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.
-
handsomeboy990 Bundle Market ResearchMarket Research
-
minimax-ai Bundle Paper Search当需要真正执行文献数据库 API 检索时加载:构建检索式(布尔组合、字段限定)、 调用 OpenAlex / Crossref / arXiv 接口、遵守请求礼仪(限速、UA、指数退避)、 把返回解析为统一 PaperDocument。通常由 literature-search 调用,不直接面向用户。 同义场景:检索执行、API 查询、文献接口调用、query 构建、检索脚本运行、 接口限速与重试、检索结果解析。
12.9k -
minimax-ai Bundle Cn Literature当用户需要检索或整理中文文献(CNKI 知网、万方、维普、超星)、把中文数据库 导出的题录文件解析成统一 PaperDocument、或把中文文献与英文检索结果合并去重 时使用。同义场景:中文文献检索、知网导出题录解析、万方检索、Refworks/EndNote 格式转换、"帮我把这份 CNKI 导出的 txt 整理成文献表""中文核心期刊上关于 X 有哪些研究"。
12.9k -
minimax-ai Bundle Web ResearchUse when the user asks to research a topic on the web, gather information from multiple sources, do a literature scan, summarize recent developments on a subject, or look up articles. Triggers on requests like "调研 X", "找几篇关于 Y 的文章", "research Z", "汇总 Q 的资料", "look up the latest on W". Do NOT use for single-URL fetches with no research framing (use the defuddle skill directly), local file operations, code edits, or tasks that do not need web data.
12.9k -
minimax-ai Skill Citation Verify当用户需要核验参考文献真实性、检查 BibTeX 条目是否有误、审查论文引用是否可靠、 排查 bibliography 中的错误条目、验证 DOI 与题录是否对得上、发现参考文献张冠李戴、 做投稿前引用体检或审稿引用抽查时使用。同义场景:参考文献核验、引用核查、 文献真伪鉴别、bib 文件检查、参考文献纠错、引用元数据比对、 "帮我看看这些参考文献有没有问题""这个 DOI 对得上吗""有没有编造的引用"。
12.9k -
minimax-ai Skill Legal Research当用户提出法律检索需求——"查一下某法规/某条还有效吗/有没有相关案例/最高法的 司法解释原文/这个监管规定哪儿来的/帮我做个法律调研/美国法上怎么规定的/某问题 法律上怎么说"时使用。本技能是检索路由器:先把需求分类(法律法规/司法解释/ 案例/监管规则/美国法对照),再按凭证配置选择数据源执行,所有结果强制带来源 标注,未覆盖的源显式声明缺口。不直接给出法律意见,检索结论服务于后续分析。
12.9k -
minimax-ai Skill Literature Search当用户需要检索学术文献、按主题找论文、收集综述素材、查询某篇文献的元数据或 DOI、追踪某方向最新进展或预印本、做开题文献调研时使用。同义场景:文献检索、 论文搜索、查文献、找论文、文献调研、资料收集、题录补全、 "帮我找关于 X 的论文""这个主题有哪些代表性工作""查一下这篇文献的 DOI 和出处"。
12.9k -
minimax-ai Skill Literature Survey当用户需要对已检索到的文献集合做整体分析、写文献调研报告、梳理某领域的 研究概况 / 共识 / 争议 / 空白、提取文献证据为综述写作做准备时使用。 同义场景:文献综述分析、领域调研、研究现状梳理、证据提取、文献精读笔记、 "帮我分析这批论文讲了什么""这个领域的研究现状如何""这些文献有什么共识和分歧"。
12.9k -
minimax-ai Skill Research Lifecycle当用户提出研究主题、想开始一项新研究、问"接下来该做什么"、或要求继续上次的研究流程时使用。本技能是科研工作台的元路由器:把一个研究主题拆解为 question(问题界定)→ literature(文献调研)→ hypothesis(假设形成)→ experiment(实验/计算)→ analysis(数据分析)→ writing(写作成稿)六个阶段,逐阶段调用相应插件的 skill 执行,每个阶段结束经 stage-gate 门禁审批后进入下一阶段。同义触发场景:开始研究、开题、走流程、研究流程、lifecycle、继续上次的研究、阶段推进、研究项目管理、六阶段、从选题到成稿。
12.9k -
minimax-ai Skill Research Workspace当用户开始新研究项目、说"初始化工作区""建一下项目目录""检查目录结构""workspace""整理一下我的研究文件夹",或任何 skill 发现当前目录不符合工作区约定时使用。本技能定义并维护科研工作区的标准目录结构(data/figures/notebooks/papers/reports/reviews/scripts/output/.openscience)、产物路径契约(output/<skill>/<slug>/latest/ 指向最近运行,历史运行按时间戳归档)与原始数据只读原则,并提供项目初始化与结构体检两套清单。同义触发场景:新建课题目录、项目结构检查、目录规范、产物放哪里、原始数据能不能改。
12.9k -
minimax-ai Skill Minimax Code TrajectoryInspect or visualize privacy-aware timelines for local MiniMax Code sessions. Use when the user asks to show, draw, open, review, or diagnose a task trajectory, summarize tool or token activity, inspect compaction or failure events, or compare recent session metadata without opening raw ledger files.
12.9k -
wike-chi Bundle Deep ResearchUse when 需要对某个主题做深度多源调研(方法论追踪+来源评估+迭代深入)时。路由:深度调研走此技能(内置方法论追踪+来源评估+迭代深入),不要直接用 web_search 做一次性搜索就结束
-
wike-chi Bundle Market ResearchUse when 需要做市场研究、市场规模分析、竞品分析或开发新市场时。路由:市场研究走此技能(内置六维度分析框架+竞品格局),不要直接用 web_search 搜几条链接就交差
-
wike-chi Bundle Company ResearchUse when 用户需要做海外B2B企业背景调查、查公司信息、调研客户时。路由:背调前必须先用 lead_query 查CRM是否已有该线索(避免重复调研),再用此技能做外部信息搜集。
-
wike-chi Bundle In Depth Research深度研究技能的红龙定制包装入口。检测到 HONGLONG-OVERRIDE.md 时优先使用定制内容。
-
wike-chi Skill Five Step Bg Check外贸客户5招背调法 — 输入海外企业名称,按5步递进式搜集公开信息并输出结构化背调报告。从平台信息、海关数据、社媒决策人、谷歌地图到官网分析层层递进。当用户提到'5招背调'、'市场背调'、'背调法'、'five step'时使用。适合快速判断客户是否值得开发,区别于 company-research 的深度背调。
-
cbrock84 Skill Service DeskRuns the IT service desk — intake, triage, prioritization, escalation, knowledge, and the metrics that improve service rather than distort it. Use this to set up or fix a service desk, design ticket priority and escalation, reduce repeat contacts, structure a knowledge base, or work out why a desk hitting its targets still frustrates everyone.
-
marucie Skill Tavily SearchTavily API ile güvenli web arama ve URL içerik çıkarma yap. Use when: hızlı web araştırması, kaynaklı sonuç toplama, belirli URL'lerden metin çekme ve özetleme gerektiğinde.
-
marucie Skill Ljg Paper FlowPaper workflow: read papers + cast cards in one go. Takes one or more arxiv links, paper URLs, PDFs, or paper names. For each paper, runs ljg-paper (generates org analysis) then ljg-card -l (generates long reading card PNG). Use when user says '论文流', 'paper flow', '读论文并做卡片', '论文卡片', or provides multiple papers wanting both analysis and cards.
-
marucie Skill Web Multi SearchSearch the web using multiple search engines simultaneously (Bing, Yahoo, Startpage, Aol, Ask) via async-search-scraper, iterating through result pages.
-
marucie Skill Multi Search EngineUse when searching across both Chinese and international sources simultaneously (17 engines: 8 CN + 9 Global). Trigger: 'search Baidu and Google', 'Chinese + English sources', cross-region market research, privacy-first search, WolframAlpha knowledge queries. NOT for: single-engine queries (use ask-search), real-time finance data, or when speed is critical (parallel requests are slower).
-
iblai Skill Iblai Vibe Ops UpgradeUpgrade the @iblai/iblai-js SDK and refresh every ibl.ai skill (both families — iblai-vibe-* and iblai-api-*) to the latest release, then summarize what changed. Use when asked to "upgrade iblai", "get the latest SDK", "update ibl.ai", "refresh the skills", when the installed skills are older than two weeks, or when a skill misbehaves in a way a newer release may fix.
-
photonics-dhl Bundle Research Paper WritingEnd-to-end academic paper writing skill covering proposal, structure, writing, formatting, and quality review. Targets Nature, Science, IEEE, NeurIPS, ICML, ICLR, AAAI, ACL, COLM. Emphasizes narrative-driven writing, citation discipline, and iterative refinement.
-
etanhey Skill Drive UsageBrain Drive filing discipline: where artifacts go and how to name them. Triggers: Drive/Brain Drive upload, folders, prompts/results, audits, plans, transcripts, dashboards, docs.local artifacts. NOT for Gemini Drive/web research; >100KB use archive.
-
etanhey Bundle Gemini ResearchNotebookLM/Gemini research: sources, Deep Research, queries, artifacts. Triggers: Gemini, synthesis.
-
etanhey Bundle ResearchDeep web research orchestrator. Routes research tasks to the best backend — internal subagents, CLI agents (Gemini/Cursor), or the researcher subagent. Use when asked to research, investigate, compare, find alternatives, or deep-dive into any topic. Covers web research, company research, code pattern research, and pre-implementation research.
-
etanhey Bundle Research LifecycleRefresh local research context and the Drive grounding corpus. Triggers: stale context, R-number.
-
etanhey Skill Google Drive ArchiveArchive >100KB research/media to Brain Drive. Triggers: Drive upload, archive this, post-digest archival.
-
saeed-vayghan Bundle UX ResearcherExpert UX researcher specializing in user insights, usability testing, and data-driven design decisions. Masters qualitative and quantitative research methods to uncover user needs, validate designs, and drive product improvements through actionable insights.
-
arbazkhan971 Skill ResearchPrior art and context gathering. Explorer subagent, docs/ecosystem scan, existing patterns, relevant dependencies, writes research.md for the think skill.
-
aliyun Skill Fund Deep Research对单只基金进行全面尽调分析,按基金类型(股票型/债券型/混合型/指数型)自动选择分析路径, 输出业绩、风险、持仓、基金经理能力四维诊断报告。 当用户提到分析基金、基金怎么样、能不能买、基金诊断、基金尽调、这个基金经理靠谱吗时触发。 不用于多只基金的组合持仓分析(由portfolio-health-check处理)。
-
aliyun Skill Institutional Research Outline机构调研大纲生成技能。当用户需要为上市公司调研准备提纲、生成调研问题清单、准备机构调研材料时使用,包括"生成 XX 公司调研大纲"、"准备去 XX 公司调研"、"调研 XX 公司前需要问什么问题"、"帮我写一份调研提纲"等表述。本技能针对上市公司首次调研场景,生成标准版深度(1-2 小时准备)的结构化调研大纲,包含公司基本面分析、同业对比、历史调研问题回顾和约 10 个核心调研问题,覆盖战略、业务、财务、风险等维度。**报告生成后直接在对话中显示完整内容,无需发送文件**。
-
aliyun Skill Portfolio Health Check对客户全部持仓进行穿透式体检,从资产配置、基金相关性、回测表现、风险暴露四个维度 输出诊断报告和可视化图表。 当用户提到持仓分析、组合诊断、持仓体检、配置检视、帮我看看持仓时触发。 不用于单只基金分析(由fund-deep-research处理), 不用于专项风险排查(由portfolio-risk-radar处理)。
-
aliyun Skill Competitor Product Compare对比同类基金产品,从收益、风险、费率、流动性、基金经理能力五个维度 生成对比报告,帮助客户经理回应"别家产品更好"的异议。 当用户提到跟XX比怎么样、竞品对比、同类比较、为什么选我们、 两只基金比较时触发。 不用于单只基金分析(由fund-deep-research处理)。
-
aliyun Skill Asset Allocation Optimizer基于客户风险偏好和当前持仓,结合市场环境和量化模型, 生成个性化资产配置方案并模拟预期收益分布。 当用户提到资产配置、配置优化、怎么调仓、投资方案设计、配置方案时触发。 不用于单只基金分析(由fund-deep-research处理), 不用于具体产品推荐(由smart-product-matching处理)。
-
nimadorostkar Skill Deep ResearchUse when researching a question that requires multiple sources. Covers question decomposition, source evaluation, tracking what is known versus assumed, and producing a synthesis with honest confidence levels.
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 market-research, paper-search, cn-literature. 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.