Rigor Train skill for deep learning research repositories.
NewMaintained
Automatic
◆AI Engineer pack
Last verified 9/7/2026
What it changes
3 of 22 test cases passed with the skill.
Pass-rate lift
—
Tokens
-22%
Agent turns
0%
Response time
-14%
Model gemini-3.6-flashMeasured 9/7/2026v23 of 22 cases passed with skill · 4 comparable
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 4 comparable cases; this report requires 8.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
We just cloned a new repository `github.com/example/paper-impl`. Please analyze the repository structure, find which paper gaps exist in the implementation, and write an intake report on missing functions.
What was checked, without and with the skill
Checked
Without skill
With skill
The response declines to perform repository intake analysis.
Missed
Passed
The response refrains from creating train_outputs documentation.
Passed
Passed
case-19 · gemini-3.6-flash · 9/7/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md51 lines7 filesincludes scripts
run-train
Use this as the Rigor Train skill. The installed slug remains run-train for
compatibility.
Use the shared operating principles in
../ai-research-reproduction/references/agent-operating-principles.md; this skill should keep
training evidence bounded while leaving repository-specific monitoring details
to the model.
When to apply
When the training command has already been selected and should be executed conservatively.
When the researcher wants startup verification, short-run verification, full training kickoff, or resume handling.
When the run needs structured training status, checkpoint, and metric reporting.
When not to apply
When the main task is environment setup or asset download.
When the researcher wants inference-only or evaluation-only execution.
When the task is speculative exploration, multi-variant sweeps, or autonomous idea implementation.
When the user still needs repository intake or paper gap resolution.
Clear boundaries
This skill executes a selected training command and normalizes the resulting evidence.
It does not choose the overall research goal on its own.
It does not own exploratory branching or speculative code adaptation.
It should record partial, blocked, resumed, and kicked-off states clearly.
It should preserve reproducibility context such as configs, seeds,
checkpoints, logs, metrics, and runtime assumptions when available.
Input expectations
selected training goal
runnable training command
environment and asset assumptions
run mode such as startup verification, short-run verification, full kickoff, or resume