neurips-writing-style
Use when rewriting a machine-learning paper for NeurIPS-style contribution framing, calibrated claims, contribution-type alignment, limitations, broader-impact prose, and language that pre-fills the mandatory NeurIPS Paper Checklist, for either the main track or the Datasets & Benchmarks track.
Profile →npx skills add brycewang-stanford/Awesome-Journal-Skills --skill neurips-writing-style --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# NeurIPS Writing Style NeurIPS writing must make a technical contribution legible to reviewers outside the authors' exact subfield. Good style is precise, evidence-calibrated, and checklist-aware. ## Introduction pattern 1. Name the problem and why current ML practice cannot solve it. 2. Identify the specific gap in method, theory, data, evaluation, system, or understanding. 3. State the contribution type and why it fits NeurIPS. 4. Preview the evidence that supports the claim. 5. Bound the claim with limitations, assumptions, or failure modes. ## Style rules - Prefer falsifiable claims over broad adjectives. - Tie every headline result to a baseline, dataset, theorem, ablation, or user/deployment context. - Use "we show" only when the paper actually proves or demonstrates the claim. - Do not bury limitations; NeurIPS reviewers are instructed to reward honest limitation reporting. - Avoid "state of the art" unless the comparison set, metric, and time boundary are explicit. - Document non-standard agent or LLM use in the method when it is part of the research procedure. ## Write so the prose pre-answers the checklist The mandatory NeurIPS Paper Checklist asks each "yes" answer to p
- Introduction pattern
- Style rules
- Write so the prose pre-answers the checklist
- Reviewer-pushback rewrites
- Worked vignette: a new optimizer paper
- Rewrite output
What does the neurips-writing-style skill do?
Use when rewriting a machine-learning paper for NeurIPS-style contribution framing, calibrated claims, contribution-type alignment, limitations, broader-impact prose, and language that pre-fills the mandatory NeurIPS Paper Checklist, for either the main track or the Datasets & Benchmarks track.
How do I install it?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill neurips-writing-style --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Awesome-Journal-Skills, a repository with 909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.