Probabl Data Science Skills

Fourteen skills that guide an agent through a machine-learning experiment in Python: exploring the data, building, evaluating, testing, smoke-testing and auditing a pipeline, iterating on experiments from diagnostics or user feedback, and organising the workspace, code style and environment. Several skills rely on the maintainer's own skore library. Aimed at data teams that want each stage of an experiment to follow a written method.

Data quality
Statistics
Testing

Source: probabl-ai/skills · pinned commit 96d77a4

View source on GitHub

LuluSkill lists this project so you can find it. A listing is not a security review or an endorsement, and nothing on this page is installed or run for you.

EDITORIAL GUIDE

An ML audit needs an existing experiment and an unresolved-use warning

The reviewed entry audits an existing evaluation report rather than training a model. This reading note does not resolve the pending licence variant or approve execution.

LuluSkill’s own reading of this project, not a summary of its README. About 3 minutes to read

This guide is LuluSkill’s own judgement about when this project fits, written from the pinned version named above. It is not the author’s documentation, not a security review and not a recommendation. LuluSkill did not install, run or test the project to write it, and the guide is shown only while this listing still points at the commit it was written against.

When this project fits

The reviewed audit entry is relevant after a pipeline has an evaluation report, approved design and experiment records. Its workflow pairs experiment identifiers with source and journal material; that is a more specific task than asking an assistant to improve arbitrary model performance.

When to choose something else

It is not a starting point for raw-data exploration or a substitute for training and validation. The licence variant and platform-use decision remain unresolved for this listing. Read this note to understand scope; do not infer permission to install, redistribute or execute from its existence.

What to provide and what to expect

The stated workflow expects a report identifier, experiment context and associated audit material. Its intended output is a traceable audit, not a newly improved model. Missing report provenance should be treated as missing input, rather than filled with invented experiment history.

Tools, permissions and boundaries

Although the project is described as read-only during audit, the entry discusses Python execution and audit or scratch-file writes. That requires a suitable environment and separately scoped permissions. A read-only data intention does not mean the workflow performs no execution or writes.

The tradeoff and an alternative

A manual audit table can connect each claim to a report and experiment without adopting this integration. That is the appropriate comparison while usage conditions are pending. Any future automated audit should preserve the same provenance instead of merely producing more findings.

A small acceptance exercise

Proposed paper exercise only: map one known metric to its report, experiment and evaluation split. Check that a different experiment identifier would be rejected and that an absent source is marked unknown. Do not perform an execution exercise until usage conditions and permissions are resolved.

Source, version and what was actually read

The pinned audit entry was read for its opening inputs, report retrieval and audit-file workflow. Other skills, licence resolution and a working report environment were not evaluated in this editorial round. LuluSkill did not install or run this project; the exercise above is a proposed reader check, not a reported result.

How to use this listing

LuluSkill publishes the description and the source link only. The skill itself stays in its author’s repository, and nothing here is installed, copied or run for you.

Read what the skill helps with The summary above says which job the project is for. If that is not the job you have, this is probably not the listing you want.
Open the original source and follow the author’s own instructions The link to the original project opens its author’s page. That page, not this one, is where the setup steps and any copying instructions live.
Use it in a compatible AI assistant Skills of this kind are normally used inside an AI assistant that can read a folder of files on your computer. Which assistants support them is the author’s decision, so check their page before you start.

Who it is for

Somebody who already wants this one job done and is willing to follow the author’s setup steps. No programming knowledge is assumed, and this listing cannot tell you whether the project suits you.

Before you start

You need an AI assistant that supports skills, and you will be following somebody else’s instructions on your own computer. Read them before you run anything.

What you end up with

Whatever the author’s project produces. LuluSkill never runs it, so this page cannot promise a result, a file, or a level of quality.

Where it is normally used

Projects like this are usually used in an AI assistant that supports skills, such as an AI coding assistant. The author’s repository says which assistants it is written for; LuluSkill has not tested it with any of them.

Version checked

The source was checked at this commit: 96d77a4

Changes made to the repository after this commit have not been checked.

License

BSD-3-Clause, from the licence file in the source repository at the listed commit. Check the repository’s licence before you use or copy the project.

Listing only

LuluSkill lists this project only. It does not host, download or run its code.

What this page does not include

The project’s files and setup steps stay in its own repository. LuluSkill has not security-tested the project or confirmed which AI assistants it works with.

Report a problem or request removal

Rights holders and users can report licence, attribution, security or accuracy problems with this page. We respond within 48 hours and record every request in our review log.

Report or request removal How copyright complaints work

Opens your email app. You can also write to contact@luluskill.com and include this page’s address.

More Data projects in the directory

Tufte Data Viz
A chart-design rule set that an agent applies while building or auditing charts, graphs and dashboards: direct labels, restrained axis and gridline treatment, contrast, responsive layout and dark-mode behaviour, with configuration notes for several common charting libraries. Aimed at people who produce data visualisations and want the same house rules applied on every chart.
Agent ML Skills
Fifteen machine-learning workflow skills covering data exploration and cleaning, feature engineering, scikit-learn pipelines, PyTorch training loops, model evaluation and hyperparameter tuning, LLM fine-tuning, retrieval-augmented generation, experiment tracking, reproducibility, model debugging and model serving. Aimed at practitioners who want an agent to follow a repeatable, leakage-aware procedure at each stage of a modelling task.