Env And Assets Bootstrap

When you're trying to reproduce an AI research repo and need to set up the environment before running anything, this handles the tedious bootstrap work. It generates conservative conda commands, maps out where checkpoints and datasets should live, and identifies missing dependencies before you waste time on failed runs. The skill focuses specifically on the setup phase after you've picked a reproduction target but before executing any model code. It's honest about what it can't resolve automatically and flags asset sourcing problems early. One solid approach to avoid the usual "missing CUDA toolkit discovered 3 hours into training" surprises.

skills.sh installs: 139.8K
GitHub stars: 506
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add lllllllama/ai-paper-reproduction-skill --skill env-and-assets-bootstrap --agent claude-code

Installs into .claude/skills of the current project.

Files

env-and-assets-bootstrap

Use this as the Rigor Setup skill. The installed slug remains env-and-assets-bootstrap for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should keep setup planning conservative while leaving environment-specific judgment to the model.

When to apply

After repo intake identifies a credible reproduction target.
When environment creation or asset path preparation is needed before running commands.
When the repo depends on checkpoints, datasets, or cache directories.
When the user explicitly wants setup help before any run attempt.

When not to apply

When the repository already ships a ready-to-run environment that does not need translation.
When the task is only to scan and plan.
When the task is only to report results from commands that already ran.
When the request is a generic conda or package-management question outside repo reproduction.