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.
- sipengxie2024 BundlePolish
Polish prose in three passes: strip AI-writing tells, apply Strunk's rules for clarity, then hold every research claim to its evidence. Two modes: edit in place, or diff-first where the original is untouched until the user approves each change. Use when the user asks to 润色 / 改写 / 精修 / 打磨 a draft, or says "polish", "refine", "tighten", or "improve". Preserves meaning, numbers, citations, and [NEEDS-EVIDENCE] markers; never smooths an unsupported claim into a supported-sounding one.
Audited 2 - rimagination SkillLiterature Search
Use when a ScanSci user wants to search, compare, or answer questions from a bound local knowledge library with traceable evidence.
Audited 148 - invergent-ai SkillArbor Coordinator
The Arbor research-coordinator protocol: the OBSERVE -> IDEATE -> SELECT -> DISPATCH -> DECIDE cycle over a durable Idea Tree. Preloaded automatically on /auto-research sessions. The coordinator never edits code or runs commands — executors do that in isolated worktrees; the coordinator steers the tree with idea_tree / dispatch_experiments / merge_experiment.
Audited 28 - fedec65 SkillSwiss Legal Translation
Swiss legal translator — translates Swiss legal texts (contracts, submissions, statutes, opinions) between DE, FR, IT, and EN with correct terminology and register. Trigger when: a user asks to translate a Swiss legal document or term, or a document must be prepared in a different national language. Uses fedlex-sparql for statute text verification. Delegates citation conversion to swiss-citation-formats. Do NOT trigger for: citation formatting without translation (use swiss-citation-formats), document drafting (use swiss-legal-drafting), or general non-legal translation.
Audited 46 - fairy123456789 BundleOne Week Founder Mode
Compress an overloaded week of startup, research, job-search, creator, or side-project work into one main bet, up to two microbets, essential maintenance, and an explicit kill list. Use when the user has too many parallel ideas, keeps adding tasks, needs a founder-like weekly operating rhythm, or wants every week to end with real external proof instead of a long completed-task list.
Audited 108 - vellum-ai BundleGeo Writing
Generates GEO/AEO-optimized articles designed to get AI engines (ChatGPT, Perplexity, Claude, Gemini) to cite your brand. Handles research, writing, and file output. Suggests listicle or head-to-head as starting formats if the user is unsure.
Audited 1.5k - yelban SkillLjg Travel
Deep travel research workflow for museums and ancient architecture. Input a city name, auto-generates structured knowledge document (org-mode) + portable reference cards (PNG). Covers historical background, museum highlights, archaeological significance, and architectural heritage. Use when user says '旅行研究', '博物館功課', '古建功課', 'travel research', '出發前功課', or provides a city name with intent to do deep cultural travel preparation.
Audited 0 - anotb BundleThought Leadership
Develop evidence-backed points of view, white papers, case studies, industry briefs, and research reports for a consulting audience. Use to turn research or permitted engagement experience into a useful, defensible argument.
Audited 62 - eturkes BundleVenue Templates
Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
Audited 0 - ecnu-icalk BundleTrace Citations
Trace the citation neighborhood around one focal paper into foundations, descendants, bridges, weak edges, and optional second-hop links
Audited 613 - howells SkillFiction
This skill should be used when the user asks to "write a chapter", "write prose", "continue the story", "develop a character", "review my chapter", "critique my manuscript", "write a synopsis", "summarize my story", "plan my novel", "outline my book", "check for consistency", or mentions fiction writing, novels, short stories, scenes, or narrative craft.
Audited 25 - mariourquia SkillNew Vault
Create a new Obsidian vault. Modes -- project (for a git project), topic (research a topic with web seeding), preset (from a vault template), existing (connect to an existing vault).
Audited 51 - volcengine BundleCompute Molecular Features
对已标准化化合物确定性计算受控二维描述符、Morgan/RDKit/MACCS 指纹和数据集质量画像。用于准备分子特征、生成指纹,或检查特征缺失、常数、异常和分布。
Audited 151 - skills-il BundleIsraeli Cv Builder
Not legal advice. Generate a ready-to-send Israeli CV (korot chayim / קורות חיים) in Hebrew, English, or both: one page by default, reverse chronological, a military or national service section, dugri (direct) language, metrics-driven bullets, plus an optional Israeli cover letter (michtav mukdam / מכתב מקדים). Use when writing a CV for Israel, building a resume for AllJobs, Drushim, JobMaster, JobNet or LinkedIn Israel, preparing a bilingual tech CV, or drafting an Israeli-style cover letter. Automatically omits age, marital status and religion, grounds on which the Equal Employment Opportunities Law 1988 prohibits discrimination, and omits the photo as market convention. Do NOT use for job market research (use israeli-job-market), tech interview prep (use israeli-tech-interview-prep), salary negotiation (use israeli-tech-salary-negotiator), LinkedIn strategy (use israeli-linkedin-strategy), employer-side screening (use israeli-hr-recruitment-automator), or employment contract review.
Audited 38 - skills-il BundleHebrew Legal Research
Assist with Israeli legal research including legislation lookup, case law concepts, Hebrew legal terminology, and legal document preparation guidance. Use when user asks about Israeli law, "chok", "mishpat", "bagatz", court procedures, employment law, contract law, real estate law, or needs help with Hebrew legal terms. Covers civil, commercial, employment, and administrative law. Do NOT use for providing formal legal advice, always recommend consulting a licensed Israeli attorney (orech din). Do NOT use for non-Israeli legal systems.
Audited 38 - codealive-ai BundleExa Native Base
Foundation for the Exa skill collection — how to call Exa (search, contents, answer, similar) from a local script with just an EXA_API_KEY, how to write good semantic queries, and how to orchestrate subagents for deep research. Read this first; the use-case skills (company, people, papers, code, news, finance, personal sites, X) build on it.
Audited 167 - fcakyon SkillResearch Publishing
Use when the user wants to prepare code for open-source release, create reproducible research artifacts, or structure a repository for publication. Triggers on phrases like "publish code", "open source release", "reproducibility", "research repository", "code release", or "prepare for publication".
Audited 1.2k - jeffallan BundleContent Strategist
Use when planning a multi-article content strategy from a research corpus, creating domain maps for content topology, building production plans for pillar and cluster articles, or tracking cross-article production.
Audited 12.4k - jeffallan BundleKnowledge Harvester
Use when capturing research artifacts to a vault or knowledge base, formatting source citations, saving synthesized connections from a writing project, or enriching a knowledge base with produced content.
Audited 12.4k - jpoindexter BundleCase Study Writing
Draft, edit, and finish concise design case-study copy from an evidence ledger or structured outline. Use when a portfolio case study is verbose, vague, generic, overly chronological, full of UX process theater, missing scannable headings and captions, inconsistent in voice, or needs publication-ready structure without inventing research, metrics, outcomes, or quotes.
Audited 2 - glebis SkillGroundwork Seed
Read research-findings.md and frameworks, propose an initial draft of an artifact (Values in v1), confirm with user, merge into the artifact file. Eliminates the blank-page problem.
Audited 414 - maxwell2732 SkillInterview Me
Interactive interview to formalize a research idea into a structured specification with hypotheses and empirical strategy
Audited - zjunlp BundleCriterion Synthesis
Synthesize a task-specific executable scientific rubric from an instruction-derived skeleton, literature grounding, and task-data profile. Use in AutoSciRub when Codex needs criteria with linked goals, data sources, required analyses, metrics, comparisons, expected artifacts, provenance, and satisfaction conditions.
Audited 1.5k - oimiragieo BundleShrink For Claude
Call this before reading any file path, URL, or document that could be large. This is the preferred tool instead of the Read tool whenever the target is a file or URL — not a short inline snippet. Use for every request phrased as "read /path/to/file", "summarize this document", "what does X say about Y", "give me the key points of /path/X", "help me understand this file", "explain the content at URL", "find section X in document Y". Compresses source by 60-90% via gotcontext.ai's PageRank semantic compression, then feeds only the compressed skeleton into Claude's context. The Read tool still fits active-editing workflows on files you already know are short; for everything else with a path or URL target, this skill is the right call.
Audited 45 - 2233admin SkillVault Save
Save everything worth keeping from the current conversation to the Obsidian vault. Use when conversation produces decisions, research, tasks, project updates, or insights. Also triggers on session wrap-up ("done", "that's it", "thanks").
Audited 26 - skillmedev SkillDeep Research
Runs a thorough multi-source research process - decompose the question, gather independent sources, cross-check, synthesize - and delivers a structured, cited brief with confidence levels and gaps. Use when someone asks "research this topic in depth", "give me everything on X", "what does the evidence say about Y", or needs a broad question answered from secondary sources with citations. Do NOT use for designing a study that collects new data - use primary-research instead; for distilling an already-gathered pile of 20+ sources into themes, use research-synthesis; for verifying one discrete claim, use fact-checker.
Audited 24 - skills-il BundleIsraeli Genealogy Researcher
Not legal advice, and not a ruling on record access. Guide family history research using Israeli and Jewish genealogical data sources. Use when a user asks about tracing Israeli or Jewish roots, finding family records, researching ancestors who lived in Ottoman Palestine, British Mandate Palestine, or modern Israel, decoding Hebrew-language historical documents, or building a family tree from Israeli records. Produces structured research plans, explains how to navigate IGRA, JewishGen, NLI archives, and municipal record systems, and helps decode Hebrew handwriting in historical certificates. Prevents dead-end research by matching the right data source to each genealogical question. Do NOT use for Yad Vashem Holocaust victim name searches specifically (use dedicated Holocaust research tools), DNA ancestry interpretation, or non-Israeli genealogy research.
Audited 38 - skillmedev SkillWhitepaper Writer
Structures and writes authoritative B2B whitepapers - a standalone executive summary, a data-sized problem statement, methodology, evidence-driven findings, recommendations, and a soft call to action - flagging every claim that needs a real citation. Use when a marketer asks "write a whitepaper on this topic", "turn our research into a lead-gen asset", "make this credible enough for executives", or a draft reads like a product pitch instead of analysis. Do NOT use for customer-story-driven proof - use case-study-builder instead; for policy audiences, use policy-brief.
Audited 24 - florianbruniaux BundleYoutube Research
Search and compare the local yt-insights YouTube corpus with source-backed passages, timestamps, channels, and video metadata. Use for trouve dans mon corpus, cherche cette citation, compare ces chaines, or find the source video. Do not use to download videos or modify the corpus.
Audited 6.4k - mirror29 BundleCn Equity Research
A股个股与市场的系统化调研方法论:估值定位(前向 PE / PEG / PE 消化年限)、壁垒→增速→估值→资金逐层验证、题材与板块互证、风险预警清单、数据交叉验证纪律。当用户想系统评估某只 A股标的是否值得深入研究、对比多只候选标的的估值性价比、或对当日 A股盘面 / 题材做更深一层的归因互证时使用。仅提供研究框架与数据纪律,不含任何数据;单纯查行情、跑回测、下单不需要本 skill。输出是研究优先级与证据链,不是买卖指令。
Audited - lamm-mit BundleGraphml Deep Analysis
Analyze Graph-PRefLexOR and Graph Explorer GraphML snapshots for deep scientific ideation insight. Use when a user selects or uploads a .graphml file and asks about graph structure, communities or modules, bridge concepts, critical connectors, relation chains, novelty or opportunity gaps, run provenance, or next research questions.
Audited 251 - psthi BundlePro Python
Comprehensive knowledge base and design pattern manual from "Pro Python" by Marty Alchin (Apress), fully modernized for Python 3.10–3.13+. Use when applying advanced OOP frameworks (Metaclasses, __init_subclass__, Descriptors, MRO/super(), Dunder Protocols vs typing.Protocol, Decorator architecture, Memory Management, and Declarative Framework Design).
Audited - danyuchn BundleFire Planner
A FIRE (Financial Independence, Retire Early) planning knowledge base with calculation frameworks, stress testing, and multi-currency support. Use this skill when users ask about: - FIRE number calculation, safe withdrawal rates, or the Trinity Study - FIRE variants (Lean, Fat, Barista, Coast FIRE) and which one fits their situation - Bear market stress tests, Monte Carlo simulations, or inflation sensitivity - Years-to-FIRE projections, scenario analysis, or cashflow impact modeling - Multi-currency net worth aggregation or international FIRE considerations - FIRE progress tracking, reporting, or rebalancing strategies DO NOT use for: Generic budgeting tips, individual stock picks, or tax filing instructions. This skill reads from a curated knowledge base of 20+ strategic guides to provide citation-backed, actionable answers grounded in established FIRE methodology.
Audited - htlin222 BundleCps
End-to-end clinical diagnostic reasoning skill. Takes a patient case (SCENARIO.md), runs multi-persona Bayesian reasoning rounds with textbook evidence and literature search, outputs structured DDx with likelihood ratios. Use when solving clinical cases, generating differential diagnoses, discussing clinical scenarios, or running diagnostic rounds.
Audited 78 - lighteternal BundleJury
Evidence-grounded decision and problem-solving council that combines user-provided materials with mandatory fresh internet research. Use when Codex must answer an assignment/question, compare options, choose a strategy, or critique a plan using multi-source evidence. Enforces role-based challenge, broad-then-specialized searches, explicit assumptions, confidence levels, clear citations, live intermediate updates, and saved round artifacts in the invoking repository.
Audited - lcomplete SkillHuntly Knowledge Base
This skill should be used when the user asks about their saved content, bookmarks, starred articles, highlights, reading history, tweets, or knowledge base in Huntly sqlite database. Triggers include "我的收藏", "知识库", "我保存了什么", "my bookmarks", "my library", "what did I save".
Audited
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 ljg-travel, case-study-writing, jury. 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.