Research AI Skills

Light 科研主线第 4 步·审 idea：以**顶会审稿人标准严审** idea，**撞车/无创新 fatal flaw 一票否决**(critical 门)， 逼出真能发表的 idea。何时用：用户问"这 idea 行不行/够不够新/能不能发""帮我严审/挑刺/找致命问题" / idea 定稿前把关 / 收到 idea-generation 的候选要审 / 怀疑撞车(被人做过)。触发词：审…

Canonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.

Independently research and write an AI-narrative / due-diligence card for a crypto token — the kind of "叙事分析" card that covers what story a token is telling and what's independently verifiable about…

安全追踪热点、研究关键词和拆解竞品内容，并将结果转成原创选题和证据包。用于用户要求找热点、看趋势、分析爆款、研究竞品账号、拆标题或开头、比较内容结构、发现评论需求和判断时效窗口。只做公开信息研究和只读采集，不自动互动、发布或使用主账号登录态抓取竞品。

Refresh and improve existing blog posts to outrank competitors using a 6-phase content audit and SERP gap analysis. Use when the user wants to update, refresh, or improve an existing blog post,…

Use when auditing, restructuring, or revising a research manuscript whose scientific question, claim hierarchy, evidence chain, section logic, figures, terminology, or prose may be unclear or out of…

Compile the Beamer tutorial deck and write a build report.

Load when a story needs factual grounding the writer doesn't have: historical detail, cultural texture, domain accuracy, or how other authors handled similar material. Pass the question and story…

Run a fast 2-agent pre-submission check for an economics paper — focuses on contribution, identification, and causal overclaiming. Completes in ~1 minute.

Typst paper assistant for existing .typ manuscripts in English or Chinese. Use for compile/export diagnosis, venue formatting, BibTeX/Hayagriva checks, grammar, logic, abstract/title, tables,…

Search the web with LLM-optimized results via the Tavily CLI. Use this skill when the user wants to search the web, find articles, look up information, get recent news, discover sources, or says…

Review user journeys, public content, and codebases for potentially relevant EU AI Act provisions, with exact official citations, evidence gaps, application dates, and plain-language next actions. Use…

This skill should be used when the user asks for "deep research", "research team", "comprehensive analysis", "research report", "investigate thoroughly", "compare X vs Y in depth", or needs synthesis…

Use when turning an academic paper PDF/arXiv/OpenReview page/local LaTeX source into a single-file Chinese HTML deep-reading page, especially when the user wants a Cheat-Sheet style explanation, KaTeX…

Review a user-provided Chinese mathematical-modeling abstract without requiring the problem statement or full paper, identify concrete writing defects, and prioritize revisions. Use when the user asks…

Guided statistical analysis: test choice, assumption checks, effect sizes, power, APA reporting. Pick tests, verify assumptions, or format results for publication. Covers frequentist (t-test, ANOVA,…

Pre-submission validation audit for arXiv papers across TeX source, PDF, figures, metadata, bibliography, file organization, and common-error scans. Produces pass/fail report with specific fixes per…

Generate publication-style charts from structured data. Use when the user wants a figure, chart, or visualization for research results.

盒子原创行业研究 Skill 组合中的产业链分析专项。梳理行业或企业所在链条的功能、角色、上下游关系与代表企业，分析成本、利润、瓶颈和技术替代，交付 Markdown 分析及可编辑、美化的产业链图。 由 `hehe-industry-researcher`…

只读检索小红书公开内容，并把账号数据、标题、封面、互动量、作者近期内容和低粉爆款整理成可追溯证据。用户要求查公开账号或笔记数据时使用；不得点赞、收藏、评论、发布、删除或导出登录凭证。 English: Read-only research for public Xiaohongshu content, collecting traceable evidence such as account…

Route a fixed research topic into a rigorous paper-generation workflow. Handles active literature search, innovation framing, contribution/evidence planning, and routes to either the review writer or…

Threads Content Specialist. Writes Threads-native posts — short, direct, opinion-led, made for conversation. Strictly enforces the 500 character limit with a count on every post. Supports standalone…

Web search and content extraction via the Tavily API. Use when you need real-time web results, citations, or raw article content without a browser. Requires TAVILY_API_KEY.

Academic paper search and metrics analysis. Searches arXiv, PubMed, Web of Science, Springer Nature, Scopus, Semantic Scholar, and OpenAlex simultaneously with journal impact factor data. Triggers on…

Web and X search via FlagshipRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity / Xquik. Use when the user wants to search the…

从指定论文、研究记录或已有幻灯片创建和修订护理文献汇报、开题、答辩及组会PPT；也处理图片或PDF到可编辑幻灯片的重建。默认交付标准pptx，保留已确认模板、范围和科学含义，并检查实际渲染与编辑性。

Pesquisar e preparar slides de aulas e palestras técnicas em PT-BR, com fontes verificáveis, sequência didática, contexto e um conceito por slide. Preserva o catálogo aprovado e a rastreabilidade de…

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。

Use quando precisar de pesquisa multi-persona com síntese protegida por evidências.

Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis,…

analyze a professor from google scholar, publication lists, personal websites, lab pages, and field-specific bibliographic databases (e.g., DBLP, PubMed, SSRN, PhilPapers, MathSciNet, arXiv, Scopus)…

When the user needs bulk SERP data, local pack data at scale, keyword volumes for hundreds of terms at once, Google Maps business data programmatically, or is building custom local SEO…

Set up a new content studio for a person. Copies the plugin template, adapts it to the person's voice, themes, and content types through interactive discovery. Use when asked to create a content…

Suede AI Answer Engine Optimization Skills. Use when asked to "improve our AI citations" or optimize for ChatGPT/Perplexity: crawler policy, entity consistency, citation-ready pages, off-site evidence…

Refresh stale content via web verification, source logging, and citation-backed updates.

Research target venue requirements and writing style for CS/AI/ML papers. Produces venue-brief.md with submission requirements and detailed writing style analysis. Use when: researching target…

Plan, conduct, and analyze UX research using proven methodologies. Use when planning user research, writing interview scripts, creating test plans, recruiting participants, analyzing qualitative data,…

Draft or revise prose a person will read (documentation, README text, ADR and spec bodies, runbooks, pull-request descriptions, commit messages, delivery summaries, briefs and reports for the owner)…

Research products and analyze markets. Use for product opportunity discovery, competitive landscape analysis, supplier evaluation, or market entry assessment.

Orchestrate end-to-end academic manuscript preparation following APA 7th edition. Use for writing papers, drafting sections, or academic writing support.

验证经济金融研究想法的新颖性。在JF、JFE、RFS、JME等顶刊及arXiv中搜索近三年文献，输出结构化新颖性报告和定位策略。

Mine online communities and analyze existing assets to understand what customers actually think, say, and struggle with. Use when the user wants to do customer research, ICP research,…

学习助手技能：根据用户已有知识水平，定制化学习新技术/新概念。 用类比和对比已知领域来解释新概念，而不是从零开始教。 触发词：帮我学一下、这是什么、怎么理解、学习、入门、教我。 触发场景：接触新技术栈、学习新概念、理解不熟悉的架构模式、准备技术分享。 即使用户没有说"学习"，只要意图是"理解一个自己不熟悉的概念/技术"，都应触发此技能。

Decide what a papercut reel should be. Picks the topic, one familiar format, the audience level, the comment-keyword funnel and caption, studies competitor reels, and runs the post-publish autopsy.…

面向 MotionSurf 本地 tex_source markdown 资产的批量论文分析入口。当用户希望批量分析多篇本地论文、处理所有尚未生成研究笔记的 markdown 论文、按标题/目录名/匹配条件筛选一批论文生成 ReadNote/ResearchPaper/* 下的 note.md 与 meta.json 时，优先使用这个 skill。它只基于本地 markdown，不走 direct…

Route and control Chinese IPO sponsor-execution work by lifecycle stage. Use when a task spans several files or skills, the IPO stage is unclear, or the user asks for an end-to-end plan covering…

Write comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on topics like segmentation, detection,…

Compiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims,…

Research Agent for [Channel]'s YouTube production pipeline. Acts as a Frontier Scout — gathering structured intelligence on a video topic so the Script Agent (or [Creator]) can immediately build…

Verify concrete factual claims in a chapter draft — numbers, statistics, benchmarks, quotes, version numbers, release years, API signatures, superlatives, citations (tech-book), and…

初五的消费者证据PR转化Skill。把已有消费者研究、市场分析、竞品分析、VOC或产品测试证据转换为消费品PR判断、风险边界、可公开主张和业务行动。需要设计或补充研究时按需交consumer-research；需要文案、舆情、文章、新闻稿或预案产物时交对应专项Skill，仅有未决取舍时进入judgment-hub。