Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Rigor Explore compatible skill slug for meaningful and potentially novel deep learning research candidates.
Passed 9 of 16 test cases with the skill, and 2 of 16 without it.
and 7 more in the full report
10 fixed3 passed either way10 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to perform bounded code adaptation to add a custom loss function in `losses/focal.py` on branch `explore/focal_loss` before executing candidate trials. Which delegated skill handles this code adaptation?
| Checked | Without skill | With skill |
|---|---|---|
| Delegates bounded code adaptation to explore-code. | Missed | Passed |
The instructions your model reads when the skill loads.
Use this as the Rigor Explore compatible skill slug after the researcher
explicitly authorizes candidate-only work on top of a durable
current_research anchor. The installed slug remains ai-research-explore for
compatibility. Rigor Explore is for meaningful and potentially novel deep
learning research candidates while preserving scientific rigor, comparability,
reproducibility, and auditable collaboration. Novelty and significance remain
hypotheses before literature contrast, ablation evidence, and fair comparison.
The skill does not promise autonomous discovery, global benchmark completeness,
novelty proof, or trusted reproduction success.
Start from the shared operating principles in
../ai-research-reproduction/references/agent-operating-principles.md, then load
../ai-research-reproduction/references/research-rigor-principles.md for research claims and
../ai-research-reproduction/references/deep-learning-experiment-principles.md when experiment
details affect comparability or reproducibility.
Use this skill only when the request has both:
current_research context such as a branch, commit, checkpoint,
run record, or already-trained local model state.Keep narrow code-only requests on explore-code. Keep narrow run-only requests
on explore-run. Keep passive repository analysis on analyze-project. Keep
README-first reproduction on ai-research-reproduction.
Use a two-loop rhythm:
test cases passed, vs 2 / 16 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.