Ai Ml Data Science

Name: Ai Ml Data Science
Author: vasilyu1983

Listed

vasilyu1983·vlatest·data·MIT

Helps with AI, machine learning, data as part of agent workflows workflows.

Repository

Install on your platform

This skill no longer installs under the name ai-ml-data-science. vasilyu1983/ai-agents-public is deleted or private, so it cannot be installed from.

We check each listing against its upstream repository with the rules the skills CLI uses, last on 2026-10-22. We don't show a command we know will fail.

Repository install instructions

What we know about this skill

Publisher

vasilyu1983

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned 12 Oct 2026

This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

No undeclared network calls: failed
Contacts 29 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: arxiv.org, catboost.ai, csrc.nist.gov, docs.astral.sh, docs.cleanlab.ai….
Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.
Hosts contacted
hastie.su.domainsundeclaredwww.statlearning.comundeclaredarxiv.orgundeclaredpapers.nips.ccundeclaredwww.oreilly.comundeclaredjoss.theoj.orgundeclareddocs.astral.shundeclareddocs.marimo.ioundeclaredpandas.pydata.orgundeclareddocs.pola.rsundeclaredduckdb.orgundeclaredscikit-learn.orgundeclaredlightgbm.readthedocs.ioproject documentationcatboost.aiundeclaredpytorch.orgundeclaredmapie.readthedocs.ioproject documentationpandera.readthedocs.ioproject documentationdocs.greatexpectations.ioundeclareddocs.evidentlyai.comundeclaredgithub.comsource hostmlflow.orgundeclareddocs.coreweave.comundeclareddvc.orgundeclareddocs.lakefs.ioundeclareddocs.feast.devundeclaredsqlmesh.readthedocs.ioproject documentationpriorlabs.aiundeclareddocs.cleanlab.aiundeclareddoi.orgundeclaredwww.cis.upenn.eduundeclaredwww.cs.toronto.eduundeclarednvlpubs.nist.govundeclaredeur-lex.europa.euundeclaredcsrc.nist.govundeclared
What it found (3 of 51)
- skills/universal/ai-ml-data-science/data/sources.json:15contacts hastie.su.domains
  "url": "https://hastie.su.domains/ElemStatLearn/",
- skills/universal/ai-ml-data-science/data/sources.json:24contacts www.statlearning.com
  "url": "https://www.statlearning.com/",
- skills/universal/ai-ml-data-science/data/sources.json:33contacts arxiv.org
  "url": "https://arxiv.org/abs/1803.09010",
Declares what it does: passed
SKILL.md parses and declares a name and a description.
SKILL.md exists, its frontmatter parses, and it declares a name and a description.
No obfuscated payloads: passed
No encoded or obfuscated payloads.
No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.
No credential access: passed
Reads no keys, tokens, keychains or credential files.
Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.
No pipe-to-shell installers: passed
No pipe-to-shell or download-and-run installers.
No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.
Pinned to a commit: passed
Scanned vasilyu1983/ai-agents-public at 3ee3637d25.
The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit: 3ee3637d25
Manifest: skills/universal/ai-ml-data-science/SKILL.md
Scanned: 33 files, 7,583 lines

This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.

What each check looks for →

About this skill

The ai-ml-data-science skill provides a foundational framework for AI agents to handle complex data processing, machine learning model development, and statistical analysis tasks. It enables agents to ingest raw datasets, perform exploratory data analysis (EDA), and deploy predictive models for decision-making.

When to use it

Automating the cleaning and preprocessing of large, unstructured datasets before analysis.
Generating Python scripts to train regression or classification models on historical business data.
Performing statistical significance testing to validate hypotheses within a dataset.
Creating visualizations to interpret trends and patterns for stakeholder reporting.

Key capabilities

Data ingestion from various file formats (CSV, JSON, Parquet).
Exploratory Data Analysis (EDA) including summary statistics and distribution checks.
Model training using libraries like Scikit-learn, TensorFlow, or PyTorch.
Evaluation metrics calculation such as accuracy, precision, recall, and RMSE.
Automated feature engineering and selection processes.

Example prompts

"Analyze this CSV file containing sales data and identify the top three factors influencing revenue growth."
"Write a Python script to train a random forest classifier on this dataset to predict customer churn."
"Perform exploratory data analysis on this time-series dataset and generate a summary of seasonal trends."

Tips & gotchas

Ensure your input data is clean and properly formatted, as the quality of the AI agent's analysis depends heavily on the integrity of the source files. This skill is best utilized when you have specific datasets ready for processing rather than for generating synthetic data from scratch.