Skip to content
Get packs

SageMaker Python Environment Setup

Builds an isolated Python 3.10-3.12 venv with current boto3 and awscli for SageMaker/AWS work

Source Download skill
Repository
huggingface/skills
Stars
11,253
Licence
Apache-2.0
Files
4 files

What it does

Once installed, the agent sets up a separate, isolated Python environment before running any code that talks to AWS or SageMaker, instead of using the computer's main Python. It creates a .venv folder with a supported Python version (3.10-3.12), installs the latest boto3 and awscli from the bundled requirements file, and checks installed package versions. The bundled setup script is idempotent, so re-running it is safe.

Great for

  • Developers preparing SageMaker deployments or training jobs who keep hitting dependency or version errors
  • Engineers who want a reproducible, isolated Python setup for AWS automation
  • Teams that want an agent to follow consistent environment rules before running pip install

Skip it if

  • Users who need a specific pinned boto3 or awscli version: the skill tells the agent to always install the latest, so pins must be added manually
  • Anyone expecting it to deploy models itself: it only prepares the environment; the deploy scripts it references are not included in these files
  • Non-AWS Python projects: the rules and requirements are specific to SageMaker and AWS automation

Try asking

  • “Set up a clean Python environment for my SageMaker deployment”
  • “Check which versions of boto3 and botocore are installed in my venv”
  • “Recreate my .venv with Python 3.12 because pip install is failing with resolution errors”
Step-by-step guide: how to use SageMaker Python Environment SetupInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the Apache-2.0 licence and an attribution note.

    hf-cloud-python-env-setup.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip hf-cloud-python-env-setup.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip hf-cloud-python-env-setup.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Ask the agent to run scripts/setup_env.py rather than typing pip commands by hand, so the Python version check is applied
  • Run scripts/check_versions.py after setup to confirm boto3, botocore and awscli are installed before deploying
  • If you need extra packages such as transformers, have the agent add them to a project-specific requirements file rather than the shared one

What's inside

  • requirements.txt
  • scripts/check_versions.py
  • scripts/setup_env.py
  • SKILL.md

Redistributed unmodified from huggingface/skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.