Name: mlflow
Rating: 55.2 (1 reviews)
Author: membranedev

Blog Docs Log in Get started

mlflow

MLflow integration. Manage data, records, and automate workflows. Use when the user wants to interact with MLflow data.

Quality

62%

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/mlflow/SKILL.md

Quality

Content

67%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 body is a well-structured, actionable integration guide built around concrete Membrane CLI commands and a clear connection state machine. Its main weakness is conceptual padding (the MLflow overview) and slightly inconsistent step numbering rather than problems with actionability.

Suggestions

Remove or condense the opening "MLflow is an open-source platform..." paragraph and the "so you can focus on the integration logic" aside, since Claude already knows what MLflow is.

Show at least one action command with a realistic example value for QUERY and actionId instead of only placeholders.

Reconcile the step numbering so the "1b" / "Step 2" references map to actual numbered headers in the workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient CLI commands, but the opening paragraph explaining what MLflow is ("MLflow is an open-source platform for managing the end-to-end machine learning lifecycle...") and asides like "so you can focus on the integration logic rather than auth plumbing" explain concepts Claude already knows and could be trimmed.	3 / 5
Actionability	It provides concrete, copy-paste-ready CLI commands for install, login, connection ensure, action list/run, and proxy requests with a flags table, but placeholders like QUERY/actionId are never shown with a real example value, leaving a minor gap from a 5.	4 / 5
Workflow Clarity	There is a clear install → authenticate → connect → poll-for-ready → search → run sequence with a state-machine feedback loop (READY/BUILDING/CLIENT_ACTION_REQUIRED/CONFIGURATION_ERROR and re-poll after action), but step numbering is inconsistent (a "1b" and references to "Step 2" with no matching header), a minor gap from a 5.	4 / 5
Progressive Disclosure	The skill is a single self-contained file with well-organized section headers and no bundle files to reference, which is appropriate structure, though the proxy-options table and action-discovery details could arguably live in a reference file, keeping it just below a 5.	4 / 5
	Total	15 / 20 Passed

Description

57%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 correctly names the MLflow domain and includes an explicit "Use when" trigger, but its capability list is generic rather than tied to concrete MLflow concepts. Stronger, MLflow-specific action and trigger terms would lift it from the middle of the scale.

Suggestions

Replace generic "Manage data, records, and automate workflows" with concrete MLflow actions such as "Track experiments, log runs and parameters, register and version models, and compare model versions."

Expand trigger terms to include natural MLflow vocabulary users say: "experiments, runs, model registry, tracking, artifacts, .mlflow".

Make the "what" as concrete as the "when" so both halves of the description are equally specific.

Dimension	Reasoning	Score
Specificity	The domain (MLflow) is named, but the actions "Manage data, records, and automate workflows" are generic and not concrete MLflow capabilities (experiments, runs, models), matching the anchor for minimal/generic actions rather than the 1-2 concrete actions of a 3.	2 / 5
Completeness	Both a "what" ("Manage data, records, and automate workflows") and an explicit "Use when the user wants to interact with MLflow data" trigger are present, but the "what" is generic so it does not reach the concrete, comprehensive level of a 5.	4 / 5
Trigger Term Quality	"MLflow" and "MLflow data" are relevant natural keywords, but common variations users say (experiments, runs, models, tracking) and any file extensions are missing, fitting the some-keywords-but-missing-synonyms anchor.	3 / 5
Distinctiveness Conflict Risk	MLflow is a specific named platform with a distinct trigger ("interact with MLflow data"), giving a clear niche, but the generic action phrasing creates minor overlap risk with adjacent data-tool skills.	4 / 5
	Total	13 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: membranedev/application-skills
Path: skills/mlflow/SKILL.md
Commit: f484c82

Reviewed: 6 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.