probabl-ai/skore-skills

choose-python-library

Resolve a library choice and add the selected dependency.

Ver código fuente

Cómo usar

  1. Copia el comando y revisa el paquete antes de instalarlo en tu entorno de agente.
  2. Consulta las herramientas, credenciales y entornos necesarios en el documento original.
  3. Describe las entradas y el resultado deseado; contrasta la salida con las fuentes.
npx skills add https://github.com/probabl-ai/skore-skills --skill choose-python-library

Antes de empezar

  • La instalación no incluye suscripción al modelo, cuota API ni permisos sobre tus archivos.
  • Las estrellas e instalaciones reflejan actividad, no una prueba independiente de calidad o seguridad.
Documento original del Skill

Contenido del repositorio de origen con títulos, ejemplos, código, tablas, enlaces e imágenes preservados.

Choose Python Library

Human-facing prose

Details: setup-workspace references/human_facing_prose.md. Present library options as a data-science choice for this job. Do not name skill ids or the wrapper CLI in the question.

  1. State the job and constraints.
  2. Run python -m skore_skills env stack. A job listed under

competing is a genuine choice; anything the policy already fixes (mandatory, stage, export) is settled — use it rather than reopening the choice. Do not read the packaged JSON file directly; it lives inside the installed package.

  1. For a genuine choice, present the smallest useful option set and

ask the user. Do not pick silently.

  1. After the user chooses, load add-python-package when

status.skills reports it installed. If it is not installed, name the package and stop. Do not call env add from this skill. Typical callers: explore-ml-data (pandas vs polars), later extras (tuning). Not setup-workspace. Plotting jobs: load plot-ml-figure if installed; do not present matplotlib vs seaborn vs plotly.

  1. Confirm symbols with python -m skore_skills api get <dotted>...

before writing calls. Several symbols go in one call. Scope for one package is python -m skore_skills env route <pkg>, not a guess.

Stop conditions

  • Do not install every candidate.
  • Do not use popularity alone as a technical decision.
  • Do not run pip directly in a managed project.
  • Do not substitute black/isort for Ruff or sklearn Pipeline for

skrub DataOps; those choices are already fixed.

  • Do not present matplotlib vs seaborn vs plotly; that job is

plot-ml-figure.

Relacionados por tarea

del mismo repositorio

Más Skills

Todos los Skills
probabl-ai
Comunidad

plot-ml-figure

Pick pandas, seaborn, plotly, or matplotlib before writing figure 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: first match on the tree (owned plot, interactive iframe HTML, seaborn statistical, pandas chart, else matplotlib). In a notebook: save PNG (or HTML) then leave the figure as the cell

Instalaciones / 1h
1
GitHub Stars
145
Actualizado
9 nov
probabl-ai
Comunidad

setup-git

Initialize safe version control, including an optional commit of the tree before setup changes it. 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. When loaded for the pre-change snapshot, commit the current tree before other setup writes, then return.

Instalaciones / 1h
1
GitHub Stars
145
Actualizado
9 nov
probabl-ai
Comunidad

shape-user-idea

Shape a user idea or a named artifact into one idea file and one 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.

Instalaciones / 1h
1
GitHub Stars
145
Actualizado
9 nov
probabl-ai
Comunidad

audit-ml-pipeline

Audit a persisted skore report read-only and produce a reusable digest. 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-audit an experiment, a re-run overwrote the same put() key, or they want a narrative of a past experiment without journal/ideas/ files. STOP when status.setup.pending is non-empty (load setup-ml-project), or when there is no approved design, no report, or no ag

Instalaciones / 1h
1
GitHub Stars
142
Actualizado
20 oct