Loading...
Loading...
Found 159 Skills
Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (Codex GPT-5.4 xhigh), fixes each gap with full derivations, re-reviews, and generates an audit report. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
Search, filter, and format entries from BibTeX or BibLaTeX .bib files for research workflows. Use when a user wants to find papers, search a bibliography, filter a library, or look up references by topic, author, year, venue, DOI, arXiv ID, keywords, annotation, abstract, or entry type. Handles Zotero-exported libraries. Supports compact search expressions such as author:, year-gte, type:, and has:, combined filters, research-oriented output fields, raw BibTeX export, and LaTeX/Typst citation snippet generation.
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.
Fully autonomous research pipeline that turns a topic idea into a complete academic paper with real citations, experiments, and conference-ready LaTeX.
Optimize and prepare figures for arXiv submission: format conversion (EPS/PDF/PNG/JPG), size reduction, metadata stripping, processor compatibility (DVI vs PDFLaTeX). Triggers on: "optimize figures for arXiv", "reduce figure size", "convert figures for arXiv", "fix arXiv figures", "figure too large", "arxiv image compression". Companion to arxiv-preflight and arxiv-package.
Audit academic manuscripts for typographic design conventions: booktabs table style, caption placement, dashes/quotes, units and numbers, cross-reference style, page layout, typographic hierarchy, professional polish. Triggers on: "check typography", "fix formatting", "polish my paper", "check my LaTeX", "typographic review", "make it look professional", "check tables", "fix captions". Companion to manuscript-review (content) and arxiv-preflight (compliance).
Translate Chinese academic text into polished English for journal submission. Produces LaTeX output with bilingual comparison. 将中文学术草稿翻译为投稿级英文。
Use this when users explicitly request to "generate NSFC schematic diagram/mechanism diagram" or need to convert the research mechanism, algorithm architecture, and module relationships in the proposal into "editable + embeddable" diagrams. By default, editable source files (`.drawio`) and rendered files (`.pdf`/`.svg`/`.png`) are output; when users actively mention the Nano Banana/Gemini image model, you can switch to PNG-only mode. ⚠️ Not applicable scenarios: Users only want to polish the main text (should rewrite text directly), only want to modify the format/size of existing images (should use image processing skills), and have no clear intention of requiring "schematic/mechanism diagram".
Use this when the user explicitly requests to "write/polish NSFC grant abstract", "generate Chinese and English abstracts", or "translate Chinese abstract to English abstract". Output both Chinese and English versions: The English version must be a faithful translation of the Chinese version (no additional information, no omission of key constraints). The default limit for Chinese abstract is ≤400 characters (including punctuation), and ≤4000 characters for English abstract (including punctuation); the final limit shall prevail as specified in `skills/nsfc-abstract/config.yaml:limits`. Also output **title suggestions**: By default, provide 1 recommended title + 5 candidate titles with justifications (the quantity shall follow `config.yaml:title.title_candidates_default`). Output method: Write the results to `NSFC-ABSTRACTS.md` in the **working directory** (the file name shall follow `config.yaml:output.filename`), which includes in order `# Title Suggestions`, Chinese abstract, English abstract, and length self-check. ⚠️ Not applicable in the following cases: - The user only wants to translate a general text unrelated to grant proposals (direct translation is required instead) - The user only wants to write the main body of project justification/research content/research foundation (use the corresponding NSFC series skill instead)
Write/restructure the "(3) Research Basis" section of the NSFC main text, and simultaneously organize "Working Conditions" and "Research Risk Responses". Use an evidence chain to prove the project is feasible, resource conditions align with research content, and risk contingency plans are executable. Suitable for scenarios where users need to write/revise sections such as "Research Basis, Preliminary Work, Feasibility Analysis, Working Conditions, Platform Team, Risk Responses".
This tool is used when users explicitly request "generate NSFC technical roadmap/roadmap drawing/roadmap/flowchart" or need to convert research content in grant proposals into a "printable, A4-readable" technical roadmap. It outputs editable source files (`.drawio`) and rendered results that can be embedded in documents (`.svg`/`.png`/`.pdf`). ⚠️ Not applicable: Users only want to modify the format/size of an existing image (should use image processing tools) or only want to polish the textual description of the technical roadmap (should directly rewrite the text).
Extract structured review themes from any input source: supports files (PDF/Word/Markdown/Tex), folders, images, natural language descriptions, web URLs, etc.; automatically identifies input types and extracts content; generates structured output of "Theme + Keywords + Core Questions" which can be directly used for systematic-literature-review and other literature review skills.