skills.rest
pymc-labs
pymc-labsOFFICIAL
Explore all skills by this author →
Website𝕏@pymc_labsGitHub

Create decision-pack Programmatically

Generate decision-packs for data science agents via Python code.

178|13|Updated Mar 19, 2026
Search Tags:#Docker#data science#decision-pack#Python automation#Modal integration
One-click install
npx skills add https://github.com/pymc-labs/decision-lab --skill create-decision-pack-programmatically-pymc-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Create decision-pack Programmatically
Source: https://github.com/pymc-labs/decision-lab/tree/main/.claude/skills/create-dpack
Command: npx skills add https://github.com/pymc-labs/decision-lab --skill create-decision-pack-programmatically-pymc-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires dlab.create_dpack, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Manually creating decision-packs for data science agents can be a time-consuming process. This Skill automates the creation of decision-packs using Python code, significantly speeding up the process.

Core Features & Use Cases

  • Automated Creation: Generate decision-packs programmatically, reducing manual setup time.
  • Customization: Configure decision-packs with various parameters such as name, description, Docker image, and default model.
  • Integration: Support for Modal integration for cloud execution, and optional features like Python library inclusion.
  • Use Case: Ideal for data scientists and researchers who need to quickly prototype and iterate decision-packs for their agents.

Quick Start

Execute the generate_dpack() function from dlab.create_dpack to create a decision-pack in your current directory.

Frequently Asked Questions about Create decision-pack Programmatically

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate decision-pack creation for data science agents using Python?▼

You can automate decision-pack creation by executing the generate_dpack() function from the dlab.create_dpack module, which generates the necessary files directly in your current directory.

What is a programmatically generated decision-pack and when do I need one?▼

A programmatically generated decision-pack is a configuration bundle for data science agents created via Python code. You need one to quickly prototype and iterate agent setups without manual file assembly.

Do I need Docker and Modal to configure and run decision-packs?▼

Yes, Docker is required as a dependency for the dlab.create_dpack module. Modal integration is supported optionally for cloud execution, allowing you to run decision-packs in a scalable environment.

Can I customize the Docker image and default model when generating a decision-pack?▼

Yes, you can customize decision-packs programmatically by configuring parameters such as the name, description, Docker image, default model, and optional Python library inclusion through the generate_dpack() function.

What's the best way to integrate Python libraries into a decision-pack for cloud execution?▼

The best way to include Python libraries is to use the optional Python library inclusion feature within the generate_dpack() function, combined with Modal integration to execute the configured environment in the cloud.

Related Skills

Explore More Data & Analytics Skills→
OfirGavishOfirGavish
3

setup

Automate NinjaClaw bootstrap with dependency installation, environment setup, and service startup.

Community
Advanced
benmaierbenmaier

Create data science agents

Design and validate data-science agent prompts and parallel-agent configurations.

Community
Advanced
caw111caw111

serverless-modal

Run GPU workloads on Modal serverless cloud with local-first execution.

Community
Advanced
DexploarerDexploarer
7

Railway Deployment Automator

Automate Railway deployments with GitHub, Docker, and CI/CD workflows.

Community
Advanced