domino-modeling-assistant

Enable AI-assisted model development within Domino by writing needed model and training code and using MCP (Model Context Protocol) servers to execute domino jobs. AI coding assistants like Cursor and GitHub Copilot can execute commands as Domino jobs, maintaining security, governance, and reproducibility. Use when setting up AI code assistants to work with Domino, configuring MCP servers, or enabling vibe modeling workflows.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/modeling-assistant/SKILL.md

Quality

Content

71%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.

The content is efficient, actionable, and provides a clear operational workflow with most validation checkpoints present. Its main weakness is progressive disclosure: several referenced files (SETUP.md, mcp-servers/domino_mcp_server/) are cited but missing from the bundle, breaking navigation.

Suggestions

Add the missing referenced files (SETUP.md and the mcp-servers/domino_mcp_server/ bundle) or remove the broken references so navigation is intact.

Make job-run validation explicit as a validate->fix->retry loop rather than implicit 'always check' phrasing, since running jobs and file sync are batch/stateful operations.

Provide at least one short copy-paste example (e.g., a minimal run_domino_job call and a status-check snippet) to lift actionability from good to fully executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly dense, operational guidance with little padding, though a few explanatory sentences (e.g., the 'Vibe modeling refers to...' intro) could be trimmed; matches 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Concrete, actionable guidance throughout: a 10-tool MCP table, specific env vars (DOMINO_API_KEY, DOMINO_HOST, DOMINO_PROJECT_NAME), and exact paths (/mnt/data/, /domino/datasets/*), with only minor gaps and no copy-paste code examples.	4 / 5
Workflow Clarity	A clear multi-step sequence is present (detect environment -> check sync/uncommitted state -> run as jobs -> check status/results -> explain/share mlflow URLs) with most checkpoints explicit, though validation loops are implicit rather than crisp validate->fix->retry.	4 / 5
Progressive Disclosure	References are one-level-deep and clearly signaled ([SETUP.md], mcp-servers/domino_mcp_server/), but the referenced SETUP.md and mcp-servers/ bundle files do not exist in the skill bundle, so navigation is broken and organization is only partially effective.	3 / 5
	Total	15 / 20 Passed

Description

87%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.

The description is specific, complete, and clearly distinct, with explicit 'what' and 'when' clauses and concrete trigger phrases. The only slight weakness is trigger-term coverage could include more synonyms or natural variations.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions (writing model/training code, executing domino jobs via MCP servers, configuring MCP servers) with only minor coverage gaps around data analysis and results handling, matching the 'several specific actions; minor gaps' anchor.	4 / 5
Completeness	Explicitly answers both 'what' (enable AI-assisted model development via model/training code and MCP-executed domino jobs) and 'when' ('Use when setting up AI code assistants to work with Domino, configuring MCP servers, or enabling vibe modeling workflows') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage ('AI code assistants', 'Cursor and GitHub Copilot', 'configuring MCP servers', 'vibe modeling workflows') but missing common synonyms or file-style triggers, so it sits just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The Domino Data Lab + MCP + AI coding-assistant niche is highly specific with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 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: 2 missing	Warning

	Total	15 / 16 Passed

Repository: dominodatalab/domino-claude-plugin
Path: skills/modeling-assistant/SKILL.md
Commit: d86698d

Reviewed: 15 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.