CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

88

1.92x
Quality

Does it follow best practices?

Impact

100%

1.92x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Evaluation results

100%

49%

Setting Up a Governance Bundle for a Credit Risk Model

Governance bundle setup with evidence submission

Criteria
Without context
With context

JWT token fetch

0%

100%

Cluster URL from JWT

0%

100%

Correct BASE URL

25%

100%

Policy discovery

100%

100%

Bundle creation fields

37%

100%

Bundle ID saved

100%

100%

EvidenceSet from policy

58%

100%

policyId not policyVersionId

100%

100%

Evidence submit endpoint

100%

100%

Evidence content format

0%

100%

Bearer auth on all calls

0%

100%

No hardcoded UUIDs

100%

100%

100%

26%

Attaching Model Artifacts to a Governance Bundle

Correct attachment types and identifier formats

Criteria
Without context
With context

JWT URL derivation

0%

100%

ModelVersion type

100%

100%

ModelVersion identifier format

100%

100%

Report type

100%

100%

Report identifier format

50%

100%

Commit hash from git

100%

100%

No invalid types

100%

100%

Attachment endpoint

100%

100%

Multiple file attachments

100%

100%

Bearer auth

42%

100%

Token fetch method

0%

100%

100%

68%

Documenting Validation Findings for a Mortgage Risk Model

Creating findings with correct IDs and severity

Criteria
Without context
With context

JWT URL derivation

0%

100%

policyVersionId not policyId

0%

100%

policyVersionId from bundle

0%

100%

Approver from stageApprovals

0%

100%

Assignee from bundle

37%

100%

name AND title both present

0%

100%

Valid severity levels

25%

100%

Critical severity used

25%

100%

Multiple severity levels

87%

100%

Findings endpoint

100%

100%

Finding description field

100%

100%

Bearer auth

100%

100%

Repository
dominodatalab/domino-claude-plugin
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.