Choose Python Library
SkillDev toolsLets your agent compare competing Python libraries for a task and help you pick one.
Available today. Use it from your connected AI after setup.
No other account needed.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the Choose Python Library skill
About this skill
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
What this skill tells your AI
The instructions your AI receives, as published by probabl-ai/skills in skills/choose-python-library/SKILL.md and read by ahel’s review.
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.
- State the job and constraints.
- Run
python -m skore_skills env stack. A job listed undercompetingis 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. - For a genuine choice, present the smallest useful option set and ask the user. Do not pick silently.
- After the user chooses, load
add-python-packagewhenstatus.skillsreports it installed. If it is not installed, name the package and stop. Do not callenv addfrom this skill. Typical callers:explore-ml-data(pandas vs polars), later extras (tuning). Notsetup-workspace. Plotting jobs: loadplot-ml-figureif installed; do not present matplotlib vs seaborn vs plotly. - Confirm symbols with
python -m skore_skills api get <dotted>before writing calls. Scope for one package ispython -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.
Signals
- GitHub stars
- 132
- Forks
- 9
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
choose-python-library- Source
- github.com/probabl-ai/skills