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.
68
82%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
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 an excellent skill description that clearly defines its scope within Domino's model risk governance domain. It lists specific concrete actions, provides comprehensive trigger terms spanning both common and regulatory-specific language, and explicitly states when to use the skill. The description is concise, well-structured, and highly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating governance bundles, attaching model artifacts and MLflow results as evidence, progressing through policy stages, and documenting findings. | 3 / 3 |
Completeness | Clearly answers both 'what' (manage model risk governance with policies, bundles, evidence, creating bundles, attaching artifacts, progressing stages, documenting findings) and 'when' with an explicit 'Use when...' clause listing specific trigger terms. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: governance, compliance, bundles, policies, model risk management, SR 11-7, NIST AI RMF, audit trails. These span both general and domain-specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: model risk governance specifically in Domino, with domain-specific triggers like SR 11-7, NIST AI RMF, governance bundles, and MLflow results that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable governance skill with executable curl commands for every step and useful gotcha callouts. Its main weaknesses are moderate verbosity (duplicated configuration block, conceptual definitions Claude doesn't need), and the absence of validation/error-recovery steps in a multi-step workflow involving API calls that can fail. The progressive disclosure structure is reasonable but the main file is heavy with content that could be offloaded.
Suggestions
Add validation checkpoints after key steps (e.g., verify bundle creation succeeded by checking the response, confirm attachment was added by re-inspecting the bundle, handle error responses from stage progression).
Remove the duplicated configuration/token block in the 'Documentation Reference' section — it's identical to the one at the top.
Trim or remove the 'Key Concepts' section — Claude can infer what policies, bundles, evidence, and findings are from the API usage context; at most keep one-line definitions.
Move the full 8-step workflow into BUNDLE-LIFECYCLE.md and keep only a condensed summary (steps + one-liner descriptions) in the main SKILL.md to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary explanations (e.g., defining what a policy, bundle, evidence, and finding are conceptually when Claude can infer these), and the configuration block is duplicated in the 'Documentation Reference' section at the bottom. The API reference table and workflow steps are reasonably efficient, but the overall document could be tightened by ~20-30%. | 2 / 3 |
Actionability | Every step includes fully executable curl commands with proper headers, JSON payloads, and variable references. Key gotchas are called out explicitly (e.g., 'Use policyId NOT policyVersionId', evidenceSet IDs not in bundle response). The commands are copy-paste ready with clear placeholder values. | 3 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced and logically ordered, with important callouts like Step 6a's discovery requirement. However, there are no explicit validation checkpoints or error-recovery feedback loops — for instance, no guidance on verifying that an attachment was successfully added, that evidence submission succeeded, or what to do if a stage transition fails. | 2 / 3 |
Progressive Disclosure | The skill references BUNDLE-LIFECYCLE.md and EVIDENCE-WORKFLOW.md for deeper details, which is good progressive disclosure. However, no bundle files were provided, so we can't verify these exist. Additionally, the main SKILL.md is quite long (~180 lines) and inlines substantial detail (the full 8-step workflow, API reference table, UI navigation, and documentation reference) that could be better distributed across referenced files. | 2 / 3 |
Total | 9 / 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.