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.
-
nealcaren Bundle Lit SearchBuild systematic literature databases for sociology research using OpenAlex API. Guides you through search, screening, snowballing, annotation, and synthesis with structured user interaction at each stage.
-
nealcaren Bundle Text AnalystComputational text analysis for sociology research using R or Python. Guides you through topic models, sentiment analysis, classification, and embeddings with systematic validation. Supports both traditional (LDA, STM) and neural (BERT, BERTopic) methods.
-
nealcaren Bundle Stata AnalystStata statistical analysis for publication-ready sociology research. Guides you through phased workflows for DiD, IV, matching, panel methods, and more. Use when doing quantitative analysis in Stata for academic papers.
-
nealcaren Bundle Interview AnalystPragmatic qualitative analysis for interview data in sociology research. Guides you through systematic coding, interpretation, and synthesis with quality checkpoints. Supports theory-informed (Track A) or data-first (Track B) approaches.
-
morgs32 Skill Update ArchitectureSync wiki/architecture workflow docs with source code: sequence diagrams, their Annotated workflow steps, Trigger steps, other mermaid diagrams, and nested citation bullets. Use when the user asks to update architecture docs, workflow docs, mermaid in wiki/architecture, annotated-step citations, or says update-architecture.
-
karstenheld3 Bundle Deep ResearchApply when conducting deep research on technologies, APIs, frameworks, people, companies, organizations, networks, or other topics requiring systematic investigation
-
christopheryeo Bundle Daily CalendarsUnified Google Calendar skill with 3 sub-commands: search (find and summarize events by date, title, attendee, email, or domain), available (check a requested meeting slot against working hours, lunch, calendar conflicts, 30-minute buffers, and the one physical meeting per day rule), and meeting (return or validate the standard 60-minute online Google Meet profile). Use for calendar searches, daily or weekly agendas, meeting lookup, attendee history, availability checks, scheduling constraints, or typical-meeting checks.
-
letta-ai Bundle Browser UseControl a real browser to navigate pages, click, type, fill forms, inspect rendered UI, take screenshots, or record video. Load only when the user asks to open or automate a browser, interact with or test rendered page UI, scrape a site that needs browser execution, or capture a browser screenshot or video. Do not load for backend logs, traces, API or stream events, source-code inspection, or plain HTTP or web research that does not require a browser.
-
mckinsey Skill Issue CreationStructured workflow for drafting NEW GitHub issues with codebase research, duplicate detection, and testing approach. Always asks clarifying questions and shows the draft for approval before creating. For searching, listing, viewing, or updating existing issues, use the "issues" skill instead.
-
cellinlab Bundle Benchmark FilterBenchmark filtering for Chinese creator, OPC, and one-person-business work. Use when Codex needs to judge whether a person, creator, or business is actually worth studying; separate business signal from vanity signal; decide what layer is worth copying; and recommend whether to stop at a shortlist or hand the target to $opc-case-research for deeper study.
-
yrzhe Skill Deep ResearchDeep research skill for systematic exploration. Auto-triggered for research, analysis, investigation tasks. Ensures data accuracy and research depth.
-
hsiangjenli Bundle Ics ManagerManage local or remote ICS calendar sources to inspect upcoming meetings, summarize work hours, and add, update, or delete calendar events when users need a quick operational view of their schedule.
-
clickhouse-clickhouse Bundle Perf ComparisonEvaluate ClickHouse performance test results from existing CI/dashboard data or local perf.py runs. Use to check PR performance changes, run local performance tests, compare with history, assess flakiness, inspect coverage/PR relevance, and summarize whether a result is actionable.
-
gaurangrshah Bundle CurateOn-demand knowledge base curation - normalize tags, find duplicates, manage topics, promote memories
-
slgoodrich Bundle Synthesis FrameworksResearch synthesis frameworks including affinity mapping, thematic analysis, and insight generation. Use when synthesizing interview data, identifying patterns across research, extracting actionable insights, or building personas from findings. Trigger on: 'synthesize my research', 'what themes emerged from interviews', 'affinity mapping', 'turn research into insights', 'build a persona from this data'.
-
luw2007 Bundle Favorites CuratorBuild and maintain a local favorites catalog from installed repositories, apps, skills, extensions, and hooks. Use when the user asks to create, refresh, curate, scan, or summarize a favorites collection, software inventory, skill inventory, or daily digest of useful local resources.
-
novusaevum Bundle ResearchMulti-source comprehensive research using perplexity-researcher, claude-researcher, and gemini-researcher agents. Three modes - Quick (3 agents), Standard (9 agents), Extensive (24 agents with be-creative skill). USE WHEN user says 'do research', 'quick research', 'extensive research', 'find information about', 'investigate', 'analyze trends', 'current events', or any research-related request.
-
aimskr Bundle Learning Research학습 리서치, 학습 자료, 공부 자료, 학습, 공부, 스터디, 개념 정리, 이해 - 특정 주제를 깊이 이해하기 위한 학습 자료를 수집·정리한다. 병렬 전문가 서브에이전트로 개념, 원리, 실습, 심화 자료를 수집하고 이해도별로 체계화된 학습 노트를 생성한다. Obsidian vault에 자동 저장. 의사결정용 자료 조사는 research 스킬을, 시장조사는 market-research 스킬을 사용할 것.
-
flowing-abyss Skill DiscourseAdvisory assistant for building discourse graphs — structured argumentation (questions, claims, evidence, synthesis) within Obsidian hierarchy notes. Searches vault for relevant notes, suggests node types, validates structure. Does NOT auto-generate content. INVOKE when user wants structured research argumentation. Triggers: "discourse graph", "discourse node", "discourse", "structured argumentation", "research graph", "дискурс граф", "граф аргументации", "структурированная аргументация".
-
flowing-abyss Bundle System NotesCreate structural system notes: meta-notes (thematic hubs), problems (research questions), and hierarchies (aggregators). INVOKE when user wants to create any structural knowledge note. Triggers: "create meta-note", "create problem", "create hierarchy", "system note", "structural note", "мета-заметка", "создай мету", "проблема", "иерархия", "структурная заметка", "узел иерархии". NEVER creates categories — human-only.
-
heshamfs Bundle Ontology ExplorerParse, navigate, and query materials science ontology structures — browse class hierarchies, inspect individual classes and their properties, look up object and data property definitions with domain/range, search for ontology terms by keyword, and parse or summarize raw OWL/XML files. Currently supports CMSO and ASMO; the broader OCDO ecosystem (CDCO, PODO, PLDO, LDO) is planned. Use when exploring what classes or properties an ontology provides, finding the right CMSO term for a crystal structure or simulation concept, understanding parent-child class relationships, or onboarding to an unfamiliar materials ontology, even if the user only says "what ontology terms describe my FCC copper simulation" or "show me the CMSO class hierarchy."
-
heshamfs Bundle Post ProcessingExtract, analyze, and summarize simulation output data — pull spatial fields at specific timesteps, compute time-series trends and detect steady state, extract line profiles through the domain, generate statistical summaries and distributions, calculate derived quantities (gradients, fluxes, volume fractions, interface area), compare results against analytical solutions or experimental data, and produce automated analysis reports. Use when interpreting finished simulation results, checking mass or energy conservation, comparing two runs or meshes, extracting interface profiles from phase-field output, or preparing publication-quality analysis, even if the user only says "what do my results look like" or "did my simulation reach steady state."
-
alienfast Skill Dependency UpdaterRuns dependency updates end to end: parallel per-package research scaled to semver, applies the whole set at once, then fixes what the quality gate actually reports. Files a Linear issue to track the run, then asks up front whether to work in an isolated worktree and whether to finish by merge or PR, shipping through /finish and removing its own worktree when done. Invoked when users request package updates, dependency updates, version bumps, or mention 'ncu' or npm-check-updates.
-
prulloac Bundle Semver ChangelogAutomate the creation and updating of a CHANGELOG.md file based on Semantic Versioning (SemVer) and "Keep a Changelog" principles. Use this skill when you need to summarize changes between the current HEAD and the latest git tag, or when initializing a new changelog for a project.
-
wulaosiji Bundle Investor Research调研风险投资机构、天使投资人和融资资金来源。生成结构化的投资人调研报告,包含机构画像、投资 thesis、投资组合、联系策略和热介绍路径。 Use when: "投资人调研", "找VC", "research investors", "VC list", "funding sources", "investor database", "天使投资人", "venture capital", "融资对象", "投资人画像". 帮助创业者识别、评估并接触适合其融资轮次的投资人。Cross-references: investor-due-diligence, pitch-deck-creator, deck-web-converter. Built by UniqueClub 🌐 https://uniqueclub.ai
-
wulaosiji Skill Competitor TrackerMonitor competitor news, product launches, pricing changes, and strategic moves. Generates structured competitor intelligence reports with recent updates, sentiment analysis, and strategic implications for startup founders. Use when: "竞品追踪", "监控竞争对手", "competitor tracker", "竞争分析", "竞品动态", "competitive intelligence", "对手新闻", "market monitoring", "竞品情报", "competitor analysis". Cross-references: market-intel-brief, social-intelligence, market-research-extractor, china-content-research. Built by UniqueClub 🌐 https://uniqueclub.ai
-
wulaosiji Skill Market Intel BriefGenerate daily/weekly AI and startup industry intelligence briefings for founders. Curates AI industry updates, funding news, and competitive intelligence into actionable founder briefings. Use when: "市场情报", "行业简报", "market intelligence", "startup news", "AI日报", "industry briefing", "market brief", "行业趋势", "tech news digest", "市场分析简报". Cross-references: competitor-tracker, social-intelligence, market-research-extractor, china-content-research. Built by UniqueClub 🌐 https://uniqueclub.ai
-
wulaosiji Skill Social IntelligenceMonitor Twitter/X for competitor activity, industry trends, and market signals. Real-time social media monitoring for startup competitive intelligence, influencer identification, and trend tracking. Use when: "社交监控", "竞品动态", "Twitter监控", "社交情报", "social listening", "competitor monitoring", "social media intelligence", "Twitter分析", "品牌监控", "趋势追踪". Cross-references: competitor-tracker, market-intel-brief, market-research-extractor, china-content-research. Built by UniqueClub 🌐 https://uniqueclub.ai
-
wulaosiji Skill China Content ResearchResearch and analyze WeChat articles and Chinese social content for market intelligence. Specialized tool for China market content research, competitive intelligence, and consumer sentiment analysis across WeChat and Chinese platforms. Use when: "微信公众号研究", "微信文章分析", "中国市场调研", "微信内容抓取", "WeChat research", "China market research", "微信竞品分析", "公众号监控", "China content analysis", "中国市场情报". Cross-references: competitor-tracker, market-intel-brief, social-intelligence, market-research-extractor. Built by UniqueClub 🌐 https://uniqueclub.ai
-
wulaosiji Bundle Investor Due Diligence在见投资人之前对其进行评级。米其林式3星评级体系,基于六维度1-4分评分。适用于中美投资人。帮助创业者判断投资人值不值得见、靠不靠谱。 Use when: "投资人背调", "查VC", "rate this VC", "投资人评级", "值不值得见", "靠不靠谱", "investor evaluation", "VC background check", "基金怎么样". 投资人对你做尽调,你也应该在见他们之前先查清楚他们是谁。Cross-references: investor-research, pitch-deck-creator. Built by UniqueClub 🌐 https://uniqueclub.ai
-
wulaosiji Skill Unique Club Founder KitNavigation layer for the complete 24-skill AI founder toolkit by UniqueClub across foundation, fundraising, market intelligence, content creation, and operations. Includes pitch planning and generation, investor research, competitive intelligence, content workflows, meeting minutes, and daily briefs. Install this kit to bootstrap your startup with proven AI workflows. Use when: 「AI创业工具包」「founder toolkit」「startup skills」「uniqueclub」「创业者技能」「AI founder tools」「创业必备」「工具包导航」「founder workflow」「创业效率套件」. Cross-references: pitch-deck-creator, investor-research, competitor-tracker, market-intel-brief, founder-content-writer, content-multiplier, meeting-minutes-ai, founder-daily-brief. Built by UniqueClub 🌐 https://uniqueclub.ai
-
wulaosiji Skill Market Research ExtractorExtract and analyze content from multiple platforms for market research and competitive intelligence. Supports 小宇宙, 抖音, 小红书, B站, 微信, Twitter/X for founder-driven market research and content strategy analysis. Use when: "内容抓取", "竞品分析", "市场调研", "内容提取", "competitive research", "market research", "content extraction", "竞品监控", "行业调研", "research automation". Cross-references: competitor-tracker, social-intelligence, market-intel-brief, china-content-research. Built by UniqueClub 🌐 https://uniqueclub.ai
-
gannonh-kata-skills Bundle Kata Research PhaseResearch how to implement a phase standalone, investigating implementation approaches before planning, or re-researching after planning is complete. Triggers include "research phase", "investigate phase", "how to implement", "research implementation", and "phase research".
-
doodledood Skill Research WebDeep web research with parallel investigators, multi-wave exploration, and structured synthesis. Spawns multiple web-researcher agents to explore different facets of a topic simultaneously, launches additional waves when gaps are identified, then synthesizes findings. Use when asked to research, investigate, compare options, find best practices, or gather comprehensive information from the web.\n\nThoroughness: quick for factual lookups | medium for focused topics | thorough for comparisons/evaluations (waves continue while critical gaps remain) | very-thorough for comprehensive research (waves continue until satisficed). Auto-selects if not specified.
-
tsinghua-fib-lab Bundle Agentsociety HypothesisUse when defining or revising research hypotheses, experiment groups, or comparison structure after literature review.
-
tsinghua-fib-lab Bundle Agentsociety Literature SearchUse when academic literature needs to be gathered or refreshed for a research topic, especially at the beginning of a project.
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 research, learning-research, lit-search. 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.