Research AI Skills

Use when reviewing mathematical validity, evidence, reproducibility, figures or a submission draft.

盒子原创行业研究 Skill 组合中的商业模式分析专项。研究一个行业常见的商业模式、组合方式、演变趋势与护城河；或研究一家企业的业务与盈利模式，并与主要竞争企业比较。用于“这个行业有哪些商业模式”“分析某公司的商业模式”“这家公司和同行怎么赚钱”“模式怎样组合、扩张和演变”等问题，也支持收入成本、单位经济、现金转换等局部分析，交付对应的商业模式分析报告。 由…

想法群聊室 — 调研员角色。被 idea-team 主编排器调用，或用户单独说"调研一下 X"、"X 的现状/竞品/数据"、"找 2026 数据"、"事实底"时触发。**用 WebSearch 拉真实 2026 数据、列竞品、引来源——只给事实，不评判，不建议**。Do NOT use when 用户要评价想法好坏（那是反方）、或要跨界启示（那是类比者）、或已有 PRD…

Full-stack autonomous math modeling agent for CUMCM (全国大学生数学建模竞赛). Reads the problem statement and data, iterates through research → coding → verification → LaTeX writing, and produces a…

Polish rough Yuque notes into structured, readable documents while preserving their meaning. Use when the user wants to clean up a draft, improve layout, or turn fragments into a document; trigger…

Chinese Word document formatting toolkit for .docx/.doc/.wps workflows. Use when Codex needs to diagnose document formatting, fix mixed Chinese/English punctuation and spacing, apply…

A decision board for evidence-based calls — the human adjudicates, the agent runs the errands. Three layers (sources → ideas → output) in plain markdown, synced on the human's command, projected onto…

Help produce written content by researching topics and gathering references. Use when user needs to write articles, emails, documentation, reports, or any content requiring research. Triggers: write,…

Use when generating a daily 24h AI / Agent / AIGC top-news briefing, publishing it as a Feishu/Lark native document, validating it, and optionally archiving it to Bitable.

Use to get a brand and its content CITED and RECOMMENDED by AI answer engines — the GEO (Generative Engine Optimization) / AI-search-visibility skill. Run when the user says "GEO," "get cited by…

Extracts figures and sub-figures from academic PDF papers. Supports Fig/Figure, Scheme, Chart, Supplementary Figure, Extended Data Figure (Nature), and Chinese equivalents (图/方案/示意图/附图/补充图).…

Generate a whole-paper modeling backbone for a HUAWEI Cup post-graduate contest problem, comparing candidate models per question with selection reasons, innovation points and validation routes. Use…

USE FOR web search, research, RAG, grounding, browse, find, lookups, fact-checking, documentation, agentic AI. All-in-one, optimized for AI agents. Pre-extracted, token-budgeted web content, deep…

核实护理研究数据版本、量表与计分、变量字典、缺失及联结条件，输出数据就绪清单和真实的数据/代码可用性声明。适用于分析前核实与数据管理；不自行替代统计建模或批准公开研究数据。

Wibi Style 官方视觉风格：把一张照片转换成蓝纸漫画大字海报。适合动作和穿搭清楚的人物日常照片，绘成蓝纸漫画海报；按照片设计英文大字，让人物与文字形成遮挡或承托。适用于用户要求蓝纸漫画大字海报，或明确调用 $blue-paper-manga-type 时。

复用已验证的web研究轨迹，完成问题拆解、同源检索、引用报告和完成验证。

Create professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage. Fast-turnaround format focusing on…

Use when the user asks to find, sharpen, evaluate, rewrite, or explain the story in scientific or scholarly materials across disciplines, including manuscripts, grants, paper outlines, abstracts,…

Systematically discover and shortlist academic literature for a research project. Use when building a reading corpus from scratch, expanding an existing one, filling topic or language gaps, or turning…

Monitor and summarize blog posts, RSS feeds, and web content for research and staying current with topics.

CSMAR (国泰安) 数据清洗标准 SOP，覆盖高频用表 / 通用清洗规则（ST 剔除、IPO 当年剔除、金融行业处理、缺失值）/ 缩尾标准 (winsorize 1%/5%) / 公司 ID 变更追踪 / CSRC 行业代码映射 / 时间对齐 / 国内学者常见陷阱。提供 Stata / R / Python 三语言模板。当用户处理 CSMAR…

Guide users through setting up a personal LLM-maintained wiki — a persistent, compounding knowledge base where the LLM incrementally builds and maintains interlinked markdown pages from raw sources.…

Create, revise, or audit academic data/result figures for CS/AI/ML papers. Data/result plots default to Python-generated editable SVG with CS/AI/ML-specific design rules for benchmarks, ablations,…

Iterate an existing paper or report from concrete review feedback: audit claims and source data, redesign figures, tighten layout, synchronize numbers, render, and verify the final document in place.…

深度调研技能：对任意命题进行系统性调研并输出专业研究报告。 覆盖技术选型、行业分析、学术研究、竞品分析、概念探索等所有调研场景。 核心方法论：快速扫描→假设驱动研究、内外数据结合（先摸清内部现状再对标外部水位）、 反面证据强制搜索、数据来源三级分类、结论置信度分级、多层次报告输出。 采用 Orchestrator-Subagent 架构（Lead+Sub-agent…

Write or fix the hook of a papercut reel. Produces the SAY / WRITE / SHOW / ALIGN block, five variants scored with the hook check, the frame-0 cover title and the motion out of the hook. Use for…

Master Anti-AI Academic Paper Refactoring & Style Guide. Designed to K.O. (Knock Out) GPT-5.6 SOL's mechanical phrasing, convoluted "绕人" nested modifiers, formulaic transition words, empty abstract…

为医学主题设计并执行可复现的中英文文献检索，产出查询式、检索记录和去重后的候选文献池。当用户要“查文献” “覆盖 PubMed 和中文来源”或核实某研究问题的文献范围时使用；本技能负责发现与记录，深度精读交给 dyz-med-key-literature，系统综述的正式筛选与纳入流程交给 dyz-med-screening-pipeline。无法直接访问知网、万方或 维普时只能提供…

Matt Berman's custom SEO content engine. Learns your brand through a smart interview, then creates content that ranks AND converts using Puppet Strings, Scroll Traps, and Care To Click psychology.…

Audit the reasoning of a document or argument (memo, proposal, investment analysis, board paper, article, the user's own draft): claims, evidence, unstated assumptions, logical gaps, fallacies, and…

组织论文论证、起草或修改章节、核对学位论文一致性，也可单独自然润色并匹配作者语气。用于学术文字与实质写作；只润色时不启动整套研究流程。

欧洲留学申请文书与 CV 方法咨询。当用户输入 /euro-docs，或说"帮我写动机信"、"Motivation Letter 怎么写"、 "CV 怎么改"、"简历要放照片吗"、"CV 怎么导出 PDF"、"个人陈述"、"SoP"、"推荐信找谁写"、 "Research Proposal 怎么写"、"文书怎么润色"时触发。motivation letter、statement of…

Smart Resale Agent hub. Orchestrates the complete 7-step C2C resale workflow. Use when user wants to sell second-hand items, list goods on resale platforms (Xianyu/闲鱼, Zhuanzhuan/转转, eBay, Depop),…

Use this skill whenever the user wants to search, verify, screen, compare, or organize real academic papers and return traceable paper addresses or links, especially for literature reviews, core-paper…

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use…

Search the web, extract URL content, and run deep research using the Parallel Chat API and Extract API. Use for ALL web searches, research queries, and general information gathering. Provides…

Run an adversarial mathematical workflow in Codex: verify proofs, write hard proofs, explore conjectures, search for counterexamples, and triage possible gaps. Use for important theorem checks, failed…

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via…

Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates…

Generate a detailed content brief for a specific article or page. Use when the user asks to "create a content brief", "write a brief", "article outline", "blog brief", "writing brief", "content…

Decompose a refined research question for a literature review into 3-5 clear, mostly non-overlapping review modules. Use when the user has a core review question and needs to build a literature review…

Set up and maintain the Parallel CLI (install, auth, balance, skills install)

历史分析、分期、物质文化和史学方法专家——验证历史一致性，以扎根于一手和二手资料的真实时代细节丰富设定

Conduct deep research on any topic — get comprehensive reports with citations, key findings, and actionable insights in minutes. Use when user wants to "deep research", "research this", "investigate",…

Reads and analyzes academic papers (arXiv preprints, conference / journal PDFs, Zotero items) at three configurable depths: quick skim (2 min), standard read (10 min), or deep analysis (30 min).…

Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science…

Retrieves NCBI BioProject metadata — title, description, organism, submitter and release dates — for a batch of BioProject accessions, using the official NCBI E-utilities API rather than scraping the…

Runs programmatic 1-to-many ABM for 50-200+ accounts: automated personalization, scaled outbound, intent-based targeting, and lookalike expansion. Use when ABM coverage must grow without adding…

Design and run ML experiments on cloud GPUs. Generates experiment code, runs on Modal, tracks results in JSONL. Use when asked to "run experiments", "train a model", "test this hypothesis", or…

Latest news articles, regulatory filings, community discussion topics for listed stocks, and SEC EDGAR filing analysis (10-K/10-Q/8-K/proxy/Form 4) via Longbridge. Triggers: "新闻", "公告", "资讯", "话题",…

Use when a Research Architect project or existing draft needs claim-level literature support for background, positioning, methods, interpretation, limitations, or revision, rather than broad generic…