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.
-
wundercorp Skill Competitor News MonitorWatch named companies for material news; cited digests.
-
patsnap Skill Scout Tech LandscapeUse for only materials-related queries requiring technology landscape analysis. Focus on any materials relevant topics such as metallic alloys, polymers, ceramics, composites, and related processing technologies. Generate structured insights on material classes, supply chains, key organizations, and R&D trends based on patents, literature, and industrial data.
-
patsnap Skill Pharmaceuticals ExplorationUsed for answering drug-related questions. For early-stage drugs, search and summarize related patents, academic literature, database records, clinical trials, patents, and licensing transaction documents to answer questions. Activate when users explicitly mention specific drugs or when calling disease_investigation_skill or target_intelligence_skill for assistance - Specify output of a drug's characteristics or other records - Search for drugs related to a specific disease - Search for drugs targeting a specific target Typical queries - Please tell me about semaglutide targeting GLP-1R for diabetes treatment - What drug is remdesivir? - Drugs used to treat hepatitis B - ALN-F12
-
patsnap Bundle Microbiome Disease Research研究微生物组与疾病机制证据链并形成研究假设。适用于:梳理菌群、代谢物、宿主通路与疾病表型之间的证据链,区分相关性与因果性并形成可验证研究假设。
-
patsnap Skill Find Cross Industry Functional Solutions RdFind transferable technical solutions from other industries by reframing a concrete R&D problem as functions, effects, constraints, and contradictions. Use when an engineering or research team needs a cross-industry solution search, functional patent search strategy, solution shortlist, transferability assessment, or experiment plan.
-
patsnap Bundle Analyze Digital Construction Technologies RdAnalyze digital and intelligent construction technologies for bridges, tunnels, highways and adjacent infrastructure using patent, scientific, commercial and project evidence. Use for technology intelligence, competitive landscapes, patent landscapes, market-entry research, R&D planning or technical due diligence.
-
patsnap Bundle Trace Technology Evolution RdBuild an evidence-backed technology-evolution map for a product or technical system using system decomposition, SVOP functional abstraction, parallel patent and literature research, reviewed scoring, a versioned TRIZ-inspired route taxonomy, evolution-forest visualization, and scenario-based forecasts. Use for technology evolution, next-generation product forms, route maps, cross-domain analogies, candidate white spaces, horizon scenarios, gray-rhino pathways, or low-probability disruption signals.
-
patsnap Bundle Reactivate Underused Patents IpAssess underused patents and related intangible assets, cluster them into decision-ready packages, evaluate internal reuse and transaction options, research candidate counterparties, and create evidence-backed portfolio activation deliverables. Use for patent portfolio activation, maintenance review, outbound licensing or assignment screening, transaction-readiness review, internal R&D reuse, candidate buyer/licensee research, management reporting, or a 30/60/90-day activation plan.
-
zhaobenxiang5-coder Bundle Ancient Mystery VideoResearch and produce finished 60-90 second Chinese vertical videos about ancient mysteries, archaeology, lost civilizations, tombs, ruins, and disputed historical questions. Use when the user asks for 神秘历史视频、失落文明、古代遗迹悬疑、秦始皇陵未解之谜, or invokes $ancient-mystery-video. Do not use for 手绘故事 or 铅笔故事; those belong to handdraw-story-video.
-
cspoerer62 Skill Lead Sourcing At ScaleBuild a target-customer list from public and licensed sources — ICP definition, source selection, enrichment, verification, and scoring — without breaking any platform's ToS. Use before any outreach, and whenever "who should we sell to" is unanswered. Triggers on "find customers", "lead list", "prospects", "ICP", "target list", "who should we sell to", "scrape", "build a list", "find their email".
-
cspoerer62 Skill Public Web Research At ScalePublic Web Research at Scale
-
plyflai Bundle Deeptalk即时把零散想法、bullet points、草稿或问题深化为结构化需求,并从当前领域、参与者、流程和约束中补出高信号的 unknown unknowns、拆分项和待决定事项。Use this skill when the user wants a mentor-like second perspective for a product, service, policy, workflow, research question, education plan, creative project, personal decision, or software idea; it is domain-agnostic and can hand results to any downstream method.
-
yuji-tt Bundle Research DeepenerDevelop a promising research or engineering approach mechanistically before pivoting. Use when results are ambiguous, implementations fail, or local progress stalls; define predictions, ablations, and kill criteria without protecting a refuted idea.
-
ryangalea23 Bundle TranscribeTranscribe a local audio recording and save it as a meeting note. Takes an audio file (mp3/m4a/wav), uploads to OpenAI Whisper, then produces a structured summary written via the `notes` skill schema in `~/work/notes/`. Default behavior: if no file given, picks the most recent recording in `~/work/recordings/`. Pairs with the `record-call` script in this skill's `scripts/` folder (Windows only). Use when asked to "transcribe this", "transcribe the recording", "summarize the call", "/transcribe", "what did we say on that call", or after running `record-call stop`.
-
stofancy Bundle Searxng Web ResearchConduct multi-query web research with SearXNG-cli, source comparison, corroboration, and coverage reporting. Use for broad or high-confidence research questions that require several searches and reading multiple sources.
-
barnabys-drew Skill Youtube DigestTranscribe a YouTube video and surface the genuinely interesting parts with timestamped deep links. Use whenever the user shares a YouTube URL and wants to know what's in it, asks "what's interesting in this video", "summarize this video", "is this video worth watching", "what does this talk cover", "give me the highlights/key points/timestamps", wants a transcript of a YouTube video, or asks whether they should watch something before committing 45 minutes to it.
-
iabuelruzz Skill Feature DevDevelop a non-trivial feature through research, consultation, planning, delegated implementation, testing, and independent review
-
connoryoushaei Skill Chat HandoffGenerate a handoff document that lets a NEW Claude conversation resume this one with full context. Use whenever the user asks to "write a handoff," "summarize this chat so I can continue elsewhere," "prep a handoff doc," says they're starting a new chat and want continuity, mentions running low on context/hitting a limit, or asks for a "context dump" or "resume doc" for this conversation. Always trigger this instead of a generic summary when the stated purpose is continuing the work in a different conversation.
-
makanfar Bundle User Story GeneratorGenerate and validate user stories from various inputs including requirements, research, and feature descriptions. Apply INVEST criteria validation, create acceptance criteria, split large stories, and convert between story formats.
-
bonniegeng-max Bundle Video DigestCheck the pinned transcript dependency and optionally test YouTube connectivity, fetch public captions into a private per-user cache, retrieve excerpts by video ID, and turn captions or a supplied transcript into timestamped Quick, Deep, or Research notes.
-
agentcorp-inc Skill Customer 360Build a comprehensive customer profile from Intercom data, including conversation history, account context, and interaction timeline. Use when the user asks to "look up a customer", "customer profile", "customer 360", "tell me about this customer", "summarize a customer's history", or provides a customer email or company name and wants a full picture.
-
inprealpha Bundle Orchestrate WorkUse when a large task breaks cleanly into smaller, largely independent subtasks; work naturally divides into multiple parallel workstreams; substantial background research can advance the task while other work proceeds; or independent subagents would substantially improve review. Coordinate assignments, shared decisions, and combined results across engineering and knowledge work.
-
sumanjeet0012 Skill Dsa Deep DiveDeep research a DSA (Data Structures & Algorithms) topic and produce an exhaustive, structured study guide: must-know core concepts, complexity tables, visual diagrams, verified top internet resources, crucial problem-solving patterns, beginner & advanced pitfalls, a practice ladder, and next-step paths. Use when the user asks to "research X for DSA", "study guide for X", "deep dive into <topic>", "explain <algorithm> thoroughly", "how does <data structure> work", or asks what to learn after mastering a topic.
-
agentcorp-inc Skill Exploring Replay Vision ObservationsGuides agents through pulling a Replay Vision scanner's observations, reading the findings, and acting on them — summarizing patterns across sessions, drilling into individual recordings, and turning real, corroborated issues into PostHog tasks, insights, or an investigating-replay hand-off. TRIGGER when: user wants to pull/read/triage Replay Vision observations, asks "what has my scanner found", wants to act on or summarize scanner findings, turn observations into tasks/work, or points at a /replay-vision/<scanner-id> URL. DO NOT TRIGGER when: creating or sizing a scanner (use creating-replay-vision-scanners), running a one-off scan you don't then analyse, or authoring a signals scout.
-
sodam-ai Skill Persona Research Analyst15년+ 리서치·분석 전문가 관점. 시장·경쟁사·사례·기술·문헌·동향을 조사하고 여러 자료를 비교·종합해 근거 있는 결론과 보고서로 정리해야 할 때 활성화한다. 단순 조회나 한 건의 사실 확인에는 활성화하지 않는다.
-
ccai40359-wq Bundle Web Research FanoutWeb research orchestration protocol — split lanes (sub-question × source type) → dispatch researchers in parallel → structured claims table (assertion + source URL + date + primary/secondary) → independent arbitration only for conflicts. MUST USE for web research, multi-source verification, vendor/market research, cross-checking — triggers include "research this", "verify across sources", "全网查", "多源核对". Not for single-fact lookups or reading local documents (use dual-read in this pack).
-
jakeschincariol Bundle Yt ViralFind what is actually working in the user's niche on YouTube and rank it by how far each video beat its own channel, then name the formula. Use for "what's working right now", "find viral videos in my niche", "why did this blow up", competitor research, or a swipe file.
-
waseemnasir2k26 Skill ResearchUse to research a business niche/market before writing a landing page — target buyer, top pains and fears, objections, and what every competitor claims (so we can position against them). Outputs ./out/research.md. Called as step 1 of the launch chain.
-
icerain-cmd Skill Reviewing ManuscriptUse when a humanities manuscript needs an evidence-based, whole-document review of research question, scope, concepts, argument, interpretation, citations, structure, and contribution.
-
icerain-cmd Skill Scoping Argument BoundaryUse when a research question is promising but its corpus, period, comparison, concepts, or claim size remain too broad or unstable for a defensible humanities argument.
-
icerain-cmd Skill Planning Humanities ArgumentUse when a research question, scope boundary, and source base exist but the manuscript still needs a defensible sequence of claims, warrants, evidence, objections, and section functions.
-
icerain-cmd Skill Formulating Research QuestionUse when a humanities researcher has a broad topic, intuition, corpus, or problem but does not yet have a precise, contestable, and researchable question.
-
icerain-cmd Skill Conducting Literature DialogueUse when a humanities researcher needs to transform verified sources into a structured scholarly conversation rather than a chronological list of summaries.
-
johnnylin2121 Skill Obsidian Vault Sync自动将文件同步到Obsidian知识库,包括复制文件、创建/更新wiki entities和topics。Use when user says "添加到知识库", "同步到Obsidian", "更新wiki", "把文件放到vault里", "归档", "添加到vault", or asks to organize files into the knowledge base.
-
yjhqwer Skill Delegate Or DieDelegation discipline for coding agents. Hand multi-file exploration, broad searches, and long sequential reads to disposable subagents instead of flooding the main thread with tool calls. Includes the self-contained brief format (question, boundaries, output contract) and status-first reporting. Use whenever a task would require reading more than ~3 files, running multi-query research, or touching unfamiliar territory.
-
ono-sendai-labs Skill Interactive DesignThis workflow guides you through the process of transforming a rough idea into a detailed design document. It systematically refines your idea through interactive requirements clarification, research, and iterative design. Use when the user has a rough idea, feature concept, or project proposal that needs to be developed into a comprehensive design before implementation — whether for a greenfield project or adding features to an existing system.
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 competitor-news-monitor, scout-tech-landscape, pharmaceuticals-exploration. 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.