accessing-mlflow

Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts (configs, logs, results), or set up the MLflow MCP server. ALWAYS triggers on mentions of MLflow, experiment results, run comparison, invocation IDs in the context of results, or MLflow MCP setup.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

100%Weight 40%Scale 1-3

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 compact, highly actionable reference: concrete MCP calls, an executable computation snippet, a clear artifacts map, and a numbered troubleshooting section, all well-organized with no unnecessary padding. It scores strongly on every dimension.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — direct MCP tool-call examples, a compact artifacts tree, and targeted gotchas (the PENDING/RUNNING exclusion note) with every token earning its place. It avoids explaining concepts Claude already knows.	3 / 3
Actionability	Provides concrete, copy-paste-ready MCP calls (search_runs_by_tags, query_runs, get_artifact_content), an executable uv/pandas snippet, and complete JSON config blocks for both Claude Code and Cursor — fully actionable rather than abstract.	3 / 3
Workflow Clarity	The query workflow is clearly sequenced (ID convention → query runs → fetch artifacts → compute in Python) and troubleshooting is a numbered checklist; the skill is read-only so no destructive/batch validation feedback loop is required, avoiding the score-2 cap.	3 / 3
Progressive Disclosure	Single self-contained file (no references/, scripts/, or assets/ bundles exist) organized into clearly headed sections (MCP Server, ID Convention, Querying Runs, Artifacts Structure, Troubleshooting) with no nested references, satisfying the well-organized-sections criterion.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 strong across all dimensions: it states concrete capabilities, includes natural trigger terms, explicitly covers both what and when, and targets a distinctive niche. No material weaknesses to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'look up runs by invocation ID', 'compare metrics across models', 'fetch artifacts (configs, logs, results)', 'set up the MLflow MCP server' — matching the score-3 anchor of several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Query and browse evaluation results stored in MLflow') and when ('Use when...', 'ALWAYS triggers on mentions of...'), with explicit triggers meeting the score-3 anchor.	3 / 3
Trigger Term Quality	Covers natural user terms users would actually say — 'MLflow', 'experiment results', 'run comparison', 'invocation IDs', 'MLflow MCP setup' — providing good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (MLflow evaluation results) with distinct triggers tied to invocation IDs and MCP setup, making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NVIDIA/Model-Optimizer
Path: .agents/skills/accessing-mlflow/SKILL.md
Commit: 33d05b0

Reviewed: 15 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.