From neurips-skills
Packages NeurIPS research artifacts (code, data, models, demos, benchmarks) for anonymous review, reproducibility, or public release. Guides artifact decisions, anonymization, and output formatting.
How this skill is triggered — by the user, by Claude, or both
Slash command
/neurips-skills:neurips-artifact-evaluationThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
NeurIPS main track does not reduce artifact quality to a generic badge workflow. It expects code,
NeurIPS main track does not reduce artifact quality to a generic badge workflow. It expects code, data, and execution details when they are needed to support the scientific claim, and its checklist and code/data guidance make artifact quality visible to reviewers.
README with exact commands, environment, expected runtime, hardware assumptions,
and which experiments are reproducible from the package.[Artifact role] method / dataset / benchmark / model / demo / proof / none
[Review package] sufficient / insufficient
[Anonymity risks] <paths, metadata, URLs, usernames>
[Reproducibility gaps] <commands, environment, data, hardware, licenses>
[Public-release plan] <archive, DOI, license, docs>
npx claudepluginhub brycewang-stanford/awesome-journal-skills --plugin neurips-skillsPackages ICML artifacts (code, data, weights, notebooks) for double-blind review and public release. Checks anonymity, licensing, decision relevance, and OpenReview code URL compliance.
Packages ICLR paper artifacts (code, data, checkpoints, demos) for anonymous review and post-acceptance release, with guidance on minimal reproduction paths, anonymization, and reviewer-friendly structure.
Assists with NeurIPS reproducibility: aligns Paper Checklist with the paper, writes code/data instructions, sets seed/compute disclosure, and decides MLRC vs. main track.