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.
-
lobbi-docs Skill Deep ResearchComprehensive research on a topic using multiple sources and approaches. Spawns parallel research threads.
-
jshsakura Skill Scientific Literature ResearcherUse when a task needs evidence-grounded answers from published research, including methods, results, sample sizes, and quality-weighted synthesis.
-
kmshihab7878 Bundle PaperclipInteract with the Paperclip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any Paperclip API endpoint. Do NOT use for the actual domain work itself (writing code, research, etc.) — only for Paperclip coordination.
-
kmshihab7878 Skill Ad ResearchAutonomous competitor ad intelligence. Scrapes competitor ads from Meta Ad Library and other platforms, transcribes video ads, extracts hooks/angles/structure, and produces a full competitive intel dump. Use when researching competitor ads, analyzing ad creative strategies, building competitive ad intelligence, or preparing for ad script generation. Mirrors Eddie's Stage 1 (Competitor Intelligence).
-
kmshihab7878 Skill Research MethodologySearch and research workflow patterns. Research depth levels, source credibility assessment, multi-hop reasoning, search query formulation, and citation management. Use when conducting research, evaluating sources, or synthesizing findings.
-
kmshihab7878 Bundle UX Researcher DesignerUX research and design toolkit for Senior UX Designer/Researcher including data-driven persona generation, journey mapping, usability testing frameworks, and research synthesis. Use for user research, persona creation, journey mapping, and design validation.
-
wondermonger-daydreaming Skill Paper ProsopopoeiaEngaging scientific papers through voices, personas, and epistolary forms. Historical figures respond to research through letters, dialogues, and performances.
-
wondermonger-daydreaming Bundle Scholar EvaluationApply the ScholarEval framework to systematically evaluate scholarly and research work using peer-reviewed assessment criteria across multiple quality dimensions.
-
wondermonger-daydreaming Skill Paper TransmutationAlchemical derivation of technologies, futures, and scenarios from scientific papers. Research-to-blueprint transformation.
-
wondermonger-daydreaming Skill Paper To Lived WorldPhenomenological world-building from scientific papers. Generates vivid 'day in the life' scenarios from research findings.
-
robomotionio Bundle ArxivSearch and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read full paper content.
-
pantheon-org Bundle Create Context FileCreates a structured, date-stamped context file filed by typology (findings, plans, guides, follow-ups, merge-requests, tickets, decisions, notes, research) with YAML frontmatter. Use when saving a finding, writing a plan, capturing a guide, recording a decision, logging a follow-up, filing a merge-request note, plus ticket write-ups.
-
pantheon-org Bundle Vault ConsolidatePropose or apply consolidation of episodic memories into semantic ones, combining related episodic captures into higher-level semantic summary notes. Use after a long session or when the user asks to clean up, organise, summarise, merge, or declutter memories, or requests memory cleanup or memory management. Always run --propose first so the user can review before --apply commits changes to the vault.
-
mk-organization-1 Bundle Agency UX ResearcherExpert user experience researcher specializing in user behavior analysis, usability testing, and data-driven design insights. Provides actionable research findings that improve product usability and user satisfaction
-
lobbi-docs Skill Research RoutingResearch Tool Routing
-
lobbi-docs Skill Research ProtocolDeep research before task execution using 4-source protocol: codebase→Perplexity→Context7→Firecrawl
-
publieople Bundle Astrbot Plugin DevelopmentBuild an AstrBot plugin — covers fork-existing vs from-scratch decision, 4-quadrant research gate, doc reading order, decorator mechanics, schema field patterns, ad-hoc verification, CI preflight script. Use when user asks to "做一个 AstrBot 插件" or "集成 X 到 AstrBot" or describes a bot feature.
-
publieople Bundle Research First DevelopmentResearch-first implementation workflow — before writing any code, find the best existing open-source solution. Triggered by "不重复造轮子", "找现成方案", "用什么库", "调研方案", "有没有现成的".
-
publieople Bundle Bilibili Video SummarySummarize Bilibili (B站) videos using opencli bilibili subtitle + summary + video commands. Extracts subtitles, official AI summary, and video metadata, then synthesizes into structured summaries, blog posts, or threads.
-
mahmoud20138 Skill Fundamental Analysis> **Skill:** Fundamental Analysis | **Domain:** trading | **Category:** research | **Level:** intermediate
-
mahmoud20138 Skill Youtube Video To KnowledgeExtract knowledge from YouTube videos — transcripts, keyframes, metadata, AI-powered analysis, and AUTOMATIC skill integration. When a YouTube URL is shared, extract the content AND route the knowledge to related existing skills in parallel. Use this skill whenever the user shares a YouTube URL or asks to summarize/analyze/extract notes from a YouTube video. Also trigger for "youtube transcript", "video notes", "watch and summarize", "video summary", "extract from youtube", "youtube to text", "video knowledge", "NoteGPT", "summarize this video", "what does this video say", "video flashcards", "add to skills", or any request involving YouTube content extraction and analysis. After extraction, always identify and update related skills with the new knowledge. Works for any YouTube video with or without subtitles.
-
mahmoud20138 Skill Hurst Exponent Dynamics Crisis PredictionMark Vogel's Oxford ISF Conference research on rolling-window Hurst exponent dynamics of wavelet-denoised S&P 500 returns (2000-2020). Covers the chaos analysis framework, cascadic wavelet denoising, recurrence quantification analysis, multifractal DFA spectra, rolling-window bootstrapping, momentum crash prediction via fractal-trend-to-mean-reversion regime shifts, and continuous wavelet transform heatmaps for crisis detection. Contradicts Mandelbrot's long-memory interpretation -- shows H>0.5 indicates fractal trends not long memory. Source: VoglData, 42nd International Symposium on Forecasting, Oxford (2022). Use this skill for "hurst exponent dynamics", "rolling window hurst", "fractal trends", "wavelet denoised returns", "chaos analysis framework", "recurrence quantification", "multifractal DFA", "momentum crash prediction", "financial crisis prediction hurst", "efficient market hypothesis violation", "nonlinear dynamics finance", "power law returns", "fractal brownian motion forecast", "cascadic wavelet
-
matteotitta Skill Win LossWin/loss analysis
-
matteotitta Skill Brand KitResearch substrate (Exa)
-
matteotitta Skill Read BookRead book
-
matteotitta Skill Expert PovExpert POV
-
matteotitta Skill Signal ScanSignal scan
-
matteotitta Skill Watch VideoWatch video — transcribe and analyze any video, at the depth you choose
-
matteotitta Skill Icp ResearchICP research skill
-
matteotitta Skill Tov GuidelinesTOV guidelines
-
matteotitta Skill Company ContextCompany context
-
matteotitta Skill Funnel StrategyFunnel strategy
-
matteotitta Skill Icp BehaviouralICP Behavioural
-
matteotitta Skill Competitor ResearchCompetitor research
-
matteotitta Skill Customer InterviewsCustomer interviews skill
-
matteotitta Skill Gtme PodcastResearch source (Exa)
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 deep-research, scientific-literature-researcher, paperclip. 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.