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.
-
frankxai Skill Wealth ResearchUse when mapping public wealth, custody, portfolio, privacy, and OSS finance tooling for an Agentic Wealth OS without using private financial data.
-
frappucc1no Bundle RecallloomUse when a task involves continuing a project, restoring project context, maintaining file-based project memory, updating current-state summaries, or recording meaningful progress across sessions. Works best for long-horizon, file-based projects and supports research writing, product document collaboration, software project coordination, and broader cross-functional project continuity.
-
highbridgedragon Bundle Jp LawSearch and retrieve Japanese laws and regulations via the official e-Gov Law API V2 (no auth required). Supports law name search, article retrieval, amendment history, and full-text keyword search. Useful for legal research, compliance checks, contract review, and any task involving Japanese statutes (民法/Civil Code, 会社法/Companies Act, 個人情報保護法/APPI, 労働基準法/Labor Standards Act, etc.). 日本の法令をe-Gov法令API V2経由で検索・取得するスキル。法令名検索、条文取得、改正履歴、キーワード検索に対応。Use this skill when researching Japanese laws, regulations, or legal texts.
-
reedliner Bundle Critical MirrorIndependent assessment of a user's judgment, interpretation, plan, choice, or leaning in any domain. Use only when the user states or implies a position and asks to evaluate it, including follow-ups that challenge or pressure the assessment. Signals: 'What do you think?', 'Is this reliable?', 'objective analysis', 'What are the risks?', 'am I missing something', 'stress test'. Do not use for pure generation, drafting, execution, summarization, research, factual Q&A, or neutral review that does not evaluate the user's position.
-
ryuketsukami Bundle Simple ExplanationExplain anything simply — lead with the answer, layer the depth, use plain words, keep every fact. Use when asked to explain, describe, clarify, simplify, summarize, teach, or break down a concept, system, codebase, architecture, decision, error, or document; when writing a TL;DR, overview, onboarding note, tutorial intro, or the answer to a how/why/what question; when asked for ELI5, layman's terms, beginner-friendly, non-technical, or plain-English explanations; or when an existing explanation buries its point, front-loads background, or overwhelms the reader. Do not apply to code or identifiers.
-
s313s Bundle Deal Signal HunterUse when AI freelancers, one-person companies, or small studios need help with client acquisition, lead research, outreach messages, self-promotion, service showcase pages, ability one-pagers, case page generation, sales conversations, pricing, proposals, follow-up messages, deal tracking, avoiding free-demo scope creep, or converting past client chats into reusable negotiation experience.
-
saltgardenia Bundle Research Code Skill---
-
scrollport Bundle Sales Qualified AccountsResearch a supplied account list or discover a bounded prospect pool, verify company fit and current decision-makers, and return sourced contact records with verified professional emails. Use when manual qualification, stale contacts or missing account context are slowing prospecting.
-
shellydeng08 Bundle Youtube ConnectorAccess YouTube data using curl, jq, and yt-dlp. Use this skill whenever the user wants to search YouTube videos, get video details or statistics, fetch channel information, read video transcripts/captions, browse comments, or explore playlists. Also use when the user mentions YouTube in any research, analysis, or data-gathering context — even if they don't explicitly say "use YouTube API."
-
shiyupro Bundle Evidence Bound ExecutionUse when creating or revising an artifact, product, or implementation that must carry prior diagnosis, user corrections, named examples, research, benchmarks, or non-negotiable acceptance conditions into the actual output, especially after a rejected iteration. Converts judgment into observable execution constraints and blocks unsupported outcome claims. Skip simple factual answers and purely mechanical edits with no qualitative or evidence constraint.
-
shivamgoyal03 Bundle MindmeshTransform unstructured knowledge from conversations, research, URLs, ideas, screenshots, and other sources into structured, searchable personal knowledge. Use when capturing, organizing, enriching, connecting, updating, or retrieving knowledge through the MindMesh knowledge system.
-
somezak1 Bundle Research Anything当用户抛出探索性想法(没做过、不知道成熟路径,如"做 AI 漫剧""搭 XX 工作流""视频转文字选型"),或明确要求"调研某方向/看看有没有成熟做法/收集资料/比较方案"时使用。适用于需要跨抖音/小红书/知乎/B站/YouTube/GitHub/Twitter/通用 web 收集市面方案的场景。
-
stmarks99 Bundle Financial AnalysisUse when asked for a stock analysis, equity deep dive, company valuation, or investment research on a publicly listed company — including requests to "analyze", "research", "value", or "build a thesis on" a ticker, or to refresh an existing analysis after earnings or a large price move.
-
stronling Bundle Deep ResearchAchieve scholarly excellence with global top-tier interdisciplinary research standards. Enforces authoritative source mandates, dual verification protocols, and polyphonic expertise synthesis. Includes an operational layer for query routing, loop resilience, and quick/deep/exhaustive iteration control. Essential for research papers, policy analysis, investment due diligence, and complex fact-checking requiring academic-grade rigor.
-
zorineinsupportable217 Bundle Buyer EvalStructured B2B software vendor evaluation for buyers. Researches your company, asks domain-expert questions, engages vendor AI agents via the Salespeak Frontdoor API, scores vendors across 7 dimensions, and produces a comparative recommendation with evidence transparency. Use when asked to evaluate, compare, or research B2B software vendors.
-
zsun79 Bundle Write Literature ReviewIterative literature-review workflow for a research topic. Use this skill to draft up to 10 search keywords, build a seed set from OpenAlex title-and-abstract matches, expand by backward and forward citations, screen candidates by title and abstract, repeat until no new relevant papers remain, rank the final set, inspect up to 30 full texts, build a concept-reference knowledge graph, and write a literature review grounded only in the final included references.
-
aaaronmiller Bundle Create Viral Content> ⚠️ **BEFORE USING THIS SKILL:** Review all files in the `references/` directory. These contain AI tell catalogs, platform templates, refinement protocols, and 40-source research basis required for proper skill execution.
-
aavanian Bundle Convo To OrgExport the current conversation to org-mode format. Two modes: (1) notes — generates an org snippet for pasting into a notes file, (2) blog — generates a Hugo-compatible org file with TOML frontmatter. Trigger with phrases like 'save this to my notes', 'summarize for notes', 'save this for my blog', 'summarize for blog', or 'export this conversation'.
-
abdullah4ai Bundle Personal ShopperSmart product research assistant using the Diamond Search methodology (7 specialized agents across 3 layers). USE WHEN: user wants a product recommendation, shopping advice, "what's the best X", "compare X vs Y", "find me a good", product comparison, buying decision help, "is this a good deal", "should I buy X or Y", "أبغى أشتري", "وش أفضل منتج", "قارن لي", "ابحث لي عن", "مقارنة منتجات". DON'T USE WHEN: user wants price tracking over time, order placement, returns/refunds help, market analysis for business entry (use mckinsey-research), general web search not about purchasing, reviewing or troubleshooting a product they already own, comparing companies as businesses. EDGE CASES: "what's the best laptop" → this skill. "what's the laptop market size" → mckinsey-research. "compare two products by specs" → this skill. "compare two companies competitively" → mckinsey-research. "is this a good deal on Amazon" → this skill. "analyze the deals market" → mckinsey-research. "أبغى أشتري لابتوب" → this skill. "أبغى أفتح
-
frostime Skill Siyuan CLIManage SiYuan Note with the `siyuan-cli` CLI. Use this whenever the user mentions SiYuan, notebooks, documents, blocks, or wants to query/update a SiYuan knowledge base.
-
girmmy Skill Opportunity TrackerRead and update the user's Opportunity Tracker — the internship, job, program, and research tracker at their own deployed URL. Use this whenever the user asks about their applications, deadlines, interviews, or where something stands; when they want their inbox swept for application updates; when they paste a job posting and want it logged or rated; or when they ask what to apply to next. Also use it before drafting any application material, since it holds the profile that material should be based on.
-
given-dream Bundle Research Review Writing PolishUse when the user is drafting or revising a research paper or review paper and wants Codex to generate, rewrite, expand, condense, translate, or polish academic prose from outlines, notes, literature summaries, figure interpretations, or draft text while preserving scientific meaning and evidential boundaries.
-
glichtenthal Bundle Briefing RoomUse when the user brings messy, layered, scattered, overloaded, or ambiguous context and asks to organize it into a brief. Trigger on notes, transcripts, research dumps, meeting context, strategy thoughts, emails, Slack threads, customer feedback, planning fragments, personal context, or requests like "make sense of this," "structure this," "what matters here," "clean this up," "prepare this for Ground Truth," or "prepare this for The Quorum."
-
goktugcy Bundle Tavilyuse this when the user asks to search the web, look up recent information, check current events, gather online sources, or research a topic using tavily search.
-
gorango Bundle Fmp SkillsFinancial Modeling Prep (FMP) provides 100+ tools for stocks, ETFs, forex, crypto, commodities, economics, ESG, SEC filings, financial statements, and more. Use when asked about financial data, stock analysis, company research, market data, or economic indicators.
-
gracker Bundle Gracker Deep ResearchGracker Deep Research Skill · 三阶段调研法(本地扫描 → 探索落盘 → 利用写作)。Phase 0 扫描本地优质资料,Phase 1 全力搜索并落盘,Phase 2 断网只读本地文件写报告 + Gracker 写作四层质检。触发词:「深度调研 XXX」/ 「Gracker Research XXX」/ 「dg XXX」。
-
moonweave-systems Bundle DecideUser-invoked research skill. Investigates current industry best practice via parallel WebSearch + context7 + GitHub adoption signals, then either decides autonomously (reversible actions) or escalates with factual-context questions (contested or information-requiring decisions). Manually triggered via `/decide` only — never auto-invoked. Use when the user types `/decide` optionally followed by a question. Without arguments, extract the pending decision from the prior assistant message.
-
morvanzhou Bundle Idea2mvpDiscover product ideas, validate them, and build MVPs. Search trending tools across Product Hunt, GitHub, Indie Hackers, XiaoHongShu, V2EX, SSPAI, etc. Validate feasibility via market research and competitive analysis. Build MVPs. Send reports via email. Triggers: 'find ideas', 'search products', 'trending tools', 'product ideas', 'validate my idea', 'build MVP', 'market research', 'competitive analysis', 'indie hacker', 'send email', '找想法', '搜产品', '找灵感', '产品调研', '验证想法', '构建MVP', '发邮件', '发送报告'.
-
mr-ds-ml-85 Bundle Searxng WebsearchUse this skill whenever the user wants to search the web, do research on a topic, fetch a webpage, or gather information from online sources using a self-hosted SearXNG instance. Triggers include: 'search for', 'look up', 'find online', 'deep research', 'fetch this page', 'web search', or any request that needs current/external information. Also use when the user wants to run websearch.py, deep_research.py, or fetch_page.py scripts. Do NOT use for local file operations, code execution unrelated to search, or tasks that don't require web data.
-
nebulaesoft Bundle ParmindSearch, read, and save to the user's Parmind knowledge base (their "second brain"). Use when the user asks about their notes/Minds, references saved knowledge, or wants to capture a durable insight.
-
pbnz Bundle NewtonReasoning and sparring partner mode for rigorous, calibrated engagement on any topic — pressure-testing ideas, researching with current authoritative sources, running reuse-before-rebuild checks on "how do I" tasks, and scoping work thoroughly before diving in. Use this skill ONLY when the user explicitly invokes Newton by name — e.g., the message starts with "Newton —" or "Newton," or the message contains "use Newton", "invoke Newton", "ask Newton", or "Newton mode". Do NOT trigger this skill for general reasoning, research, problem-solving, or advice requests where the user has not named Newton specifically.
-
paperasseai Bundle DemarchesGrounded, citation-enforced knowledge for government procedures — French démarches first (visa, titre de séjour / ANEF, CAF/APL, carte Vitale, déclaration de revenus & 2042 box map, auto-entrepreneur, CFE, INPI, passeport, CNI, retraite…) plus Nigerian document authentication. Use whenever a question touches administrative procedures, official forms, supporting documents, or a stuck government téléservice; answer from a card and cite it with its sources_verified date.
-
pierojf Bundle Dr JoeUse when evaluating non-thesis academic coursework such as essays, reports, literature reviews, lab reports, or design reports, or when the user explicitly invokes Dr. Joe by name. Do not activate implicitly for a thesis or dissertation.
-
pilgrimch Bundle Autonomous Research OrchestratorPursue an empirical research goal through bounded experiments, evidence-based replanning, Luna workers, and Brain handoffs. Use to initialize, resume, or run autonomous research, or maintain its orchestration. Automatically keep adjacent-stage working documents short and a traceable research history of methods, outcomes, decisions, and contributions. Skill maintenance or research review does not resume a paused experiment.
-
platanor Bundle Hardware ComplianceReference knowledge base on EU hardware/IoT cybersecurity law, maintained by Platanor Technologies — covering the Cyber Resilience Act (Regulation (EU) 2024/2847), the Radio Equipment Directive cybersecurity requirements (Directive 2014/53/EU, Delegated Regulation (EU) 2022/30 as amended, EN 18031), the NIS2 Directive (Directive (EU) 2022/2555), and the Cybersecurity Act / EUCC certification framework (Regulation (EU) 2019/881). Use this skill whenever the user asks anything about CRA compliance, essential cybersecurity requirements (Annex I), product risk classification (Default, Important Class I/II, Critical), CE marking for products with digital elements or radio equipment, vulnerability and incident reporting (CRA Article 14 or NIS2 Article 23), CRA/RED/NIS2 penalties and fines, deadlines and transition periods, manufacturer/importer/distributor obligations, whether NIS2 applies to a hardware manufacturer or its customers, EUCC/CSA certification and assurance levels, how these four regulations relate to
-
ideaflowco Skill CciSearch Claude Collective Intelligence knowledge base for solutions to problems. Use when the user asks about common issues, wants to find existing solutions, or mentions "CCI", "collective intelligence", or "knowledge base".
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 wealth-research, recallloom, jp-law. 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.