What is zenml-quick-wins?

A guide for adding ZenML practices to machine-learning operations, such as recording run details, tracking experiments, setting alerts and schedules, managing secrets, handling streaming events, and configuring model governance.

Use it to implement metadata logging, experiment tracking, alerts, schedules, triggers, secrets, streaming events, and the ZenML Model Control Plane.

It helps teams put repeatable controls around ML workflows so runs, models, credentials, and operational events are easier to manage.

zenml-quick-wins — Plugin for Claude Code by zenml-io: A guide for adding ZenML practices to machine-learning operations…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add zenml-io/skills

agentmods

npx agentmods add plugins/zenml-io/skills/zenml-quick-wins

Clone the repo

git clone --depth 1 https://github.com/zenml-io/skills

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/zenml-io/skills/zenml-quick-wins.svg)](https://agentmods.dev/plugins/zenml-io/skills/zenml-quick-wins)

Your own site

<a href="https://agentmods.dev/plugins/zenml-io/skills/zenml-quick-wins"><img src="https://agentmods.dev/badge/plugins/zenml-io/skills/zenml-quick-wins.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 1 skill, 2 agents cost 220 tokens a session between them.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

zenml-quick-wins scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json#zenml-quick-wins · 22 lines

What it actually says

{
  "name": "zenml-quick-wins",
  "source": "./skills/zenml-quick-wins",
  "description": "Guided implementation of ZenML MLOps best practices including metadata logging, experiment tracking, alerts, schedules and triggers, secrets, streaming events, and Model Control Plane setup",
  "version": "1.0.1",
  "author": {
    "name": "ZenML Team",
    "url": "https://github.com/zenml-io"
  },
  "homepage": "https://docs.zenml.io",
  "repository": "https://github.com/zenml-io/skills",
  "license": "Apache-2.0",
  "category": "mlops",
  "keywords": [
    "zenml",
    "mlops",
    "pipelines",
    "metadata",
    "experiment-tracking",
    "model-governance"
  ]
}

Contents

What it installs

The manifest is a name and a version. 1 skill, 2 agents travel with it, and installing the plugin installs all of them — 220 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside marketplace.json#zenml-quick-wins in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

marketplace.json 11 KB

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 22 lines scan A 1429ff498174

Subscribe to this mod's changes

zenml-quick-wins is a plugin published in the GitHub repository zenml-io/skills (6 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Data and AI DevOps and cloud MLOps agent-skills skills

gemini-skills

A library of skills for the Gemini API, SDK and model interactions.

google-gemini/gemini-skills · not measured

developer-kit-ai

AI/ML capabilities including prompt engineering, RAG, and chunking strategies.

giuseppe-trisciuoglio/developer-kit · not measured

experiment-tracker

ML experiment tracking with metrics logging and run comparison.

rohitg00/awesome-claude-code-toolkit · not measured

context-compression

Production strategies for compressing LLM context windows. Anchored iterative summarization, opaque compression, tokens-per-task optimization, and probe-based evaluation.

viktorbezdek/skillstack · not measured

agent-development

Design and build custom Claude Code agents with effective descriptions, tool access patterns, and self-documenting prompts. Covers Task tool delegation, model selection, memory limits, and declarative instruction design. Use when: creating custom agents, designing agent descriptions for auto-delegation…

danstrem2/clawdbot-skill-master-pack · not measured

nextjs

Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.

vercel/next.js · not measured