Research AI Skills

Use when assembling the AEA Data and Code Availability deposit for an AER, AER:Insights, or AEJ acceptance, writing the README, or auditing a replication package before the AEA Data Editor review.…

Business model classification, business model analysis, structural analysis of how a company makes money, product offering decomposition, distribution channel analysis, customer segment analysis,…

毛泽东思维框架：以《毛泽东选集》五卷为核心，提炼毛泽东分析问题、制定战略、组织行动的认知操作系统。 核心来源：《矛盾论》《实践论》《论持久战》《中国社会各阶级的分析》《星星之火可以燎原》《论联合政府》《关于正确处理人民内部矛盾的问题》等。 核心模型：7个。决策启发式：10条。 触发词：「毛泽东」「毛选」「教员」「用毛泽东的方式分析」「从毛选的角度」「教员怎么看」…

Prove that a knowledge base actually works before trusting it — after building or adopting docs, a knowledge graph, or a wiki, verify it can orient a fresh agent and resist false premises. Use at the…

Evaluate page content for usefulness, E-E-A-T, readability, thinness, and AI citation readiness, plus last-mile draft cleanup (AI-typical phrasing and invisible Unicode watermark characters). Use for…

根据目标期刊要求，对论文进行投稿前全面检查，涵盖格式、引用、图表、数据可用性等所有投稿必需项。

Use when looking up journal impact factors (JCR IF), checking a journal's impact factor by name, comparing IF across journals, or answering questions about "影响因子" / "impact factor" / "IF". Triggers on…

CRO (Richard Feynman)｜需要研究问题设计、一手证据获取与核验、竞品或市场情报扫描、多源证据综合与不确定性说明时调用。 不适用：需要财务、法律、产品或营销的最终结论、纯执行性的内容与投放工作、需要登录账号或联系第三方，或问题已有明确实验可直接验证。

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries.…

This skill should be used when the user wants to read, fetch, extract, or analyze the content of a web page from a URL. Use when the user provides a URL to access documentation, articles, blog posts,…

Explain repeated competitive outcomes - why deals are won or lost against a competitor or across a period - from buyer and deal evidence rather than rep folklore, with the cohort defined, buyer-stated…

News briefing + verification workflow. Use when the user asks for news, headlines, daily briefing, “today's news”, “latest updates”, breaking news, or requests specific current numbers/events that…

Load for research tasks, architectural investigations, and vendor, library, or technology comparisons.

Web of Science 全流程技能：主题/作者/标题/DOI/高级检索（内部 API，含 SID 回退）、论文详情解析、结果页解析（含离线快照模式）、翻页、DOM 结构参考。

法条引用核验与纠偏，用于检查草稿、问答、备忘或合同审查记录里已经写出来的法条引用是否准确、一致、可追溯。Use when：用户已经有一段文本，想确认其中法规名称、条号或引用表达是否可靠。NOT for：主题检索法规、案例检索、案号识别、以及未形成引用文本前的纯资料探索。要求只依据当次核验返回给出“命中 / 不命中 / 需复核”结论，不得把未核验内容写成已确认依据。

Route writing and editing work to the smallest relevant focused skill. Use when a request involves prompts, general prose, AI-pattern removal, academic voice, research abstracts, cadence, semantic…

Read and extend the user's own Zotero 7 library through the local desktop app — search papers, list collections and tags, pull PDF full text for summarising, add references by DOI/PMID, and export…

Runs a sourced KYC / AML research screen on a company: registration, officers, beneficial owners, sanctions, PEPs and adverse media, with namesakes excluded and a risk rating, using the Nimble…

Internal link analysis AND generation. Analyzes orphan pages, link equity, anchor text. Also generates link suggestions for new content. Use when user says "internal linking", "orphan pages", "link…

Design process methodology: NNG's six phases, Double Diamond, Google Design Sprint, IDEO, Lean UX, and the bridge from AI-assisted building to evidence-based UX. Use when framing how the work should…

Runs a pre-submission review of a technical paper across five dimensions: macro logic, writing details, English grammar, LaTeX formatting, and figure quality. Uses a reviewer-style severity taxonomy…

When the user wants to capture SERP evidence, search result snapshots, competitor URLs, or SERP features for specific keywords without doing SEO analysis.

5-level repair escalation when quality gates fail. Surgical → Section-rewrite → Stage-rewrite → Full-regen → From-scratch. Hard cap 4 rounds total. Use when quality.json reports overall_passed=false…

Use this skill for "review this paper", "review this manuscript", "peer review", "review my paper", "critique this manuscript", "review this submission", "give me feedback on my paper", "check my…

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

Compose, revise, or audit research proposals, opening reports, and research plans from supporting evidence. Use for 研究计划、开题报告、科研项目申请书. Invoked as researchwrite for compatibility; use nature-writing…

Create a Product Requirements Document using a comprehensive 8-section template covering problem, objectives, segments, value propositions, solution, and release planning. Use when writing a PRD,…

Detects AI-generated writing four ways — a heuristic audit against a catalog of known AI patterns, deterministic statistical signals (n-gram entropy, burstiness, repetition, stylometry — features…

Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation formats

Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says…

AI Berkshire skill: 组合管理：从"研究公司"到"管理组合". Source: skills/portfolio-review.md.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time…

Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF",…

Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research…

Trigger: SDD research, external evidence, source-backed research. Investigate optional questions using available authorized sources.

Generate professional primary market / venture capital industry research reports, including sector deep-dives, investment memos, and market analysis. Produces detailed PDF reports covering TMT,…

Divergent research ideation — generate many candidate directions, then adversarially filter to the strongest

Create grounded paid-media creative concepts, copy angles, refresh hypotheses, and measurable test briefs across advertising platforms. Use for ad copy, creative briefs, UGC concepts, headlines,…

CEO coordinator that dispatches research, strategy, finance, and writer specialists via A2A and synthesizes their findings into a GO/NO-GO investment briefing. Use for multi-agent advisory workflows.

[omh] Prepared PDBQT inputs: run bounded standalone Vina docking with real poses, scores and replay provenance; never infer efficacy or safety. Use when the user says: molecular-docking,…

Use when writing or revising academic papers, especially Chinese journal manuscripts, that need natural prose, de-AI-ification, Markdown formatting, or quality checks

Advanced web search using Tavily API for current information retrieval

Build and maintain company research profiles on AlphaGBM — auto-generated from fundamentals, PE/PB Band history, financial red flags, and event radar. Each profile is one user+ticker record that the…

Literature-backed English technical-prose writing rules (agent-style, 21 rules). Its lane is FORMAL technical prose (papers, design docs, proposals, READMEs, commit messages). Use ONLY when the user…

雷达Skill（AI Radar）——零API、零Key、零服务器的中文AI资讯查询，读 AI News Radar 公开静态 JSON 出中文简报。 触发条件：用户想知道"今天 AI 圈有什么"、"AI…

Search current news for a topic, company, competitor, or hook and return dated, attributed articles. Uses the newsjack CLI and Medialyst REST API when available, tries direct Medialyst MCP if the CLI…

Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims,…

Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use…

Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use…

Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for…

Domain-specific statistical modeling guidance for cognitive science and neuroscience, encoding when and how to apply mixed models, correction methods, Bayesian approaches, and effect size reporting