are terms users would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with the specific niche of 'Domino AI Gateway' as a proxy for LLM providers. The combination of Domino platform context, specific provider names, and gateway-specific functions makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at actionability with multiple concrete, executable code examples covering various integration patterns. However, it is significantly bloated with explanatory content Claude doesn't need (what a gateway is, provider tables, security concepts), and everything is crammed into a single file with no progressive disclosure. Trimming to essential setup + usage code with references to external docs for details would dramatically improve token efficiency.
Suggestions
Remove or drastically reduce the 'What is AI Gateway?', 'Supported LLM Providers' table, 'Security', and 'Cost Management' sections — these explain concepts Claude already knows or can find in the linked docs.
Split detailed content (best practices, troubleshooting, monitoring) into separate bundle files and reference them from a concise SKILL.md overview.
Add a validation step after endpoint creation (e.g., 'Verify the endpoint works: send a test request and confirm a 200 response') to improve workflow clarity.
Consolidate the three usage examples (OpenAI, LangChain, Direct API) — show one primary pattern inline and reference others in a separate file to reduce the monolithic structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Significant verbosity throughout: explains what AI Gateway is (Claude knows proxy/gateway concepts), lists supported providers in a table (easily looked up), explains basic concepts like access control and security that don't add actionable value. The 'What is AI Gateway?' section, supported providers table, security section, and much of the monitoring/cost management sections are padding. The skill is ~200+ lines when it could be under 80. | 1 / 3 |
Actionability | Provides fully executable, copy-paste-ready code examples for multiple integration patterns (OpenAI client, LangChain, direct API, streaming, retry logic). The endpoint creation via API and usage examples are concrete with real imports, URLs, and JSON payloads. | 3 / 3 |
Workflow Clarity | The endpoint creation steps are clearly sequenced (both UI and API), and troubleshooting covers common errors. However, there are no validation checkpoints — e.g., after creating an endpoint, there's no step to verify it works; after configuring access control, no verification step. The workflow for going from setup to usage is implicit rather than explicitly sequenced. | 2 / 3 |
Progressive Disclosure | Everything is in a single monolithic file with no bundle files to reference. Content that should be split out (provider table, full code examples for each integration pattern, troubleshooting, log format details, best practices) is all inline, creating a wall of text. The external doc links at the end are helpful but the body itself is not structured for progressive disclosure. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- dominodatalab/domino-claude-plugin
- Commit
47c6e0a
- Reviewed
Table of Contents
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.