domino-model-endpoints

Deploy and monitor model API endpoints in Domino. Covers creating prediction endpoints, version management, Grafana dashboards for latency/errors/resources, alerting, and GPU inference with NVIDIA Triton. Use when deploying models as APIs, monitoring production endpoints, or debugging endpoint issues.

Quality

82%

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

72%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.

Actionable and well-structured with strong code examples, but weakened by missing verification steps in the deploy workflow and dead references to non-existent bundle files.

Suggestions

Add a verification checkpoint after deploying (e.g., 'Confirm the endpoint returns 200 on a test prediction before relying on it') to raise workflow_clarity.

Create the referenced DEPLOY-ENDPOINT.md, MONITORING.md, and SCALING.md files, or remove the 'Related Documentation' links, so navigation is not broken.

Drop the redundant opener 'This skill provides comprehensive knowledge...' since the description already states the skill's purpose.

Dimension	Reasoning	Score
Conciseness	Largely efficient code, tables, and numbered steps, but the opener 'This skill provides comprehensive knowledge...' restates the description and could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready predict() code, a curl invocation, Dockerfile/requirements snippets, and concrete UI steps plus metric and env-var tables.	5 / 5
Workflow Clarity	A lifecycle diagram and numbered Quick Start give a clear sequence, but there are no validation checkpoints (e.g., confirming the endpoint is live before calling it).	3 / 5
Progressive Disclosure	The body is well-sectioned, but the 'Related Documentation' links to DEPLOY-ENDPOINT.md, MONITORING.md, and SCALING.md point to files that do not exist, breaking navigation.	3 / 5
	Total	15 / 20 Passed

Description

92%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, third-person description that explicitly covers both capability and trigger conditions with concrete, domain-specific actions. Adding a few synonyms (e.g., 'serving models', 'model APIs') would round out trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('creating prediction endpoints, version management, Grafana dashboards for latency/errors/resources, alerting, and GPU inference with NVIDIA Triton') with comprehensive coverage.	5 / 5
Completeness	Clearly states what it does and includes an explicit 'Use when deploying models as APIs, monitoring production endpoints, or debugging endpoint issues' trigger clause.	5 / 5
Trigger Term Quality	Natural phrases like 'deploying models as APIs', 'monitoring production endpoints', 'debugging endpoint issues' are present, but common synonyms and file/extension terms are missing.	4 / 5
Distinctiveness Conflict Risk	Domino-specific niche anchored by NVIDIA Triton and Grafana gives it distinct triggers with minimal overlap risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: dominodatalab/domino-claude-plugin
Path: skills/model-endpoints/SKILL.md
Commit: d86698d

Reviewed: 14 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.