Rigor Setup skill for README-first deep learning repo reproduction.
SkillScore77Maintained
Automatic
◆DevOps & SRE pack
Last verified 9/6/2026
What it changes
Passed 13 of 17 test cases with the skill, and 7 of 17 without it.
Without skill41%
With skill77%
Checks it passed that the model alone missed
The output delegates paper resolution gaps to the paper resolver.
The output references scripts/plan_setup.py for planning the setup.
The output identifies scripts/bootstrap_env.sh as the POSIX wrapper script.
and 5 more in the full report
8 fixed9 passed either way5 still failing0 broke
Pass-rate lift
+36 pp
Tokens
-30%
Agent turns
0%
Response time
-41%
Model gemini-3.6-flashMeasured 9/6/2026v217 of 22 cases passed with skill · 17 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 6
Prompt
We are preparing a setup blueprint for reproducing a diffusion model codebase in `/workspace/diff-model`. We need to generate the environment bootstrap script execution command. Which Python utility script in the repository setup scripts directory should be invoked directly for automated environment bootstrapping?
What was checked, without and with the skill
Checked
Without skill
With skill
The output references scripts/bootstrap_env.py as the primary environment bootstrapper script.
Missed
Passed
case-02 · gemini-3.6-flash · 9/6/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md49 lines13 filesincludes scripts
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.
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.