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.
- richard0901 BundleSci Retrospective 09
Use when the project reaches 09-SCI数据来源与伦理豁免核查器 in the SCI original retrospective research workflow.
Audited 1 - richard0901 BundleSci Experiment 22 Title Abstract Keywords
Use when the project reaches 22-SCI实验标题摘要关键词撰写器 in the SCI original experimental research writing workflow. 为实验研究专属路线撰写标题、摘要和关键词。
Audited 1 - richard0901 BundleSci Retrospective 05
Use when the project reaches 05-SCI回顾性研究文献检索式生成器 in the SCI original retrospective research workflow.
Audited 1 - equinor SkillPaperlab Reference Dataset Curation
Curate reference datasets for PaperLab validation, including source tracing, unit normalization, uncertainty notes, license status, and citation mapping.
Audited 167 - howard-lynn-ye SkillVolatility Models
Fit and forecast volatility - GARCH, range-based realized variance, HAR-RV - without the two errors that silently move the answer: the units `arch` expects, and a range estimator used on bars that gap. TRIGGER - GARCH, GARCH(1,1), EGARCH, GJR-GARCH, arch_model, conditional_volatility, DataScaleWarning, "y is poorly scaled", rescale=True, res.scale, alpha + beta near 1, IGARCH, persistence; realized volatility, realized variance, Parkinson, Garman-Klass, Rogers-Satchell, Yang-Zhang, close-to-close, high-low volatility estimator; HAR-RV, Corsi; "my GARCH forecast says 1200% annualised vol", "which volatility estimator should I use", vol targeting input. SKIP for the arch package's API and its SPA/StepM/MCS bootstrap (lib-arch), for choosing a forecasting library (factor-and-timeseries-research), for discrete high-vol/low-vol state labels (regime-detection), for implied volatility (derivatives-pricing), and for turning a vol forecast into position size (portfolio-and-risk).
Audited 1 - howard-lynn-ye BundleTrend Following Models
Build a trend-following or time-series-momentum strategy the way the paper defines it, and measure the two look-aheads that flatter its backtest. TRIGGER - time series momentum, TSMOM, Moskowitz Ooi Pedersen, 12-month momentum, trend following, managed futures, CTA replication; Donchian channel, turtle rules, breakout system, 20-day high, moving average crossover, golden cross, 50/200 MA; volatility targeting, vol scaling, ex-ante volatility, 40% vol target, risk parity across futures, inverse-vol sizing, ATR sizing; "my trend backtest has a Sharpe of 3", "should I skip the most recent month", "do I trade the close or the next open". SKIP for computing the indicator itself and whether it repaints (signal-construction), for cross-sectional ranking of many names (factor-and-timeseries-research), for combining several alphas into one (alpha-combination-and-neutralization), for how much to bet given an edge (position-sizing-kelly), and for the engine that runs the loop (backtesting-engines).
Audited 1 - crawlora-org BundleTravel Hotel Research
Researches hotels, flights, attractions, short-term rentals, and live events via the Crawlora API — Booking.com, Expedia, Agoda, TripAdvisor, Trip.com, Airbnb, and Ticketmaster — returning clean JSON. Use when the user wants to search or compare hotel/stay prices and reviews, look up flight options, find attractions/things-to-do or concerts/events, or research an Airbnb host or listing.
Audited 1 - arcsin1 BundleRed Research Framework
丹朱教研以白底、中国红和明确连接关系表达教学与研究框架。它把复杂内容拆成可讲述的模块和路径,重点是逻辑推进而不是装饰。
Audited 2.5k - agentic-in SkillBlogwatcher
Monitor blog or website updates, compare publish dates, and summarize deltas rather than repeating unchanged content.
Audited 586 - peterbamuhigire BundleDemo Driven Design Process
Use when a design or feature must converge through repeated demo, feedback, dogfooding, selection, and decision capture. Do not use merely to choose one prototype's fidelity; route that artefact decision to wireframing-and-prototyping. through).
Audited 31 - peterbamuhigire BundleWireframing And Prototyping
Use when a flow or feature needs sketches, wireframes, wireflows, or a clickable/coded prototype and the fidelity must match the learning question. Do not use to run a multi-round convergence process or produce final visual design; route those to demo-driven process or UI craft.
Audited 31 - panaversity BundleKnowledge
Capture and structure institutional knowledge before it is lost. Activate for: institutional knowledge, knowledge capture, knowledge transfer, knowledge base article, knowledge management, preserve knowledge, what do they know, departing employee knowledge, exit knowledge, succession knowledge, tacit knowledge, undocumented knowledge, before they leave, knowledge interview, knowledge extraction, document what we know, knowledge at risk, knowledge map. NOT for: policy lookup or FAQ queries (use policy-lookup), onboarding plans (use onboarding), offboarding checklists (use offboard).
Audited 38 - cwinvestments SkillMemstack Product Feedback Analyzer
Use this skill when the user says 'analyze feedback', 'feedback analysis', 'what are customers asking for', or has support tickets, reviews, or survey data to categorize, score, and prioritize into actionable reports. Do NOT use for competitor analysis or market research.
Audited 433 - amazon-quick BundleLead Prospector
Researches and identifies ideal prospects for small business sales. Builds targeted lead lists with company intel, decision-maker contacts, and personalized talking points. Use when user says 'find me leads', 'build a prospect list', 'who should I sell to', 'research companies in [industry]', 'find decision makers', 'identify potential customers', or 'prospect list for [product/service]'.
Audited 50 - amazon-quick SkillContract Clause Extractor
Extracts, classifies, and risk-scores key clauses from contracts and legal agreements. Identifies standard vs non-standard terms, flags high-risk provisions (unlimited liability, broad indemnification, auto-renewal), and produces structured clause inventories with plain-language summaries. Use when asked to 'review this contract', 'extract key clauses', 'flag risky terms', 'contract risk assessment', 'what are the key provisions', or 'summarize this agreement'.
Audited 50 - amazon-quick SkillStandup Summarizer
Summarize daily standup notes into blockers, progress, and plans. Use when asked to 'summarize standup', 'process standup notes', or 'daily summary'.
Audited 50 - ai-driven-dev Bundle05 Spike
Produces an evidence-bounded spike for an uncertainty blocking estimation, feasibility, or design. Use when the user wants to frame, investigate, resume, or conclude one. Not for general research or implementation.
Audited 559 - lunartech-x BundleThesis Supervisor
Comprehensive thesis and dissertation supervision assistant. Supports dissertation structure guidance (proposal through defense), chapter-by-chapter writing support (introduction, literature review, methodology, results, discussion), supervision strategies, committee management, defense preparation, timeline planning, feedback integration, formatting requirements (APA 7, Chicago, university styles), viva voce preparation, and examiner expectations. Triggers on: thesis, dissertation, supervision, defense preparation, viva, proposal defense, thesis structure, thesis chapter, literature review chapter, methodology chapter, results chapter, discussion chapter, thesis timeline, committee, thesis formatting, dissertation proposal.
Audited 17 - zjunlp BundleResearch Lit
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
Audited 1.5k - synapseradio BundleCite
Generate APA-format citations from paper links. This skill should be used when the user asks to "cite a paper", "generate APA citations", "format references", or provides paper links (arXiv, DOI, conference URLs) for citation formatting.
Audited 2 - seemseam BundleArchi Full
Run or read full-project architecture analysis and summarize structural weaknesses, hotspots, and maintainability risks.
Audited 3.6k - codealive-ai BundleStructured Log
Write structured entries to daily memory log with facts, concepts, and files — use after any meaningful work, research, or decision
Audited 167 - codealive-ai BundleExa Company Research
Company research using Exa search. Finds company info, competitors, news, tweets, financials, LinkedIn profiles, builds company lists. Use when researching companies, doing competitor analysis, market research, or building company lists.
Audited 167 - dragoon0x SkillUser Psychology
Apply motivation, friction, and trust patterns to product decisions. Maps cognitive biases and behavioral triggers to specific UI and copy choices. Use when reviewing flows for drop-off points or when something feels right but doesn't convert.
Audited 13 - jaechang-hits SkillScientific Brainstorming
Structured ideation methods: SCAMPER, Six Thinking Hats, Morphological Analysis, TRIZ, Biomimicry, plus more. Decision framework for picking methods by challenge type (stuck, improving, systematic exploration, contradiction). Use when generating research ideas or exploring interdisciplinary connections.
Audited 389 - practice019 BundleProduct Design
产品设计探索:UX 研究、流程审计与评审、视觉构思、克隆现有产品界面、实现选定视觉目标、设计 QA、保存设计上下文。当用户要做产品设计、体验研究、设计评审时使用。 Use this skill when Product Design is explicitly invoked or the main task is product design exploration, UX research, flow auditing or critique, visual ideation, cloning a live product surface, implementing a selected visual target, design QA, saved design context, or sharing a prototype.
Audited - cdeistopened BundleMeta Ads Creative
Create high-converting Meta (Facebook/Instagram) ad creative using the 6 Elements framework, proven ad formats, and research-driven copywriting. Optimized for lo-fi, native-feeling ads that don't look like ads.
Audited 29 - rongxinzy BundleResearch Advisor
协助科研人员进行选题构思、项目规划、问题排查与科研决策,输出具体的研究方案、风险评估矩阵或决策树等文档。当用户提出新研究想法、分享当前项目遇到的卡点、咨询战略性问题,或使用“选题”、“开题”、“项目构思”、“研究方向”、“研究路径”、“风险评估”、“问题排查”、“卡住了”、“下一步怎么走”等关键词时触发。
Audited 162 - fdiblen BundleRseng Numerical Accuracy
Covers floating-point correctness in research code: why 0.1 + 0.2 != 0.3, choosing absolute vs relative tolerances in tests, accumulation error and safe summation, precision choices (float32 vs float64), catastrophic cancellation, NaN and infinity handling, and cross-platform or cross-library result drift. Use PROACTIVELY when floating-point comparisons fail mysteriously, when writing numerical tests or choosing tolerances, when results differ across machines, compilers, BLAS builds or library versions, or when precision or numerical stability questions arise in analysis or simulation code.
Audited 27 - frankxai BundleDomain Slug Sub System Slug
The <SUB-SYSTEM> skill inside the <DOMAIN> Domain Sub-Stack. Loads when any /<SLUG>-* command fires or when <SUB-SYSTEM> keywords are detected. Carries the research-grounded protocol this sub-system runs.
Audited 47 - carlheath SkillAphorism
Aphorism database for citable lines. Distinguishes between user aphorisms (own, go to TELOS WISDOM.md) and external aphorisms (from other authors, go to a separate aphorism database). Supports search, categorisation, citation format, and retrieval for chronicles/scripts. [WHAT] Quote database where each aphorism has: text, author, source, domain tag, captured-on date. User-own aphorisms go to `~/.claude/memory/USER/TELOS/WISDOM.md`, external ones to `~/.claude/memory/KNOWLEDGE/Sources/aphorisms.md`. [WHEN] Use when: aphorism, quote, citable, "save this line", quotable, wisdom-quote, "who said X", find a quote about Y, "add to the quote database". Auto-activates after writing/editing if a line stands out. [LANGUAGE] Configurable. [EXPERTISE] Aphorism curation, quote attribution, citation format, retrieval.
Audited 9 - carlheath SkillThinking Science
Hypothesis-driven experimentation loop. Formulates testable hypotheses, designs experiments, measures results, and iterates. [WHAT] Scientific method applied to any kind of question: formulate hypotheses, identify what would falsify them, design tests, analyse results, update understanding. Works for tech, policy, strategy, and research. [WHEN] Use when: hypothesis, experiment, test the assumption, scientific method, "is it actually true that..." [EXPERTISE] Hypothesis formulation, experiment design, falsification, iterative learning
Audited 9 - robsonrung SkillSummarize
Create a concise continuity summary from the active session. Use when the user asks to summarize current work, prepare a handoff, or compact session context. Do not use to summarize an unrelated document or to store a handoff.
Audited 2 - timlai666 BundleInvestment Research Prompts
This skill MUST be used when the user needs stock screening, portfolio risk review, dividend portfolio design, pre-earnings analysis, industry competition analysis, DCF valuation, technical analysis, or stock trend/anomaly detection. MUST trigger on requests like 選股, 投資組合風險, 股息策略, 財報前瞻, DCF 估值, 技術面分析, 產業競爭研究, 趨勢識別, or investment research prompts.
Audited 1 - k-dense-ai BundleZhenan Bao
Applies the reasoning, materials design principles, and research philosophy of Zhenan Bao (chemical engineer, Stanford University, flexible electronics). Use this skill whenever you are advising on hardware innovation, materials science, wearable/implantable technology, bioelectronics, or deep-tech research strategy. Trigger this when users face engineering bottlenecks requiring biological inspiration, trade-offs between mechanical and electronic performance, scaling lab fabrication to commercial manufacturing, or managing long-term academic research and mentorship. Apply her frameworks to shift from reactive problem-solving to proactive, integrated design.
Audited 57.3k - k-dense-ai BundleTerrie E Moffitt
Applies the developmental psychopathology and longitudinal research frameworks of Terrie E. Moffitt (psychologist, Duke University). Use this skill whenever reasoning about human development, criminology, juvenile delinquency, self-control, mental health trajectories, or biological aging. Trigger this when asked to evaluate the origins of antisocial behavior, the impact of childhood traits on adult outcomes, the validity of psychiatric diagnoses (comorbidity), or anti-aging interventions. Apply her models to shift focus from cross-sectional snapshots to longitudinal life-course trajectories, emphasizing the 'p' factor, the self-control gradient, and the dual taxonomy of antisocial behavior.
Audited 57.3k
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 travel-hotel-research, cite, sci-retrospective-09. 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 get-skill add <owner>/<name>, or copy the file into your agent's skills directory.