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.
-
clearailhc Bundle Scientific Critical Thinking【调研·证据质量】评估研报、论文、环评、工艺手册等证据的可信度与偏倚。适用:交叉验证 web_search 结果、评级券商研报与学术来源、识别混杂与夸大结论。不适用:撰写正式同行评审(无此需求);系统文献综述流程(用 literature-review)。
-
ficilcom Bundle Company ResearchResearch a specific company before applying or interviewing by gathering facts from primary and official sources, recording the source and date behind every claim, and keeping anonymous or unverifiable material clearly separated from confirmed fact. Use when a user asks what a company actually does, how it makes money, what its published conditions are, whether a posting matches the company's own disclosures, or what to verify before an interview; do not use to predict hiring outcomes, to repeat review-site content as fact, or to bulk-crawl sites that prohibit automated access.
-
kroshank Skill Academic Paper WriterStructure theses, essays, and academic papers with introduction, theoretical framework, development, conclusions, and bibliography. Use when the user asks for a TFG, essay, research paper outline, or academic write-up.
-
kroshank Skill Deep Research SynthesizerTurn large amounts of information into structured insights and actionable conclusions, filtering noise. Use when the user pastes many sources, notes, or threads and wants a synthesis, not a recap.
-
yogiraja Skill Read WikiQuery the knowledge base before doing work. Use when the user asks "what do we know about X", "get context before I update this", "have we seen this pattern", "what connects A and B", or any question that accumulated project or cross-project knowledge could answer. Also invoke proactively when starting a non-trivial code task in a project that has a wiki: read the relevant pages first before touching files. Strictly read-only: never writes to any wiki file. Triggers on /read-wiki or phrases like "check the wiki", "get context", "what's in the wiki about", "have we documented".
-
l3rowniecakez Skill Redmine LogtimeSummarize the work just done in this session and record it on a Redmine issue as a Note and/or a time entry (Logtime). Use when user says "/redmine-logtime", "สรุปงาน", "ลง logtime", or wants to log time/notes for the Redmine issue currently being worked on.
-
l3rowniecakez Skill Redmine Summary WeeklySummarize Redmine spent time (logtime) over a week or custom date range, grouped by Project, for reporting in a status meeting with a supervisor. Use when user says "/redmine-summary-weekly", "สรุปงาน week นี้", "สรุปงานประจำสัปดาห์", or wants a project-grouped work summary to present in a meeting. Read-only — never posts/writes anything to Redmine.
-
yogiraja Skill Explain Yogi Like He Is 5Run a deep Socratic learning session to make sure the user truly understands a piece of code, a PR, a system design, a concept, or a decision. Use this whenever the user says "explain this to me", "walk me through", "teach me", "help me understand", "I want to learn X", "break this down", "quiz me on", or shares a file or link and wants to be taught rather than just told. Also trigger when the user wants to understand a past decision, trace through logic, or prepare to explain something to someone else. Do not just summarize, run the full incremental mastery loop.
-
arozumenko Bundle Deep ResearchUse when the user asks to 'research trends', 'analyze a topic', 'fact-check this', 'verify claims', 'what's the state of X', or hands you a document to vet. A disk-first, checkpointed research workflow with three modes — trend research, topic analysis, and fact-checking.
-
swyxio Bundle Research Grounded WritingResearch, draft, or revise substantial nonfiction whose claims need traceable support, including articles, essays, technical explainers, recommendation memos, reports, profiles, and source-backed publishing copy. Use for the evidence and attribution layer; pair with swyx-writing for voice and with a format-specific skill when one exists. Do not trigger for a simple factual answer or research with no writing deliverable.
-
swyxio Bundle Podcast Publishing AssistantTranscribe long-form audio, YouTube videos, podcasts, interviews, or panels; summarize them; extract chapter markers; and draft publishing assets like titles, YouTube descriptions, show notes, and tweet/X copy. Use when a user shares a YouTube link or audio/video file and asks for transcription, diarization, summaries with timestamps, chapter markers, show notes, titles, descriptions, promo copy, or social posts. Especially use for Whisper-based workflows, source-audio-first podcast processing, and any request to turn a recorded conversation into publishable assets.
-
swyxio Bundle Person Profile WritingResearch, draft, or revise source-grounded biographies and person-centered speaker, founder, or expert profiles. Use when identity resolution, career chronology, roles, projects, public ideas, or attribution are central to the deliverable. Pair with research-grounded-writing for evidence and swyx-writing for prose.
-
venilkukadiya52 Bundle Career Signal OsResearch-driven professional intelligence and content OS. Personalize once from a CV/profile and optional projects, then use /CSpost to research current problems in the user's field, choose the strongest evidence-backed topic and format, create a humanized LinkedIn-ready post or learning asset, and keep free/manual fallbacks when connectors are unavailable. Also supports /CSstart, /CSbrief, /CSprofile, /CScareer, /CSproject, /CSlearn, /CStest, /CSaudit, /CShistory, /CSsettings, /CSconnectors, /CSideas, /CSseries, /CSvisual, /CSpoll, /CSreply, and /CSrepost.
-
venilkukadiya52 Skill Career Signal DoctorRun a CareerSignal health check across profile state, local storage, research/image/code capabilities, connectors, fallbacks, and plugin package integrity. Use on /CSdoctor.
-
venilkukadiya52 Bundle Daily PostCreate today's best evidence-backed professional post after live research, topic scoring, originality checks, and format selection. Use on /CSpost, "what should I post today?", "good morning where is my post?", or equivalent requests.
-
venilkukadiya52 Skill Career SignalRoute CareerSignal OS workflows for professional onboarding, daily LinkedIn-ready posts, research briefs, profile audits, career gaps, build-before-post projects, learning, post audits, performance learning, and optional connector setup. Use when the user says /CSstart, /CSpost, /CSbrief, /CSprofile, /CScareer, /CSproject, /CSlearn, /CStest, /CSaudit, /CShistory, /CSsettings, /CSconnectors, or naturally asks CareerSignal to create or manage professional content.
-
ivy00johns Skill Find UnknownsConvert your unknown-unknowns to known — cheaply, before they get expensive to fix. Owns two moves: a blindspot pass (research an unfamiliar domain and learn the questions you don't yet know to ask) and a comprehension quiz (after a big change, explain the diff and verify you understand it before merging). Routes the rest of the unknowns lifecycle to the owning skills. Use when you're in unfamiliar territory, can't articulate what "good" looks like, feel like you're missing something, or want to be sure you understand what got built. Trigger on "find my unknown unknowns", "blindspot pass", "what am I missing", "I don't know this domain/codebase", "teach me my blind spots", "map my unknowns", "quiz me on this change", "do I actually understand this diff", "only merge if I understand it", "comprehension check". Sibling to grill-me — that interviews you on decisions you already hold opinions about; this surfaces the ones you don't.
-
sapientinc Bundle Literature Scout 2Literature Scout
-
sapientinc Bundle Literature Scout 3Literature Scout
-
venilkukadiya52 Skill Research BriefProduce a concise current professional research brief without forcing a social post. Use on /CSbrief or requests like "what changed in my field this week?".
-
venilkukadiya52 Skill Performance LearningLearn from approved/published posts and outcomes, update voice/topic preferences, and summarize what content creates useful professional outcomes. Use on /CShistory, performance reviews, or when metrics/edits are supplied.
-
sapientinc Bundle Literature Scout 4Disabled offline literature scout
-
sapientinc Bundle Literature Scout 5ML Literature Scout
-
ivy00johns Bundle Plan BuilderTransform research documents, Compass artifacts, PRDs, and conversational goals into structured project plans the orchestrator can execute. Use when the user has source material plus a build request, says "make a plan" / "plan this out", or @-mentions files alongside a build ask. Also trigger when orchestrator would be the next step but no plan exists yet. Produces the plan — orchestrator consumes it.
-
agentik-os Skill LenseResearch scout for an already-refined idea — finds 2-3 high-quality external references (design precedents or knowledge sources) and shows how each both supports AND challenges the idea. Activate when the user types /lense, or asks to find references / precedents / prior art / evidence / examples / sources / "qui a déjà fait ça" / "des références" / "des précédents" / "trouve des preuves" / "validate this idea against reality" for an idea that is already clear enough to act on. Use AFTER /mono has clarified the idea — not for brainstorming or clarifying a vague idea (that's /mono), and not for next-step recommendations (handled elsewhere).
-
agentik-os Skill Ads AudienceBuilds 5-7 forensic audience personas from a business URL — demographics, psychographics, pain points, buying triggers, platform-specific targeting (Meta/Google/LinkedIn/TikTok/Pinterest), persona scoring, negative audiences. Use when the user says "/ads audience <url>", "build personas", "buyer personas", "customer profiles", "who should I target", "targeting research", "audience research", or in French "construis les personas", "personas d'audience", "qui cibler", "profils clients", "recherche d'audience". Also runs as a subagent of /ads strategy.
-
jhamidun Bundle JtbdAJTBD и Next Move Theory: работы клиента, сегментация по работам, Forces/Switch Interview, ODI. Триггеры: «JTBD», «граф работ», «NMT». НЕ CustDev→user-research-synthesis.
-
jhamidun Bundle PerplexityPerplexity веб-поиск и research с источниками: дефолт pplx-max.py по подписке Max. Триггеры: «перплексити», «поищи в вебе с источниками».
-
jhamidun Skill Social IntelДосье на человека/компанию по соцсетям (Scraping API). Триггеры: «досье на», «кто этот человек». НЕ домены → osint-recon; компания по открытым источникам → account-research.
-
jhamidun Bundle Account ResearchДосье на компанию/человека: веб-поиск + CRM. Триггеры: «что за компания», «пробей контрагента». НЕ соцсети→social-intel; домен/IP→osint-recon.
-
jhamidun Bundle Citp Research RuCITP — карта «5 слоёв данных × 6 этапов воронки»: что собирать на этапе, откуда и чем. Триггеры: «где брать данные», «анализ глубинок». НЕ дизайн воронки → funnel-design-ru.
-
jhamidun Bundle Content ResearchResearch под контент-артефакт: источники, CRAAP, цитаты с пруфами. Триггеры: «найди источники», «проверь факты для статьи». НЕ лонгрид → /deep-research.
-
jhamidun Bundle User Research SynthesisСинтез исследований в инсайты: интервью, опросы → темы, персоны; CustDev: респонденты, карта эмпатии. Триггеры: «синтез интервью», «юзабилити».
-
jhamidun Skill Social Intel 2Досье на человека/компанию по соцсетям (Scraping API). Триггеры: «досье на», «кто этот человек». НЕ домены → osint-recon; компания по открытым источникам → account-research.
-
jhamidun Bundle Perplexity 2Perplexity веб-поиск и research с источниками: дефолт pplx-max.py по подписке Max. Триггеры: «перплексити», «поищи в вебе с источниками».
-
jhamidun Skill Meeting Analyzer 2Транскрипт встречи → протокол: решения, action items, риски; вход tl;dv/Plaud/Spark или аудио. Триггеры: «саммари звонка», «разбери транскрипт».
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 scientific-critical-thinking, company-research, academic-paper-writer. 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.