generated: '2026-09-16'
method: searched
source: https://github.com/probabl-ai/skills
note: 'Provider-published Agent Skills (probabl-ai/skills, catalog .catalog.json), saved verbatim. These are data-science
  workflow skills for coding agents (skrub/scikit-learn/skore), not REST call recipes, so they do not list Skore
  Hub operationIds. Installed with `skore skills install` (skore-cli). Re-verified 2026-09-16: all 14 skills/<name>/SKILL.md
  paths present upstream.'
catalog: https://github.com/probabl-ai/skills/blob/main/.catalog.json
install: pip install skore-cli && skore skills install
skills:
- file: probabl-audit-ml-pipeline.md
  name: audit-ml-pipeline
  description: 'Owns the `audit/` folder: one `# %%` (jupytext percent) Python file per experiment, aligned 1:1
    with `experiments/NN_<short_name>.py` and `journal/NN_<short_name>.md`, that loads the experiment''s skore report
    **read-only** and uses bare-last-expression cells whose `__repr__` carries the audit''s signal. The agent executes
    the audit file via the bundled in-process runner (`audit-ml-pipeline/scripts/run_cells.py` — IPython `InteractiveShell.run_cell`),
    which streams a markdown digest of each cell''s stdout + last-expression repr to stdout (optionally also to
    a file). The digest fuels narrative work (the `JOURNAL.md` Status + History update, follow-up questions about
    a past experiment, cross-experiment comparison). Stops at "audit/NN_*.py is placed, executed, and the digest
    is available." Never calls `skore.evaluate(...)` or `project.put(...)`.'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/audit-ml-pipeline/SKILL.md
- file: probabl-build-ml-pipeline.md
  name: build-ml-pipeline
  description: Declare the pipeline from data source to predictor as a **skrub DataOps graph** (not as a bare `sklearn.Pipeline`).
    Every step is either a pure-Python function (stateless) attached via `.skb.apply_func`, or a sklearn-compatible
    estimator (stateful) attached via `.skb.apply`. Stops at the declared object — no fit, split, tuning, persistence,
    or evaluation.
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/build-ml-pipeline/SKILL.md
- file: probabl-data-science-python-stack.md
  name: data-science-python-stack
  description: Opinionated Python stack for data-science / ML work — one library per job, organized into tiers (mandatory
    / user choice / optional / transitive). SKILL.md is the index; per-library `references/<library>.md` files carry
    scope, "pick this when" / "pick something else when", and pairings.
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/data-science-python-stack/SKILL.md
- file: probabl-evaluate-ml-pipeline.md
  name: evaluate-ml-pipeline
  description: 'Methodology for evaluating a single sklearn-compatible learner (in particular, the `SkrubLearner`
    produced by `build-ml-pipeline`). Owns: which entry point to call (`skore.evaluate` first, the explicit report
    classes when needed), which cross-validator to pick from scikit-learn''s catalogue, how to consume the structural
    metadata (`groups`, `times`, …) attached at build time via `.skb.mark_as_X(split_kwargs=...)`. Stops at "what
    does the report say". Defaults (metrics, plots) come from skore; only override on explicit user request.'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/evaluate-ml-pipeline/SKILL.md
- file: probabl-explore-ml-data.md
  name: explore-ml-data
  description: Owns data understanding BEFORE any model is designed. Places and executes `data/eda.py` (a jupytext
    `# %%` script) via the shared in-process runner, reads the streamed digest, then writes a persisted `data/eda.md`
    report (plus linked `data/eda_<table>.html` skrub `TableReport` pages) and the `## Data understanding (EDA)`
    section of `journal/JOURNAL.md`. The point is to surface the dataset facts — shape, dtypes, missingness, cardinality,
    target balance / skew, datetime / group structure, feature associations — that JUSTIFY the later learner / splitter
    / metric decisions, so the user understands *why* the modelling choices are made. Uses `skrub.TableReport` for
    dataframe overviews and the shared runner `audit-ml-pipeline/scripts/run_cells.py`. Stops at "EDA executed,
    `data/eda.md` + HTML written, JOURNAL EDA section updated." Never designs the model, never edits `src/<pkg>/`,
    never modifies the user's raw data files.
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/explore-ml-data/SKILL.md
- file: probabl-iterate-from-skore.md
  name: iterate-from-skore
  description: Source the next ML experiment proposal by **reading the audit digest** at `scratch/audit/<stem>/audit.md`
    (produced by `audit-ml-pipeline` at § 4 record-outcome). For every row in the digest's `## Checks summary` whose
    `severity` is `issue` or `tip`, follow the row's `documentation_url` to draft a Backlog row whose `Item` is
    the mitigation the docs recommend. The `## Metrics summary` provides context for the human summary paragraph
    but does not drive Backlog rows on its own. Returns the enriched Backlog rows + a one-paragraph summary back
    to `iterate-ml-experiment`, which writes the rows into `JOURNAL.md` and re-presents the sourcing menu so the
    user can promote a `B<N>` row. Stops at "Backlog enriched, summary returned"; never writes a per-experiment
    design note, never picks the "winning" finding — the user picks via `B<N>`.
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/iterate-from-skore/SKILL.md
- file: probabl-iterate-from-user.md
  name: iterate-from-user
  description: 'Source the next ML experiment proposal from the user via one of three entry points selected by `AskUserQuestion`:
    (a) a scientific article URL the agent must read and synthesize, (b) a resource link or path (GitHub issue /
    spec file / reference repo), or (c) free-text the user types directly. In every branch, the agent reads the
    source, synthesizes its understanding of what to implement, and confirms with the user *before* returning the
    Proposal block. Hand the confirmed Proposal back to `iterate-ml-experiment`, which writes it into `journal/NN_short_name.md`
    and seeks the user''s design-note approval. Stops at "Proposal returned, user-confirmed"; never writes a design
    note, never authors acceptance criteria.'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/iterate-from-user/SKILL.md
- file: probabl-iterate-ml-experiment.md
  name: iterate-ml-experiment
  description: 'Owns the iteration loop on top of an ML workspace: the `journal/JOURNAL.md` index and the per-experiment
    `journal/NN_short_name.md` design notes that must be drafted and approved by the user **before** `experiments/NN_short_name.py`
    is created. Drives the propose → iterate → approve → implement → record loop; dispatches to `iterate-from-skore`
    / `iterate-from-user` for sourcing.'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/iterate-ml-experiment/SKILL.md
- file: probabl-organize-ml-workspace.md
  name: organize-ml-workspace
  description: 'Decide where files live in an ML experimentation project: reusable code in `src/<pkg>/`, one `#
    %%` script per experiment in `experiments/`, design notes + index in `journal/`, reports in `reports/`, agent-only
    probes in `scratch/`. Owns the layout, the file-creation rules (one file per experiment, ask before editing),
    and the jupytext `# %%` script convention. Never imposes `data/` — the user owns that.'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/organize-ml-workspace/SKILL.md
- file: probabl-python-api.md
  name: python-api
  description: 'Look up the public API of a Python package against the *installed version* and cache what''s worth
    keeping. Four shapes by question type: (0) cache hit under `scratch/api/<lib>/<version>/`; (1) `inspect.signature`
    + `pydoc.render_doc` for a symbol; (2) `dir` / `pkgutil.iter_modules` for a module surface; (3) WebSearch +
    WebFetch of versioned docs for narrative ("how", "which", "what does X return when Y"). Never write a symbol
    from training-data memory — recognition is not a lookup.'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/python-api/SKILL.md
- file: probabl-python-code-style.md
  name: python-code-style
  description: 'Owns Python code style for this stack: ruff for lint + format, numpydoc for docstrings. Three responsibilities
    — (1) place the project''s `ruff.toml` from the bundled template once the stack and workspace are in place,
    (2) run ruff against any Python files Claude has just generated or edited, and (3) contextualize each touched
    file''s comments to the data-science problem — rewriting any leftover template / workflow prose (skill names,
    gates, runner, digest, guard-rails) into concise, problem-specific docs so the user''s committed files read
    like a colleague wrote them, not like a generated scaffold. Stops at "the touched files pass `ruff check` and
    document the problem, not the process."'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/python-code-style/SKILL.md
- file: probabl-python-env-manager.md
  name: python-env-manager
  description: 'Single source of truth for "which Python environment manager does this project use, and how do I
    install a package with it?". Owns the detection table (pixi / uv / poetry / hatch / conda+mamba / pip+venv),
    the install / remove / upgrade commands per manager, and the bootstrap path when no manager is in place (default
    recommendation: pixi). Stops at "the install command was issued with the right manager and the package is importable".'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/python-env-manager/SKILL.md
- file: probabl-smoke-test-ml-pipeline.md
  name: smoke-test-ml-pipeline
  description: 'Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that
    fits the experiment''s learner on a portion of the real `data/` source and predicts on a *disjoint* portion
    that deliberately carries **no pre-history buffer**. The assertion is structural — the number of predictions
    must equal the number of rows in the predict grid. A pipeline that loads-then-features-then-splits will silently
    drop the cold-start rows of the predict slice and the test will fail with a row-count mismatch; a pipeline that
    marks X early and references upstream history nodes from feature steps will pass trivially. The smoke test is
    the executable proof of the X-marker placement rule from `build-ml-pipeline`.'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/smoke-test-ml-pipeline/SKILL.md
- file: probabl-test-ml-pipeline.md
  name: test-ml-pipeline
  description: 'Owns the `tests/` folder of an ML workspace and the pairing rule between an experiment and its tests.
    Lightweight router: every test category has its own subskill (`smoke-test-ml-pipeline` is the only one for v1;
    `regression-test-ml-pipeline` / `distribution-test-ml-pipeline` etc. plug in as siblings as the workspace grows).
    This skill places an empty `tests/<category>/` folder, enforces the stem-pairing rule between `tests/<category>/test_NN_<short_name>.py`
    and `experiments/NN_<short_name>.py`, and dispatches to the matching subskill when the user asks for a test.'
  upstream: https://github.com/probabl-ai/skills/blob/main/skills/test-ml-pipeline/SKILL.md