Research & Search
Research agent skills teach AI agents to gather and synthesize information properly: literature reviews, competitive analysis, web research with citations, and structured summaries. Each SKILL.md encodes a method, not just a prompt, so results stay consistent across runs.
-
seaworld008 Bundle UX Researcher DesignerPlan and synthesize UX research, personas, journey maps, and usability studies when validating product needs or design decisions.
65 -
infometa Bundle Arxiv WatcherSearch and summarize papers from ArXiv. Use when the user asks for the latest research, specific topics on ArXiv, or a daily summary of AI papers.
228 -
infometa Bundle Note OrganizerJoplin — Note Manager — personal knowledge base. Personal productivity tool. Use when you need Joplin capabilities for personal organization, tracking, or management.
228 -
infometa Bundle Paper Quick ReaderAI 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么构造的、论文精读、 paper summary、summarize this paper、compare these papers、literature skim、extract methodology。 不做:论文检索、文献管理、论文翻译、扫描件 OCR、论文写作 / 降重。
228 -
infometa Bundle AI Research Radar定时任务:每日研究简报。漏掉重要论文和行业报告?每天帮你盯着,关键信息一条不漏 This skill should be used when the user asks about 定时任务:每日研究简报. Keywords: 每日简报, 研究简报.
228 -
infometa Skill Company Tearsheet快速生成公司一页纸概览(Tearsheet),涵盖业务描述、关键财务、估值、股东结构和近期催化。 触发词:公司速览、tearsheet、公司概况、一页纸、公司简介、company overview、快速了解、公司画像
228 -
infometa Bundle Earnings盈利分析技能,支持两种模式: - Preview 模式:业绩发布前的前瞻分析、情景假设、关键观测指标 - Analysis 模式:业绩发布后的深度解读、Beat/Miss 分析、估计修正 触发词:earnings analysis、earnings preview、业绩分析、业绩前瞻、财报分析、季报解读、pre-earnings、post-earnings、Q1/Q2/Q3/Q4 results
228 -
infometa Bundle Layer1 Fin DataUse when you need structured financial data such as prices, rankings, limit-up/limit-down screening, stock pattern counts, ETF/industry constituents, valuation metrics, macro time series, or financial indicators.
228 -
infometa Bundle Layer1 Fin GraphUse when you need industry/theme identity resolution, industry graph nodes/public factors, industry-chain graph overview/tree/node/map access, industry viewpoints, anomalies, crowding, or macro graph panels from the Fin Graph source namespace.
228 -
infometa Bundle Layer1 Same BoatUse for read-only Chinese investment research / 投研知识库 queries: 行业/板块/概念研究目录, 分析师资料, 研报观点, 市场要闻, 分析师解读, 行情异动归因, 行业观点, market news, analyst viewpoints, sector viewpoints.
228 -
infometa Bundle Layer1 Doc SearchUse when you need structured retrieval for news, company news, events, announcements, research reports, meeting minutes, morning briefings, timelines, or document details from the Doc Search source namespace.
228 -
infometa Skill Layer2 Stock Brief当用户明确提到某个具体股票或上市公司时——如'保隆科技最近怎么了''帮我快速看一下600519''茅台最近有什么重要信息'。整合行情、公告、新闻和研报。行业整体问题用 industry-brief,研报专项用 research-digest,公告专项用 announcement-brief。
228 -
infometa Bundle Case Research中国财税法律案例与法规检索助手。当用户需要检索税务相关判例、行政复议决定、税收法规政策、国家税务总局公告、各地税务实践案例,或需要查找类似税务争议案例时,应使用本 Skill。适用于税务争议应对、税务筹划合规性验证、法律研究等场景。
228 -
infometa Skill Contract Drafting EngineDraft contracts, build template libraries, and write supplementary agreements (scenarios C3/C4/C9). Use this skill after intake and research to deconstruct the deal structure and commercial logic, identify the contract type, choose a contract structure package, assemble locked general clauses with bespoke core clauses, and add risk annotations to non-standard/high-risk clauses — producing a complete contract text with clearly separated fixed legal clauses and fillable commercial variables.
228 -
infometa Bundle Contract Scenario RouterIdentify the user's true contract-work intent and route it to the correct scenario (C1-C9). Use this skill FIRST for every contract request to determine scenario type, core objective, binding output standard, whether interactive intake is required, output weight tier, and the next skill in the chain — before any drafting, review or research happens.
228 -
infometa Bundle Destination Research目的地调研 · 把"江西附近游玩"或"成都"这类输入,转成结构化的目的地候选清单(含特色/季节性/必玩/避雷)。完全调用 search-orchestrator 编排底座,不重复造检索逻辑。
228 -
infometa Skill Layer2 Industry Brief当用户询问某个具体行业的近况、景气、估值或政策影响时——如'白酒最近怎么看''动力煤行业发生了什么''半导体景气如何'。聚焦单一具体行业;跨多行业找方向时先收窄到具体行业、事件或研报证据;个股问题用 stock-brief。
228 -
infometa Bundle Outreach CommunicationThis skill should be used when the user is NOT a parent seeking counseling, but instead a researcher, journalist, editor, public speaker, policy maker, content creator, or training instructor who wants Ma Laoshi (马老师) to speak/write/present on family education topics for external audiences. It provides academic data, speech scaffolds, journalist Q&A, signature quotes, and citation norms for external communication scenarios such as academic conferences, media interviews, public WeChat articles, short-video scripts, policy briefings, and internal training.
228 -
infometa Skill Layer2 Evidence Ledger当用户需要把已取证的公开股市投研材料整理成证据台账、信源审计、证据强弱表或结论依据清单时使用。只整理和校验已有证据,不负责新增取数、认证、预测、账户诊断或生成新事实。
228 -
infometa Skill Layer2 Research Digest当用户明确询问研报内容或分析师/机构观点时——如'最近茅台有哪些研报''券商怎么看白酒''最近策略研究在关注什么'。主角是研究观点和报告共识,不是行情或新闻综述(那用 stock-brief 或 industry-brief)。
228 -
infometa Skill Layer2 Research Red Team当用户需要对公开股市投研结论做反方审查、证伪检查、风险透视、叙事漏洞排查或多空证据拆分时使用。只基于已取证材料进行批判性复核,不负责新增取数、预测、回测、账户诊断或交易建议。
228 -
infometa Skill Layer2 Announcement Brief当用户询问某条公告的内容或含义时——如'帮我看一下这条股权激励公告''腾亚精工最近公告说了什么''这条业绩预告主要说了什么'。必须先获取公告原文再展开分析,不是泛新闻或研报综述。
228 -
infometa Skill Layer2 Policy Event Brief当用户问具体政策事件、官方会议表态或监管动向时——如'这次降准对市场意味着什么''最近重要会议释放了什么信号''这个行业政策变化影响哪些方向'。侧重政府/监管发布的具体政策解读;宏观国际风险只在有明确公开事件证据时做有限背景说明。
228 -
infometa Bundle Layer2 Stock Narrative Valuation当用户已经点名某个具体股票或上市公司,并希望做深度个股叙事、估值隐含预期、股价为何涨跌、是否透支、历史主升浪复盘、商业模式/护城河或反方证伪时使用。基于公开资料、行情、财务指标、研报和产业空间假设,分析市场当前可能隐含了什么终局预期。仅做公开投研推演,不输出买卖、仓位、目标价或个人账户建议;最近新闻/公告快查仍用 layer2-stock-brief。
228 -
infometa Skill Layer2 Transmission Chain Builder当用户需要把公开事件、行业异动、政策或主题行情拆成事件到机制到产业链上下游的传导链路时使用。适用于 MLCC、新能源、AI 算力、半导体等行业/板块解释,不负责预测、回测、账户诊断或生成新事实。
228 -
infometa Skill Public Target Research根据 ParkBrief 使用公开搜索、公开网页或用户粘贴的公开材料发现候选企业并记录 QueryLedger。用于首次宽召回、补齐候选、指定链节/区域搜索或证据不足时扩展来源;只写发现账本,不做最终主体结论或排名。
228 -
infometa Skill MemoIRAC-scaffolded case analysis memo with research gaps flagged — the scaffold, not the analysis. Rule blocks are RESEARCH NEEDED, Application is STUDENT ANALYSIS prompts, Conclusion is blank. Use when a student needs to scaffold a case analysis memo, write up their analysis, or build an IRAC memo for a case.
228 -
infometa Skill Legal WritingStructural feedback on a legal writing draft (memo, brief, paper, exam essay) — organization, analysis depth, clarity, citation form. NEVER rewrites the draft. Use when the user says "feedback on my memo", "read my draft", or "critique my brief".
228 -
theheavenlyd3mon Bundle FlaresolverrUse the minimal FlareSolverr wrapper for a one-off health check or browser-backed GET/POST when ordinary retrieval is blocked by Cloudflare or DDoS-GUARD. Choose flaresolverr-cli instead for named session lifecycle, cookie-only returns, dry-run planning, or the full operational command surface.
28 -
theheavenlyd3mon Bundle PolymarketQuery Polymarket: markets, prices, orderbooks, history.
28 -
theheavenlyd3mon Bundle BrowserbaseUse when working with Browserbase or the browse CLI.
28 -
theheavenlyd3mon Bundle Flaresolverr CLIUse a small FlareSolverr JSON CLI for browser-backed GET and POST requests, readiness checks, and session lifecycle management when a site requires Cloudflare or DDoS-GUARD challenge handling.
28 -
theheavenlyd3mon Skill Reply ResearchResearch an X account or specific post before drafting a reply, then draft a value-add reply (not a pitch, not generic, not spam). The
28 -
theheavenlyd3mon Bundle Verification MethodologyVerify work against explicit criteria using direct, source-faithful evidence, reproducible checks, and clear verdicts. Use before declaring an artifact, implementation, or claim complete; do not use for exploratory research without pass/fail criteria.
28 -
theheavenlyd3mon Bundle Research MethodologyPlan, conduct, evaluate, and synthesize rigorous research. Use for journalistic, industry, or technical investigations that need credible evidence and a traceable method.
28 -
theheavenlyd3mon Bundle Open Source ResearchSystematically research, evaluate, and extract insights from open-source projects (GitHub repos, docs sites, community resources). Multi-tool deep-dive: README → subdirectories → external docs → synthesis.
28
Frequently asked questions
What are Research & Search agent skills?
Research agent skills teach AI agents to gather and synthesize information properly: literature reviews, competitive analysis, web research with citations, and structured summaries. Each SKILL.md encodes a method, not just a prompt, so results stay consistent across runs.
Which Research & Search skills are most installed?
Popular Research & Search skills on SkillMD right now include ux-researcher-designer, arxiv-watcher, note-organizer. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Research & Search skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.