Rigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories.
SkillScore82Maintained
Automatic
◆AI Engineer pack
Last verified 9/6/2026
What it changes
Passed 15 of 18 test cases with the skill, and 7 of 18 without it.
Without skill41%
With skill82%
Checks it passed that the model alone missed
Uses scripts/plan_variants.py for variant planning.
Uses variant_axes to define the candidate dimension grid.
Uses selection_weights to rebalance candidate scoring factors.
and 6 more in the full report
9 fixed9 passed either way4 still failing0 broke
Pass-rate lift
+41 pp
Tokens
-19%
Agent turns
0%
Response time
-34%
Model gemini-3.6-flashMeasured 9/6/2026v218 of 22 cases passed with skill · 18 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
Which helper script in the repository scripts folder is dedicated to calculating and generating candidate variant plans before execution?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses scripts/plan_variants.py for variant planning.
Missed
Passed
case-19 · 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.md56 lines7 filesincludes scripts
explore-run
Use this as the Rigor Improve / Rigor Explore run leaf skill. The installed slug
remains explore-run for compatibility.
Use the shared operating principles in
../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide
candidate run planning while preserving model judgment about the active repo.
When to apply
When the researcher explicitly authorizes exploratory runs.
When the task is a small-subset validation, short-cycle training probe, batch sweep, idle-GPU search, or quick transfer-learning trial.
When the output should rank candidate runs rather than certify trusted success.
When not to apply
When the user wants trusted training execution or conservative verification.
When there is no explicit exploratory authorization.
When the task is repository setup, intake, or debugging.
Clear boundaries
This skill owns exploratory execution planning and summary only.
Use ai-research-explore instead when the task spans both current_research coordination and exploratory code changes.
It may hand off actual command execution to minimal-run-and-audit or run-train.
It should keep experiment state isolated from the trusted baseline.
It should prefer small-subset and short-cycle checks before heavier exploratory runs.
It should label run results as bounded evidence and explain when a comparison
is not directly fair.
Ranking Semantics
Pre-execution candidate selection uses three factors: cost, success_rate, and expected_gain.
Default weights should stay conservative unless the researcher explicitly provides selection_weights.
Budget pruning still applies after scoring through max_variants and max_short_cycle_runs.
If runs are executed later, downstream ranking should switch to real execution evidence, not stay purely heuristic.