
Cloud Data Platform Engineer AI Skill
Yusra




Skill fileClaude Skills for DevOps
Build the ML platform: feature store with point-in-time correctness, serving infrastructure, and paved paths teams actually use.
$9· one file, yours to keep
Yours to keep · instant download
Or all of them, $6.99/mo
Nikolina and 2,500+ other specialists, in your AI. Ask for any of them by name.
7 days free, then $6.99/mo · cancel anytime
One file
All-in-one
30-day money-back · secure checkout by Stripe
# Nikolina - Feature Store & ML Platform Engineer ## Who Nikolina Is Drop Nikolina into Claude and get a Senior Feature Store and ML Platform Engineer who builds the layer underneath the models: a feature store that returns the same value offline and online, serving infrastructure that holds a latency budget under load, and a paved path that a new model team can ship on in a week instead of a quarter. She treats the platform as a product with tenants, SLOs, and a support contract, not as a pile of shared notebooks. Her first move on any engagement is to measure, not to redesign: she reproduces the training set, replays the online request log, and shows the numeric gap before proposing anything.
Our models look great offline and fall apart in production. Build us a real feature platform.
Nikolina returns a skew diagnosis with the offending features named and quantified, an offline and online feature store design with point-in-time join semantics, materialization and freshness SLAs, a serving architecture with latency budgets and cost per prediction, a registry and tracking setup, and a platform-versus-product ownership boundary.
Build the ML platform: feature store with point-in-time correctness, serving infrastructure, and paved paths teams actually use. Load it once into Claude Projects and you get a configured Feature Store & ML Platform Engineer without re-explaining context at the start of every session. Check every number against a known-good source and an honest holdout before anyone builds a decision on it, and state the uncertainty instead of shipping a single confident point estimate.
Download the .skill package (it contains SKILL.md), then, in Claude, turn on code execution in Settings → Capabilities and add it under Customize → Skills → + → Create skill → Upload a skill (in ChatGPT, Gemini or another AI, open it as a .zip and paste SKILL.md into Project instructions or custom instructions), add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.
Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.
Without a skill file your AI starts every session as a general assistant. With Nikolina loaded it applies Feature Store & ML Platform Engineer methodology from the first message, with consistent quality every time. Check every number against a known-good source and an honest holdout before anyone builds a decision on it, and state the uncertainty instead of shipping a single confident point estimate.
Download your .skill file from the order email or your account. In Claude, turn on code execution in Settings › Capabilities, then go to Customize › Skills › + › Create skill › Upload a skill. Start a new chat and ask for the specialist by name.