yuangao-tum
UserClaude Code skills for writing peer-review rebuttals: process + tactics (write-rebuttal) and 28 per-concern answer templates (nlp-rebuttal)
Categories
Indexed Skills (2)
nlp-rebuttal
Scenario playbook for answering a SPECIFIC reviewer concern in an NLP/ML/AI rebuttal — 28 concern types (novelty, simple combination, unclear motivation, weak baselines, marginal gains, missing ablations, no significance, data leakage, no human eval, reproducibility, and more), each with a bad-answer anti-pattern and a recommended-answer template. Use when drafting a reply to a concrete review comment, when the user quotes a reviewer ("the reviewer says...", "R2 complains..."), asks which strategy fits a concern, or asks for a rebuttal reply template. Complements write-rebuttal (overall process and tactics); this skill picks the response strategy per concern.
write-rebuttal
Write conference/journal author-response rebuttals that clarify and convince, following Parikh–Batra–Lee's "How we write rebuttals" method (two-audience mindset, itemize→brain-dump→draft→revise, 18 tactics, the neutral-third-party test). Use when responding to peer reviews, writing an author response / rebuttal / reviewer reply for NeurIPS, ICLR, ICML, CVPR/ICCV/ECCV, AAAI, ACL/ARR/EMNLP, or any venue, planning rebuttal experiments, or when the user says "rebuttal", "author response", "respond to reviewers".
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.