probabl-skills

Plugin probabl-skills from marketplace probabl-skills in probabl-ai/skills. Commands read from the repo's manifest — 30 days ago.

Skills (28)

• add-python-package

  Add a Python dependency through the project env manager, or ask the user to install it when env.managed is false. Trigger when a workflow needs a missing import, after choose-python-library picks a library, or for editable install of src/<pkg>/. SKIP choosing between competing libraries (choose-pyth

• audit-ml-pipeline

  Read-only audit of one persisted skore report: `audit/NN_<stem>.py` (jupytext percent), 1:1 with `experiments/` and `journal/`. Do not execute it. Run `materialize.py` once. Never call `skore.evaluate` or `project.put`. TRIGGER when a completed run needs an audit, the user asks to audit, show, or re

• build-ml-pipeline

  Declare the pipeline from data source to predictor as a skrub DataOps graph. Stateless steps use `.skb.apply_func`. Stateful steps use `.skb.apply`. After the graph exists, attach the locked splitter and any non-default score. No fit, tune, persistence, or `skore.evaluate`. TRIGGER when writing or e

• choose-python-library

  Resolve a genuine choice between Python libraries for one job, then ask `add-python-package` to add the chosen dependency. Trigger for competing-library questions or an optional package not already fixed by the project stack — at first use (tabular exploration, pipeline, or eval extras), never durin

• data-science-python-stack

  Deprecated compatibility skill. Trigger only when an installed workflow still references this old id. modelTier: small

• evaluate-ml-pipeline

  Evaluate one learner with `skore.evaluate`. The splitter and any non-default score are already on the DataOp from `build-ml-pipeline`. This skill writes the call without `splitter=`, persists the report, and records the locator. When the locked split is the training table and test table that shipped

• explore-ml-data

  Owns data understanding before any model is designed. Place `data_analysis/data_analysis.py` and do not execute it. Run `materialize.py` once, write `data_analysis.md` and JOURNAL § Data understanding. Never design the model, edit `src/<pkg>/`, or modify raw data files. TRIGGER when the user asks to

• export-ml-notebook

  Write a jupytext percent `# %%` Python file out as an `.ipynb`. `data_analysis/`, `experiments/`, and `audit/` are filled with empty outputs. Pass `--html` when that notebook should also become a viewer on the site. Kernel `notebook convert` stays for a source that is itself the execution. Trigger o

• export-ml-project

  Coordinate on-demand export: executed notebooks and/or an offline MkDocs documentation site. Trigger on a generic "export" request, or to flip the notebooks/site gates after setup. modelTier: small

• export-ml-site

  Package JOURNAL, exploratory data analysis markdown, and design notes into an offline MkDocs site opened via the file:// URL of report.html at the workspace root. Embeds existing notebook HTML companions in their associated reports. Never executes Python. Trigger when the user asks for a website, mk

• frame-ml-problem

  Record the problem, the deployment setting, the comparison metric, the baseline, and the fold count in the journal before model code. Ask every missing decision in one turn, from `frame show`. Does not write Python, estimator hyperparameters, or splitter constructors. TRIGGER when the user asks whic

• manage-ml-backlog

  Canonical backlog loop step. Record an experiment outcome in History and triage idea files. Summarize open, discarded, and aside ideas in the JOURNAL Ideas table. Move a row into Backlog when it is promoted, and keep the idea file. Also supports the model-entry selection mode: show real B<N> rows su

• model-ml-pipeline

  Deterministic entry point for modeling. On a first landing, write the locked baseline design note and ask for approval. Later landings offer only the choices the workspace justifies (an EDA proposal, Backlog, discussion). A missing modeling lock loads `frame-ml-problem` and stops. After a design is

• organize-ml-workspace

  Deprecated compatibility skill. Trigger only when an installed workflow still references this old id. modelTier: small

• persist-ml-git

  Persist the current loop stage with the real git CLI when the end-turn hook says invoke. Trigger after `python -m skore_skills git end-turn --stage <stage>` returns action invoke, or when the user asks to commit this turn's work. modelTier: small

• plot-ml-figure

  Pick how to write a figure before custom plot code. Trigger when explore-ml-data, evaluate-ml-pipeline, or audit-ml-pipeline is about to save or display a chart, or when the user asks for a plot. Not a session owner. Not for skore/sklearn Display plots that already exist on a report. HOW TO USE: fir

• research-ml-practice

  Literature and web research for an ML methodology concern (EDA extra measurements, leakage, transforms, feature engineering, learner family), or an EDA extra-analysis survey from JOURNAL plus existing EDA. Trigger when explore-ml-data or build-ml-pipeline load this skill. Not for routine profiling o

• review-ml-choices

  Show the project choices already stored in status and let the user change one by re-entering the skill that owns it. Trigger when the user asks what we decided, what the current settings are, or to change a stored project choice. SKIP an explicit sync, export, or “a constraint changed” request — tho

• review-ml-experiment

  Post-evaluate review. Read the stored report, then write one markdown idea file and one Ideas row per candidate. Trigger after a successful evaluate, on "review this stem", or when review consent is audit or proceed. Do not write History, Backlog, or a design note. modelTier: medium

• search-ml-literature

  Search scientific and technical sources for a query and, after the user picks and confirms one direction, write one idea file and its Ideas row. Comes after review, beside the backlog. Do not call research-ml-practice. Do not write History, Backlog, or a design note. Do not pick a winner. modelTier:

• setup-git

  Set up git for an ML workspace after scaffolding. Trigger when the user asks to initialize version control, add ignore rules, or make the first commit. This action owns first-time git setup only. Before the first commit, ask once which unknown hidden files and review paths to keep tracked. role: hel

• setup-ml-project

  Coordinate ML project setup. Trigger when the user asks to set up or bootstrap a workspace, or when a pipeline stage finds status.setup.pending non-empty. Ask only those pending pieces. The question tells the user to select each piece they want. It starts by saying that before any modeling, the work

• setup-python-env

  Bootstrap a Python environment manager and three named envs (default runtime, agent tools, composed dev). Detect with `python -m skore_skills env detect`, persist the manager and `env.managed`, then `env init --manager`, `env sync --execute`, install Skore for a recorded hub or mlflow destination (p

• setup-workspace

  Detect an existing ML workspace or scaffold a fresh one via `python -m skore_skills scaffold --package <pkg>`. Cookiecutter only: directories, README.md files, and src/<pkg>/ stubs. After a first scaffold, turn executed notebooks and the documentation site on by default (no ask). TRIGGER for a new M

• shape-user-idea

  Shape an idea the user already has, or answer a project question, and write one idea file and its Ideas row after they confirm. A topic with no artifact belongs to search-ml-literature. Do not write History, Backlog, or a design note. Do not pick a backlog row. role: helper modelTier: medium

• smoke-test-ml-pipeline

  Owns one experiment's smoke test: a small pytest that fits on part of real `data/` and predicts on a disjoint slice with no pre-history buffer. Prediction count must equal predict-grid rows. TRIGGER when an approved experiment needs its smoke test, `pytest tests/smoke/` fails on row count, the user

• sync-ml-reports

  Copy skore reports between local, Hub, and MLflow with `skore sync`, and optionally switch the recorded upload destination. Trigger when the user asks to sync or migrate reports, switch skore mode, upload reports to Hub or MLflow, or pull Hub/MLflow reports onto disk. First G-SKORE-MODE pick stays e

• triage-ml-task

  Session owner: list installed entry skills and ask which to run. Load a skill without asking only when the request is certain to be that skill. Trigger on an ambiguous request, a finished stage, a workspace-open session, or "what should we do next". role: entry modelTier: medium

Similar plugins