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.
-
waterhyacinthinnanhu Skill Topic SurveySurvey a research field interactively, exploring papers by topic and writing a structured literature review.
-
waterhyacinthinnanhu Bundle Idea RefineryIteratively refine a research idea through literature survey, validation, and branching exploration until convergence.
-
waterhyacinthinnanhu Bundle Experiment ReportWrite structured experiment reports for robot learning and AI research.
-
jay-523 Skill Deep ResearchMECE decompose a research question, run parallel Codex web-research agents via tmux, iteratively deepen via DAG, synthesize findings
-
jay-523 Skill Parallel ResearchDecompose a research question into MECE domains and run parallel Claude agents via tmux
-
ranioren Bundle Keep SummarizerSummarize Google Keep notes into a list of tasks. Use when the user asks "whats my tasks" or asks to summarize their Keep notes.
-
adnaanmhd Skill Comparative ResearchUse this skill whenever the user asks to evaluate, compare, or recommend between real-world options — devices, tools, vendors, services, platforms, or any category where the right choice depends on market data, specs, and target-user fit. Trigger on phrases like "recommend a...", "which X should I buy/use/choose", "compare these options", "find the best...", "top N choices for...", "compare these for me...", "comparative research for...", or any time the user needs a structured, evidence-backed selection decision. Use this skill even if the user's question seems quick or casual — e.g. "which phone should I get?" — because proper candidate selection requires a structured process to avoid bias. This skill is critical any time data availability might otherwise skew the recommendation toward well-documented options over better-fit options.
-
clemens865 Skill Idea ScoutDeep, autonomous domain decomposition and landscape research for any idea or problem statement. Takes a raw idea (from one sentence to a paragraph) and runs a 6-phase research process: decomposes the idea into problem space, target users, domain, adjacent domains, and assumed solution direction; performs exhaustive parallel web research on current state of the art, key players, recent momentum, technical foundations, and user sentiment; synthesizes gaps, blind spots, friction points, challenges, and opportunities; maps 3-5 distinct solution directions with feasibility and differentiation analysis; runs contrarian and timing checks including cross-domain analogies; and scores all findings by confidence level with full source attribution. Outputs a structured research dossier to /docs/idea-scout/. Use this skill whenever the user has a raw idea they want explored before building, wants to understand a problem landscape, needs domain research, or wants to validate whether an idea is worth pursuing. Triggers on:
-
usmanskillsmd Skill HactHistory-aware collaboration tuning for Codex projects. Use when asked to review past conversations/threads/sessions, summarize user preferences from project history, convert recurring patterns into gu
-
usmanskillsmd Skill Skill 72SKILL
-
usmanskillsmd Skill Meta Analysismeta analysis — rigorous statistical analysis methods and tools for academic and applied research.
-
usmanskillsmd Skill Skill 94SKILL
-
usmanskillsmd Skill X Research Skillx-research-skill
-
usmanskillsmd Skill Leaflet Web Mapsleaflet web maps — rigorous geospatial analysis methods and tools for academic and applied research.
-
usmanskillsmd Skill Rna Seq Analysisrna seq analysis — rigorous bioinformatics methods and tools for academic and applied research.
-
usmanskillsmd Skill Openclaw Mckinsey Researchmckinsey-research
-
usmanskillsmd Skill Academic Searchacademic-search
-
usmanskillsmd Skill Core Researchercore-researcher
-
usmanskillsmd Skill Sw Autoresearchsw-autoresearch
-
usmanskillsmd Skill Text Mining Nlptext mining nlp — rigorous data mining methods and tools for academic and applied research.
-
usmanskillsmd Skill Expanso Text Summarizeexpanso-text-summarize
-
usmanskillsmd Skill Customer Research Dvcustomer-research-dv
-
usmanskillsmd Skill Amazon Listing Optimizeramazon-listing-optimizer
-
usmanskillsmd Skill Academic Press Release Writing学术新闻稿撰写专业工具。包含规范的五段式写作结构、全流程工作步骤、常见问题解决方案和效率提升技巧。**当以下情况时使用此 Skill**:(1) 需要撰写学术机构、科研团队的新闻通稿/宣传稿;(2) 需要将学术论文、科研成果转化为面向公众的科普性新闻稿;(3) 用户提到"学术新闻稿"、"科研宣传稿"、"论文新闻稿"、"成果宣传"等关键词;(4) 需要规范的新闻稿写作模板和流程指导。
-
arturseo-geo Bundle ResearchResearch Skill
-
arturseo-geo Skill Grounded ResearchGrounded research mode that reduces hallucinations using Anthropic's three recommended techniques: admitting uncertainty, extracting direct quotes before analysis, and citing sources for every claim. Use this skill when the user asks for grounded research, fact-checked analysis, document-based Q&A, verified claims, source-verified research, "based on this document" tasks, citation-backed answers, or any task where factual accuracy matters more than creative exploration. Do NOT trigger for creative writing, brainstorming, code generation, casual conversation, or tasks where unconstrained output is desired. This mode makes responses shorter and more conservative but dramatically more trustworthy. The user must explicitly invoke this skill or the task must clearly require factual grounding — never auto-trigger on general research tasks (use the research skill instead).
-
yipintangzsp Bundle Summarize Paysummarize-pay - 实用工具(SkillPay 收费版)
-
yipintangzsp Bundle AI Market ResearchAI 市场调研分析 | 竞品情报收集 | 行业趋势预测 | 消费者洞察
-
yipintangzsp Bundle Citation Generator引用格式生成 | 论文引用 | 参考文献 | 多格式支持 | 学术必备神器
-
yipintangzsp Bundle Keyword Researchkeyword-research - 实用工具(SkillPay 收费版)
-
yipintangzsp Bundle Youtube Summarize Payyoutube-summarize-pay - 实用工具(SkillPay 收费版)
-
mosaxiv Skill SummarizeSummarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
-
xvary-research Bundle Xvary Stock ResearchUse when building thesis-driven equity analysis in Claude Code from public SEC EDGAR data and market snapshots — workflows /analyze, /score, /compare with bundled Python tools.
-
cihebi2 Bundle Bioinforw Data PlottingRecommend and adapt scientific plotting templates from a local Bioinforw or NGplot catalog for research data visualization. Use when Codex needs to choose a chart type from `catalog_enriched.jsonl`, refresh `embedding_input.jsonl`, return top-k templates with Python/R code paths, map user columns to template-required columns, or turn a research plotting request into an executable plotting starting point.
-
alubiama Bundle Scientific Method SelectorRoute scientific and evidence-oriented work to the right research method or staged evidence workflow. Use when the user wants scientific backing, literature review, claim checking, study appraisal, or evidence synthesis, and the main challenge is choosing the right research path rather than jumping straight into conclusions.
-
daianepepes-lab Skill ResearcherResearch any topic thoroughly using web search and multiple sources. Use when asked to research, investigate, find information, or gather data on any subject.
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 topic_survey, idea_refinery, experiment_report. 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.