В каталоге 183 730 навыков в 14 категориях.
Use whenever the user wants to obtain, download, or fetch a paper's PDF — given a DOI, an arXiv id, a paper title, a cit...
Paper 图表可视化辅助命令（B 诊断 + C 设计建议双模式自适应）。当用户要查图表、图表诊断、图表设计、画图建议、该用什么图、图注怎么写、配色选什么、色盲友好、坐标轴规范、误差棒标注，或说"帮我看看这张图""图表有什么问题""我该画什...
Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figure...
Generates publication-quality figures and diagrams from output/PAPER_PLAN.md for GIScience, GeoAI, and remote sensing jo...
Reconstruct research-figure images as editable Figma artwork or native PowerPoint figures. Draw, inspect actual previews...
Convert academic paper figures (architecture diagrams, system diagrams, timeline/pipeline diagrams, flowcharts, method o...
用于整篇论文的科研图件规划、数据图、可编辑示意图、实验图片、概念生图、混合组图、图注引用、交付和审稿返修。用户要求制作论文全部主图与补充图、更新数据后同步图件，或从论文材料完成科研绘图流程时使用。
Create, revise, and validate publication-ready academic paper figures and tables. Use for LaTeX tables, related-work com...
Discover recent arXiv papers matching a research profile and generate Obsidian-compatible Markdown notes. Use this skill...
Convert academic papers into engineer-friendly progressive documentation
Add labels, captions, and text references to every figure in a LaTeX paper
Wibi Style 官方视觉风格：把一张照片转换成留白平涂小景。适合街拍、咖啡店、书店、旅行和日常人像，把人物动作与现场关系收成纸面中央的平涂小画。适用于用户要求留白平涂小景、上传照片换风格，或明确调用 $paper-flat-vigne...
Use when planning a source-grounded method overview, architecture, pipeline, system/data-flow, mechanism, or agent-workf...
논문의 초록, 서론, 결론을 쓰거나 고칠 때, 또는 주장과 증거가 맞는지 점검할 때 따르는 구조 원칙. 국문과 영문 논문 모두에 적용. "초록 고쳐", "서론 다시", "주장과 증거 맞나", "기여 정리" 같은 요청...
This skill should be used when extracting structured full text from scientific PDF papers — converting PDFs to TEI XML v...
Use when building reusable Obsidian glossary notes from an existing paper source manifest, optionally with a raw-section...
Paper 命令导航器。当用户问 Paper 能做什么、有哪些命令、该用哪个命令，或说 help / 帮助 / 怎么用 / 命令一览 / 不知道从哪开始时使用——即使用户只说"我想写论文但不知道用什么"也应使用。行为铁律：一轮提问摸清用户当...
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture di...
Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image...
Implement research papers from arxiv. Use when the user provides an arxiv link, asks to implement a paper, or wants to r...
Paper 题录导入命令（题录整理器 + 题录-草稿一致性核对器）。当用户有从知网/Zotero/EndNote 导出的题录要批量整理、整理参考文献、题录入库、做题录与草稿引用的一致性核对、查哪些草稿引用有对应题录、查题录与草稿字段差异，或...
为研究项目搭建标准科研工作目录的脚手架命令。当用户要开始一个新研究项目或新论文、想初始化或规范科研项目的目录结构、要搭多项目科研工作区，或提到 paper-init、科研工作目录时使用——即使用户只是说"帮我建个放论文材料的文件夹"也应使用...
Builds a self-contained paper-context bundle for implementing a research paper — sources, transcription, figures, annota...
Self-improving documentation convergence loop. Computes quality deltas between review rounds, identifies recurring issue...
Paper 论证链检查命令（结构对应检查器）。当用户已有论文大纲、要查论证逻辑、查 RQ 与方法结果结论是否对应、查论证链是否闭环、查论文逻辑结构，或说"帮我查查论证有没有问题""我的逻辑完整吗""RQ 和结论对应吗""方法能不能回答我的问...
当用户改动论文里的核心声明（研究问题、核心论点、因果关系、边界条件、假设、关键结论、对已有研究的态度）时， 必须先扫描该声明在全文其他章节的出现位置，列出来让用户核对哪些需要联动修改，再开始动手。 本 Skill 抓的是「论证一致性」（语义...
Search 10 academic paper databases via REST APIs for research papers, preprints, and scholarly articles. Covers PubMed,...
Searches 18 scholarly APIs for papers, preprints, citations, open-access full text, repository records, and journal OA s...
Find and retrieve scientific papers. Use when locating literature by topic, identifier, author, or citation.
Search 11 academic literature APIs for papers, preprints, citations, and open-access full text, and return results with...
Handcraft paper from plant fibres — fibre harvesting, pulping, sheet forming with a mould and deckle, pressing, and dryi...
On-brand visual marketing content using Paper MCP and parallel agent teams. Reads the project's brand/ directory to buil...
Use when editing an open Paper board through the local Paper MCP server at http://127.0.0.1:29979/mcp. Prefer this over...
Paper 研究设计参谋命令（方法-RQ 匹配检查器 + 方法类引导器）。当用户已有研究问题（RQ）要定研究方法、检查方法能否回答 RQ、选什么方法类、查方法与 RQ 匹配度、研究设计行不行、涉人类被试要理伦理审查提示清单，或说"帮我设计研...
Judge and reshape the story told by an entire paper figure deck. Use when writing or revising a paper to derive a ground...
当用户在一次对话里同时提出多个论文写作任务（"顺便也帮我..."、"另外..."、"还有..."）， 必须先把这些任务列出来让用户挑一个，拒绝在同一个会话里串行做完所有事。 Use when 用户的一条请求里出现两个以上独立的写作 / 修改...
Run a cumulative daily or retrospective sweep of research papers on a chosen topic, audit their claims, methods, integri...
Orchestrate the full PaperOrchestra (Song et al., 2026, arXiv:2604.05018) five-agent pipeline to turn unstructured resea...
Paper 论文大纲命令（结构草案共写器）。当用户已有研究问题（RQ）和文献笔记、要搭论文骨架、起草章节大纲、写论文结构、整理写作框架，或说"帮我把论文大纲列一下""论文应该怎么组织""章节怎么分""我有 RQ 和文献、想搭个大纲"时使用—...
在执行 ≥ 30 条目的批量核查 / 批量修改任务（引用核查、术语一致性检查、格式统一、文献元数据补齐）时， 必须采用"派多个 Agent 并行 + 每个 Agent 输出 JSON + 主进程汇总落盘 + 分批断点续跑"的标准模式， 不得...
Use when comparing or recreating this repo's UI in Paper MCP and fixing parity issues against the live rendered site.
Use when an agent needs to parse a local paper PDF or text artifact into fulltext, sections, snippets, and an extraction...
Convert academic research PDFs into self-contained, highly readable standalone HTML digests that can be read instead of...
在执行任何 ≥ 30 条目的批量任务（批量改文件、批量核查引用、批量重命名、批量格式统一）之前， 必须先在 3–5 个样本上跑一遍，把样本结果给用户看，确认逻辑正确后再推全量。 Use when 用户请求处理"全部"、"所有"、"批量"、"...
Generate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper out...
Produces a detailed, venue-aware paper outline from all available upstream artifacts (RESEARCH_PLAN, lit review, idea re...
Paper 绘图代码生成命令（内建于 paper-figure，可独立调用）。当用户要生成绘图代码、plot 代码、画图代码、matplotlib 代码、ggplot2 代码、帮我生成图表代码、帮我写画图脚本、生成柱状图代码、散点图代码、折...
End-to-end procedure for adding a player-facing feature (command, listener-driven behavior, or config option) to a Bukki...
Resolve, validate, and audit manuscript integrity and applicable requirements for academic manuscripts and paper artifac...
This skills helps agents to review and polish research papers written in LaTeX, focusing on writing clarity, grammar, La...
Polishes existing academic prose while preserving the author's meaning: grammar and flow repair, tone calibration agains...
Systematic top-down workflow for polishing academic papers. Structure to logic to expression with user confirmation at e...
Wibi Style 官方视觉风格：把一张照片转换成纸上人物志·CD版。适合人物日常照片：把动作与穿搭画成橙底日文扁平插画封面，装入透明 CD 盒，生成方形静态产品展示图。适用于用户要求纸上人物志·CD版，或明确调用 $paper-port...
DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.
Generate a conference poster (article + tcbposter LaTeX → A0/A1 PDF + editable PPTX + SVG) from a compiled paper. Use wh...
DEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file wit...
Generate, critique, and iterate image-generation prompts for high-fidelity academic paper poster reference mockups befor...
Paper 开题报告组装命令（多源汇聚组装器）。当用户要写开题报告、组装学位论文开题材料、按中文学位论文制度节点整理立项文档，或说"帮我组装开题报告""开题报告怎么写""开题要准备什么""选题依据怎么写""文献综述部分帮我整理""研究内容部...
在跨多文件批改、术语统一、整篇论文润色、章节重写等可能改动专业术语 / 缩写 / 人名 / 概念命名的操作之前， 必须先显式列出"保护术语清单"，让用户确认哪些词不得被同义替换或改写，再开始执行。 Use when 用户要求跨章节修改、批量...
Create Paper-first UI prototype directions, especially after grill-with-docs has settled product and domain decisions. U...
논문 원고를 독립 심사, 지적 분류, 수정 실행, 문체 정리의 바퀴로 반복해 미리 정한 품질 기준에 닿을 때까지 진행할 때 사용. "품질 나올 때까지 반복", "심사 돌려", "한 바퀴 더" 같은 지시에 적용.
AI 论文速读 Skill：三档深度（裸读 / 引导 / 精读）+ 页码级 Provenance 防幻觉 + 多篇对比。 触发词：论文速读、读这篇论文、抓核心观点、论文对比、多篇对比、与我研究方向的关联、 第几页提到 X、这篇论文的数据集怎...
Rate an academic paper from 1 to 5 by page length, affiliation, citations
내용이 고정된 논문 원고 전체를 처음 읽는 독자 기준으로 쉽고 매력적으로 다듬을 때 사용. "가독성으로 가자", "읽기 쉽게", "발표 점수 올려", "기호 줄여", "숫자를 표로" 같은 요청에 적용. 주장과 숫자는...
基于论文文本的通用读论文助手。用户提供论文文本（文件路径或直接粘贴），解答各类读论文需求——总结、精读、内容问答、概念解释、批判性分析等，并将结果以 Markdown 写入当前工作目录。触发词：读论文、论文总结、精读这篇论文、帮我分析这篇论...
Manage academic paper reading workflows from local PDFs, URLs, web search, Zotero, Obsidian/Dataview, or optional Feishu...
将用户提供的研究论文一次制作成完整、可持续共读的中文 HTML 网页，包含原文与完整翻译、逐图带读、图例对应、论证链、知识卡及随手记；也用于按反馈维护这类网页。
中文论文深读、总结/TL;DR、工程拆解、按论文实现/复现、比较与证据审计。用户给出论文 PDF、链接、标题、摘要、正文或图表，或明确要读论文时使用。只有论文锚点且无附言时澄清阅读目标；只有阅读意图时问哪篇。已有论文时，“看看这篇”直接深读...
以论文作者身份完成学术审稿 rebuttal 全流程。当用户提供审稿意见（reviewer comments / reviews / meta-review）和论文文件（PDF/LaTeX/DOCX/Markdown），需要分析审稿意见、判...
Extracts text from PDF files and generates 3 thought-provoking questions that explore the study in depth. Supports direc...
For all readers, with a specialty in experimental and behavioral research: reconstruct, replicate, adapt, and extend pap...
Make a faceless 9:16 explainer reel in the cut-paper 'Claude mascot' style (flat textured paper shapes, a terracotta box...
Convert academic PDF papers into structured Chinese reading reports with original figures. Use when the user asks to sum...
Map an AI/ML paper into a reproducible claim-to-experiment ledger. Use when Codex needs to turn a paper PDF, HTML digest...
Plan and run minimal environment smoke tests for AI/ML paper reproduction repositories. Use after sources are locked, or...
Audit reproduced AI/ML paper results against the paper's claim map. Use after smoke or experiment runs when Codex must c...
Lock official and trustworthy reproduction sources for an AI/ML paper. Use after a claim map exists, or whenever Codex m...
学术辅导的研究与文献入口。用于澄清选题、检索或导入文献、系统综述筛选、每日文献追踪、讨论研究方法和组装开题报告；从用户自然语言需求选择所需流程，研究决策由用户作出。
Deep-read one or multiple research papers with source-linked explanations, equations, experimental critique, reusable ac...
Use when an agent needs to search scholarly APIs, normalize paper metadata, deduplicate hits, and return a portable rank...
Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files...
Set up and run the botference document-review interface (Google-Docs-style comments on rendered LaTeX/Markdown, bots rep...
Paper 模拟评审命令（多视角模拟审稿意见器）。当用户要投稿前预演评审、答辩前预演、模拟审稿、预审论文、查审稿人会怎么看、学位论文盲审模拟、期刊审稿模拟、答辩委员追问预演，或说"帮我模拟评审""模拟审稿看看""预审下我的论文""审稿人会提...
Review an author's manuscript, its argument and paragraph structure, analyze reviewer comments, draft rebuttals, and ver...
Deep single-paper academic analysis — journal credibility, author profiling, reference verification, citation impact, an...
논문 원고를 표준 기준표(축 일곱, 1~5점 기준 문장, 지적의 크기, 투고처 판)로 모의 심사하고 점수와 지적을 같은 형식으로 낼 때 사용. "심사해 줘", "모의 심사", "리뷰 돌려", "점수 매겨 봐", "심...
Comprehensive peer review of academic papers for top-tier computer science conferences and journals. Supports PDF and La...
Run a pre-submission manuscript audit covering argument, numerics, references, writing, figures, methods, preregistratio...
Run a cross-model adversarial pre-submission audit from Codex. Use when a user explicitly requests the heavier paper-rev...
Reviews the manuscript produced by `paper-draft` (in `output/manuscript/`) as a demanding IJGIS / ISPRS JPRS reviewer-ed...
Use when independently reviewing a research-paper draft before submission, running a mock top-conference panel, assessin...
Comprehensive IEEE PES paper review for Physics-Guided SSL GNN power grid research. Use when reviewing paper sections, c...
Route first-source academic paper and peer-review intelligence collection, crawling, normalization, and synthesis throug...
专业学术论文审稿 skill。以领域专家视角对学术论文（本地 PDF、arXiv ID/URL、粘贴文本）进行系统评审，自动识别论文学科与贡献类型并切换对应领域专家标准，输出顶会 OpenReview 风格（NeurIPS/ICLR/ICM...
Expert academic paper review including summary, methodology critique, and practical implications
Paper 修订辅助命令（修订建议对照表 + 逐点回复信起草器）。当用户投稿/答辩后收到审稿意见要写回复信、要逐点回复审稿人、要改稿、要准备 point-by-point response、要 response letter、要修订建议、要...
Automated academic paper and technical content scanning for the Research department. Discovers relevant papers from arXi...
Transform a supplied photograph into a tactile miniature layered paper diorama. Use for 微型纸雕、立体纸艺场景、paper-cut photo scen...
Paper 系统综述筛选命令（PRISMA 2020 筛选台账 + 流程图生成器）。当用户要做系统性文献综述、做 PRISMA 筛选、定纳入排除标准、两轮筛选文献、文献去重、要 PRISMA 流程图、要数据提取表、要偏倚风险评估清单、要 P...
文献检索与综述辅助命令。当用户已有研究问题（RQ）或明确方向，要查文献、做文献综述、找研究缺口（Research Gap）、了解"某方向别人做到哪一步"时使用——即使用户只说"帮我查查这方面的研究""这个领域有哪些论文""有没有人研究过 X...