env-and-assets-bootstrap
lllllllama/rigorpilot-skills
Prepare conda environments and asset paths for README-documented deep learning repo reproduction.
What is env-and-assets-bootstrap?
This skill sets up conservative conda-first environments and asset path assumptions for deep learning repository reproduction. Use it after identifying a credible reproduction target to prepare environment creation, checkpoint/dataset paths, and cache location hints before running any commands.
- Generate conservative conda environment setup notes tied to repo README
- Produce candidate conda commands for environment creation
- Plan asset paths for checkpoints, datasets, and cache directories
- Identify checkpoint and dataset source hints from repo documentation
- Flag unresolved dependency or asset risks before execution
How to install env-and-assets-bootstrap
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill env-and-assets-bootstrap- Target repository path with README documentation
- Identified reproduction goal or experiment name
- Knowledge of OS and any package constraints
How to use env-and-assets-bootstrap
- 1.Provide the target repo path and selected reproduction goal
- 2.Share relevant README setup steps and known constraints
- 3.Run the skill to generate environment setup notes and conda commands
- 4.Review the asset path plan and checkpoint/dataset source hints
- 5.Address any flagged dependency or asset risks before proceeding to execution
Use cases
- Preparing a conda environment for a deep learning paper reproduction before first run
- Planning dataset and checkpoint directory structure for a multi-stage training pipeline
- Identifying missing dependencies or asset sources from README before attempting setup
- Creating environment assumptions for a repo that requires specific Python/CUDA versions
- Documenting asset paths and cache locations before handing off to execution
- ML researchers reproducing published deep learning work
- Engineers setting up training environments from README-documented repos
- Teams preparing reproducible setups before distributed runs
- Anyone translating repo setup instructions into executable environment plans
env-and-assets-bootstrap FAQ
No. This skill is specific to README-documented repo reproduction. Use it only when preparing a concrete target repository for setup.
No. Target selection happens before this skill. This skill only prepares the environment and assets once a target is chosen.
No. It generates conservative setup notes and candidate commands for you to review and execute.
The skill will flag this as a risk and may forward gaps to an optional paper resolver, but conservative setup planning requires documented guidance.
The skill is POSIX-first (conda + bash). Windows support depends on repo-specific constraints and may require manual translation.
Full instructions (SKILL.md)
Source of truth, from lllllllama/rigorpilot-skills.
name: env-and-assets-bootstrap description: Rigor Setup skill for README-first deep learning repo reproduction. Use when the task is specifically to prepare a conservative conda-first environment, checkpoint and dataset path assumptions, cache location hints, and setup notes before any run on a README-documented repository. Do not use for repo scanning, full orchestration, paper interpretation, final run reporting, or generic environment setup that is not tied to a specific reproduction target.
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
../../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.
Clear boundaries
- This skill prepares environment and asset assumptions.
- It does not own target selection.
- It does not own final reporting.
- It does not perform paper lookup except by forwarding gaps to the optional paper resolver.
Input expectations
- target repo path
- selected reproduction goal
- relevant README setup steps
- any known OS or package constraints
Output expectations
- conservative environment setup notes
- candidate conda commands
- asset path plan
- checkpoint and dataset source hints
- unresolved dependency or asset risks
Notes
Use references/env-policy.md, references/assets-policy.md, scripts/bootstrap_env.py, scripts/plan_setup.py, and scripts/prepare_assets.py.
Use scripts/bootstrap_env.sh only as a POSIX wrapper around the Python bootstrapper when a shell entrypoint is more convenient.
Related skills
More from lllllllama/rigorpilot-skills and the wider catalog.
analyze-project
Read-only analysis of deep learning repositories to understand structure, configs, and suspicious patterns.
ai-research-explore
Auditable deep learning research exploration with idea gating, fair comparison, and governed experiments.
explore-code
Auditable exploratory code modifications for deep learning research on isolated branches with rollback tracking.
ai-research-reproduction
README-first deep learning repository reproduction with auditable evidence and standardized outputs.
paper-context-resolver
Resolve reproduction-critical paper details when README and repo files leave gaps.
safe-debug
Conservative diagnosis and minimal patching for deep learning training failures without automatic code mutation.