A set of skills to steer your AI-assisted machine learning experiments. The skills help you:
- build your machine learning pipeline with core data science libraries (e.g. scikit-learn, skrub, skore, pandas, polars) while ensuring your agent follows correct methodologies
- evaluate and store your results so you can easily audit and get insights from them
- connect your agent to Skore Hub to get a comprehensive view of your experiments and results
- iterate on your next experiments from a Skore audit digest (a separate backlog turn) and from your own feedback
- organize your workspace according to best practices for data science projects (e.g. cookiecutter template)
Probabl skills let you focus on the science while AI agents handle the implementation, guided by two important ingredients: core data science libraries for maintainability and methodological best practices for running your machine learning experiments properly.
In practice, from a prompt such as:
╭────────────────────────────────────────────────────────────────────────╮
│ > Given the context in the file `data/README.md` and the data located │
│ in `data/`, let's build a first machine learning pipeline that will │
│ serve as baseline for the next experiments that we are going to run │
│ together. │
╰────────────────────────────────────────────────────────────────────────╯
you can expect your agent to start experimenting with you. The skills work well with models such as Claude Opus and Sonnet and produce great results with smaller models such as Qwen 3.7 Flash or DeepSeek v4.1 Flash.
As for agent harnesses, we tested them with Claude Code, OpenCode, Cursor, and GitHub Copilot and found no significant difference in terms of skill invocation.
You can install the skills using the skore CLI that you can install from PyPI or from
conda-forge and run the following command.
First install skore-cli:
# with pip
pip install skore-cli
# with uv
uv tool install skore-cli
# with pixi
pixi global install skore-cli
Then run the following command:
skore skills installInstall a smaller workflow pack by id when you do not need the full companion:
skore skills install setup # workspace, environment, git, export
skore skills install data_analysis # data exploration
skore skills install model # frame, build, smoke-test, evaluate, audit
skore skills install loop # triage, explore, model, review, backlog, export
skore skills install export # notebooks and documentation siteskore skills install ml-experimentation remains the complete pack,
containing every active skill. The default install / install all
behavior is unchanged.
You can use uvx or pixi exec to install the skore CLI and directly run the
command in an isolated environment:
uvx --from skore-cli skore skills installor
pixi exec --spec skore-cli skore skills installIf you prefer npx, then you can use:
npx skills add probabl-ai/skillsIf you only use Claude Code and prefer the native plugin flow, this repo is also a Claude Code plugin marketplace:
/plugin marketplace add probabl-ai/skills/plugin install probabl-skills@probabl-skills/plugin update pulls new releases.
| Skill | Description |
|---|---|
| triage-ml-task | Session owner: list installed entry skills and ask which to run. |
| review-ml-choices | Show stored project choices and re-enter the skill that can change one. |
| review-ml-experiment | Gate the skore-check audit, then write one idea file per candidate. |
| setup-ml-project | Ask setup choices up front, then coordinate workspace, environment, and git. |
| setup-workspace | Detect or scaffold the standard ML workspace layout. |
| setup-python-env | Detect the env manager and bootstrap the runtime, agent-tools, and composed development environments. |
| setup-git | Initialize safe version control for an ML workspace. |
| persist-ml-git | Commit the current loop stage when git end-turn says invoke. |
| model-ml-pipeline | Require locked problem framing, then coordinate modeling choices, build, smoke testing, evaluation, and audit. |
| export-ml-project | Coordinate executed notebooks and an offline MkDocs site. |
| sync-ml-reports | Copy skore reports between local, Hub, and MLflow, and optionally switch the upload destination. |
| Skill | Description |
|---|---|
| explore-ml-data | Explore the dataset before designing any model. |
| frame-ml-problem | Lock the problem, deployment setting, metric, baseline, and fold count before any model code. |
| research-ml-practice | Literature research for an ML methodology concern. |
| build-ml-pipeline | Declare a skrub DataOps graph from the data source to the predictor after framing is locked. |
| evaluate-ml-pipeline | Evaluate one sklearn-compatible learner with the locked validation scheme and persist structured skore reports. |
| smoke-test-ml-pipeline | Structural pytest: prediction count must match the predict-grid row count. |
| audit-ml-pipeline | Audit a persisted skore report read-only and produce a reusable digest. |
| Skill | Description |
|---|---|
| manage-ml-backlog | Record experiment outcomes and triage idea files into backlog rows, keeping each file with a triage flag. |
| shape-user-idea | Shape a user idea or a named artifact into one idea file after they confirm. |
| search-ml-literature | Search scientific and technical sources and write one idea file for the direction the user confirms. |
| Skill | Description |
|---|---|
| add-python-package | Add a dependency through the project env manager, or ask the user when the environment is user-managed. |
| choose-python-library | Resolve a library choice and add the selected dependency. |
| plot-ml-figure | Pick pandas, seaborn, plotly, or matplotlib before writing figure code. |
| export-ml-notebook | Convert a jupytext percent file into an executed notebook. |
| export-ml-site | Package workspace markdown and existing notebook HTML into an offline MkDocs site. |
Canonical package policy lives in the CLI; print it with python -m skore_skills env stack. choose-python-library resolves competing libraries.
The catalog temporarily retains two deprecated compatibility skills. They are not included in workflow packs:
| Deprecated skill | Replacement |
|---|---|
| organize-ml-workspace | Use setup-workspace. |
| data-science-python-stack | Use choose-python-library and the canonical package policy. |
Catalog ids python-env-manager and python-code-style have been removed. Run
skore skills remove on any leftover sidecars and reinstall the setup pack.