Loading...
Loading...
Found 4 Skills
Submission cover letter assistant for academic papers. Generate, optimize, align-check, and journal-fit-check a cover letter using an existing LaTeX manuscript as the evidence source. Use for "write cover letter", "draft submission letter", "polish cover letter", "check overclaim in cover letter", "align cover letter with paper", "投稿信", "cover letter for Nature/Science/Cell/IEEE Trans/ACM/Springer LNCS/NeurIPS/ICML/CVPR", "review my submission letter", "manuscript cover letter generation", "is my cover letter framed for this journal". Use latex-paper-en for source edits to main.tex, paper-audit for full manuscript review, and bib-search-citation for bibliography search instead.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Write, revise, and polish SCI journal papers based on LaTeX paper projects. Defaults to AI autonomous mode, and also supports human-machine collaboration where only review plans are output; provides author-stylized writing, numerical fact verification, multi-round logical tree review, and a closed-loop PDF/Word rendering workflow. ⚠️ Not applicable: Format/style parameter-only modifications, pure reference management, image processing, non-paper writing tasks.
Deep anonymization sweep for double-blind paper submissions, plus clean de-anonymization for camera-ready. Use when a researcher says "anonymize my paper", "double-blind check", "blind this submission", "remove author names", "did I leak my identity" — or, after acceptance, "de-anonymize" / "restore authors for camera-ready". Sweeps the whole leak surface, \author/\affiliation/\email/\orcid/\thanks, acknowledgments and grant numbers, hyperref pdfauthor and compiled-PDF metadata, first-person self-citations (rewritten to third person), GitHub/dataset/homepage links vs anonymized mirrors, LaTeX comments, .bib annotations, home-directory paths, and supplementary material (.git dirs, notebooks, LICENSE/AUTHORS files). Bundles a stdlib-only scanner (scan_anonymization.py, check ids shared with preflight-check) and a reversible-edit workflow (toggle + manifest) so every change is cleanly undone at camera-ready. Advisory only; never submits anything.