domino-governance

Manage model risk governance in Domino using policies, bundles, and evidence. Covers creating governance bundles, attaching model artifacts and MLflow results as evidence, progressing through policy stages, and documenting findings. Use when the user mentions governance, compliance, bundles, policies, model risk management, SR 11-7, NIST AI RMF, or audit trails.

1.92x

Quality

—

Does it follow best practices?

Impact

100%

1.92x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, executable 8-step governance workflow with concrete curl examples and useful gotchas, but it loses points on duplicated setup blocks, missing per-step validation for state-changing calls, and two referenced bundle files that do not actually exist. Tightening the repeated bash and creating the referenced files would materially improve it.

Suggestions

De-duplicate the JWT/cluster-URL bash block: define it once in Configuration and reference it from the Documentation Reference section instead of repeating it verbatim.

Add explicit verification after each state-changing call (e.g., re-GET the bundle after PATCH/POST to confirm status changed, or check the HTTP response) to satisfy the validation-checkpoint expectation for risky operations.

Create the referenced BUNDLE-LIFECYCLE.md and EVIDENCE-WORKFLOW.md files (or remove the links) so progressive-disclosure navigation actually resolves.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete curl commands and a compact API table, but the JWT/cluster-URL bash block is duplicated verbatim in both Configuration and Documentation Reference, and the cluster-URL caveat repeats. Not a 3 due to this redundant padding; not a 1 because the bulk is lean and actionable.	2 / 3
Actionability	Provides fully executable curl commands with real field names and concrete JSON payloads (e.g., the ModelVersion/Report attachment bodies and submit-result-to-policy call), copy-paste ready. Not a 2 because nothing is pseudocode or missing key details.	3 / 3
Workflow Clarity	A clear 8-step sequence with helpful gotchas (EvidenceSet IDs not in bundle response; use policyId not policyVersionId), but state-changing calls (PATCH stage status, POST findings, POST attachments) lack explicit per-step validation/verification checkpoints. Per the rubric, missing validation for risky/batch operations caps this at 2; not a 1 because steps are clearly ordered.	2 / 3
Progressive Disclosure	Signals one-level-deep references to BUNDLE-LIFECYCLE.md and EVIDENCE-WORKFLOW.md, but neither file exists in the bundle (references/ is empty), so the navigation is broken; and the full JWT/cluster-URL setup and API reference are inline rather than split out. Not a 1 because references are at least clearly signaled; not a 3 due to missing target files and inline-heavy structure.	2 / 3
	Total	9 / 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, comprehensive, and includes an explicit 'Use when' trigger clause with natural, distinctive keywords grounded in the model-risk-governance domain. It cleanly satisfies all four dimensions with no vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'creating governance bundles, attaching model artifacts and MLflow results as evidence, progressing through policy stages, and documenting findings' — matching the multiple-specific-actions anchor. Not a 2 because it is comprehensive rather than naming only some actions.	3 / 3
Completeness	Explicitly answers what (governance via policies/bundles/evidence with named sub-actions) and when ('Use when the user mentions ...'). Not a 2 because the 'Use when' clause is explicit, not implied.	3 / 3
Trigger Term Quality	Provides good natural coverage users would say — 'governance, compliance, bundles, policies, model risk management, SR 11-7, NIST AI RMF, or audit trails'. Not a 2 because it spans common variations rather than a single phrase.	3 / 3
Distinctiveness Conflict Risk	Clear niche (Domino model risk governance, regulatory frameworks SR 11-7 / NIST AI RMF) with distinctive triggers unlikely to fire for unrelated skills. Not a 2 because the domain-specific terms strongly differentiate it.	3 / 3
	Total	12 / 12 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
Commit: 64f4433

Reviewed: 1 day 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.