← Back to Skills Marketplace
Mlflow
by
Vlad Ursul
· GitHub ↗
· v1.0.1
· MIT-0
133
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install mlflow
Description
MLflow integration. Manage data, records, and automate workflows. Use when the user wants to interact with MLflow data.
Usage Guidance
This skill delegates MLflow access through the Membrane service and its CLI. Before installing or using it: verify the CLI package (@membranehq/cli) is the official package you intend to install; be aware npm install -g executes code from the npm registry; you will perform an interactive login that authorizes Membrane to access your resources — review Membrane's privacy/security documentation and the permissions requested when connecting your MLflow instance. Do not share local API keys with the agent; follow the SKILL.md flow (create a Membrane connection) so Membrane handles credentials. If you need higher assurance, review what actions are created on Membrane and audit any created action's configuration and logs.
Capability Analysis
Type: OpenClaw Skill
Name: mlflow
Version: 1.0.1
The skill bundle provides instructions for an AI agent to manage MLflow workflows using the Membrane platform and its CLI tool (@membranehq/cli). The SKILL.md file outlines standard procedures for authentication, connection management, and action execution without any evidence of malicious intent, data exfiltration, or harmful prompt injection.
Capability Assessment
Purpose & Capability
The name/description (MLflow integration) match the instructions, which direct the agent/user to create a Membrane connection for the mlflow connector and run actions against it. Relies on Membrane as an integration proxy, which is a coherent design choice for this purpose.
Instruction Scope
SKILL.md confines actions to installing/using the Membrane CLI, logging in, creating a connection, listing/searching/creating/running Membrane actions, and polling action build state. It does not instruct reading unrelated files, exporting arbitrary environment variables, or exfiltrating data to unexpected endpoints beyond Membrane.
Install Mechanism
No formal install spec is present in the registry metadata, but the README instructs users to run an npm global install (npm install -g @membranehq/cli@latest) and also suggests npx usage. npm is a normal distribution channel but has moderate risk compared to curated package managers; users should verify the package source (official @membranehq) before installing.
Credentials
The skill requests no environment variables or credentials in metadata and instead relies on interactive Membrane login (OAuth-like flow). This matches the stated preference to let Membrane manage credentials server-side and is proportionate to the stated purpose.
Persistence & Privilege
The skill does not request always:true and is user-invocable; it does not ask to modify other skills or system configuration. Autonomous invocation is allowed (platform default) but not combined with other concerning flags.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mlflow - After installation, invoke the skill by name or use
/mlflow - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Auto sync from membranedev/application-skills
v1.0.0
Auto sync from membranedev/application-skills
Metadata
Frequently Asked Questions
What is Mlflow?
MLflow integration. Manage data, records, and automate workflows. Use when the user wants to interact with MLflow data. It is an AI Agent Skill for Claude Code / OpenClaw, with 133 downloads so far.
How do I install Mlflow?
Run "/install mlflow" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Mlflow free?
Yes, Mlflow is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Mlflow support?
Mlflow is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Mlflow?
It is built and maintained by Vlad Ursul (@gora050); the current version is v1.0.1.
More Skills