domino-model-serving

Deploy, invoke, and retire Domino model APIs and registered models via REST. Covers modelServing lifecycle, registered-models v1 vs v2 paths, MLflow tracking vs registry API, inference URLs vs management API, and GenAI endpoint vanity URLs. Use when automating model deployment, predictions, registry updates, or debugging stop/archive/delete behavior.

Quality

89%

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

86%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.

An efficient, well-structured overview that demonstrates strong domain judgment (v1-vs-v2 registered-model paths, management vs inference URLs, stop/archive/delete distinctions) with real validation guidance around destructive operations. The main gaps are the absence of executable POST/invoke examples and an explicit failed-deployment recovery path.

Suggestions

Add a copy-paste-ready POST example (with a minimal JSON body) for creating a model API or registering a model, mirroring the existing curl snippet, so the deployment half of the lifecycle is as executable as the list/poll half.

Include one concrete invoke example against the 'url' field so the inference-path auth guidance ('use the model API token documented on docs.domino.ai') becomes actionable rather than deferred.

Add a short error-recovery branch to the lifecycle: when status is Failed, name where to look (e.g., version events/logs endpoint) before re-attempting, closing the feedback loop.

Dimension	Reasoning	Score
Conciseness	Lean, table-driven, and assumes Claude's competence — it never explains what REST, MLflow, or a model registry is, and every line carries non-obvious operational knowledge ("modelName ... is the registered model name string, not an opaque UUID"). Matches the 'every token earns its place' anchor; nothing to trim for a 4.	5 / 5
Actionability	Concrete route paths, one executable curl with a conditional ${TOKEN:+...} header, and poll-until-Running guidance make this mostly executable. But only one code snippet appears: no POST example or request body for registering/deploying, no invoke example, and the invocation-auth section defers to 'confirm in API-SPECS.md before hardcoding' rather than giving the concrete command.	4 / 5
Workflow Clarity	The six-step lifecycle includes real checkpoints for destructive ops — 'Treat DELETE ... as best-effort; verify resource gone before assuming cleanup' and 'poll status instead of fire-and-forget retry loops' — so the destructive-operation cap does not apply. It falls short of a 5 because there is no explicit error-recovery loop (e.g., what to inspect or do when status is Failed).	4 / 5
Progressive Disclosure	The body is a genuine overview that pushes route catalogs and detail to clearly signaled, one-level-deep references ('Details and route list: API-MODEL-SERVING.md') plus a Related documentation section, with no inlined walls of API reference. No bundle files exist under the skill's own references/scripts/assets directories, but the split-and-point structure fully fits the top anchor.	5 / 5
	Total	18 / 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 description: concrete third-person action verbs, an explicit and specific 'Use when' clause, and a well-delineated niche. The only weakness is a jargon-tilted what-clause that misses a few natural synonyms a user might say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("Deploy, invoke, and retire Domino model APIs and registered models via REST") and comprehensively enumerates coverage areas: "modelServing lifecycle, registered-models v1 vs v2 paths, MLflow tracking vs registry API, inference URLs vs management API, and GenAI endpoint vanity URLs". No significant coverage gaps remain to justify a 4.	5 / 5
Completeness	Explicitly answers both: what ("Deploy, invoke, and retire Domino model APIs and registered models via REST" plus enumerated scope) and when ("Use when automating model deployment, predictions, registry updates, or debugging stop/archive/delete behavior"). Matches the top anchor exactly.	5 / 5
Trigger Term Quality	The 'Use when' clause carries natural phrases users would say ("automating model deployment, predictions, registry updates, or debugging stop/archive/delete behavior"), but the what-clause leans on API jargon ("modelServing lifecycle", "GenAI endpoint vanity URLs") and misses common synonyms like 'host a model' or 'model endpoint'. Good coverage with a few natural terms missing, so 4 rather than 5.	4 / 5
Distinctiveness Conflict Risk	A clearly fenced niche — Domino-platform REST automation — explicitly distinguished from MLflow tracking and (via the body) UI endpoint monitoring. Trigger phrases (deployment automation, predictions, registry updates, stop/archive/delete) are unlikely to pull in the wrong skill.	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: 10 suspicious	Warning

	Total	15 / 16 Passed

Repository: dominodatalab/domino-claude-plugin
Path: skills/domino-model-serving/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.