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.
- ur-grue BundleTopic Background Brief
Organise user-provided notes, facts, and context into a structured background brief for a story — creating a scannable reference document that a journalist, producer, or editor can consult throughout production.
Audited 46 - ur-grue BundleEvent Timeline Compiler
Compiles key events into a structured, scannable timeline — formatted as a table or numbered list — designed for use in graphic production, digital interactives, sidebar fact boxes, and editorial planning documents.
Audited 46 - ur-grue BundleSource Cross Referencer
Takes a specific claim and a list of sources you have gathered, then maps which sources support, contradict, or are silent on the claim — so you can see at a glance whether your sourcing is solid before publication.
Audited 46 - ur-grue BundleHistorical Precedent Finder
Identifies historical precedents relevant to a current news event or policy debate, provides a structured comparison showing why each precedent is or is not analogous, and lists the sources a journalist should consult to verify and deepen each comparison.
Audited 46 - ur-grue BundleDemographic Data Brief
Produces a concise, journalist-ready profile of the population structure, trends, and key demographic characteristics of a specified region, city, country, or community — ready to use as background for a story or segment.
Audited 46 - ur-grue BundlePolitical Landscape Brief
Produces a structured research framework that maps the key political actors, power dynamics, fault lines, and contextual background a journalist needs to understand before reporting on a region or country — without making factual assertions about current events that require live verification.
Audited 46 - ur-grue BundleStock Footage Brief
Produces a structured brief for a researcher or footage coordinator to use when sourcing stock or archive footage from libraries, broadcasters, or specialist archives.
Audited 46 - ur-grue BundleMeta Analysis Finder
Explains what meta-analyses and systematic reviews are, how to locate them for a given topic, and how to read them critically — giving journalists a reliable route to the strongest available evidence without relying on individual studies.
Audited 46 - ur-grue BundleManuscript Formatter
Reformats a manuscript, article, or long-form text to match a specific publication's structural and style requirements — adjusting headings, paragraph spacing, citation format, pull-quote placement, and front matter without altering the content itself.
Audited 46 - ur-grue BundleLocation Visual Brief
Produces a written visual brief describing the architectural character, light conditions, landscape qualities, and cinematic potential of a specific location — giving a director, cinematographer, or art director a working picture of a place before a recce.
Audited 46 - ur-grue BundleDerived Metrics Calculator
Takes raw numbers you provide and calculates derived figures — percentage changes, per-capita rates, index values, or ratios — with plain-language explanations ready to drop into a story.
Audited 46 - ur-grue BundleCross Country Data Comparer
Takes a specific indicator or metric and produces a structured, journalist-ready comparison of how multiple countries perform on that measure, including context on what the differences mean.
Audited 46 - ur-grue BundleJournal Landscape Guide
Maps the academic publishing landscape for a given field — explaining which journals matter, what they signal about credibility, and where preprints fit — so journalists can navigate scientific literature without prior academic training.
Audited 46 - ur-grue BundlePolicy Decisionmakers Finder
Maps the roles, institutions, and access channels a journalist needs to identify who actually controls a given policy area — from elected officials to unelected technocrats to influential advisers.
Audited 46 - ur-grue BundleScience Jargon Explainer
Translates dense scientific terminology from academic papers, press releases, or expert interviews into plain English a journalist can quote or paraphrase.
Audited 46 - ur-grue BundleArchive Institution Finder
Identifies which museums, national archives, libraries, film institutes, or specialist collections are most likely to hold historical material relevant to your story or documentary subject.
Audited 46 - ur-grue BundleCompetitor Engagement Analyzer
Interprets audience engagement signals from a competitor's published piece — comments, shares, reader responses, social traction — to identify what resonated with the audience and why.
Audited 46 - ur-grue BundlePaper Plain Language Summary
Translates the key findings of a scientific paper — abstract, methods, and conclusions — into clear, accurate plain English that any reader can understand without specialist knowledge.
Audited 46 - marielynneblock BundleNeurokit2
Comprehensive biosignal processing toolkit for analysing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.
Audited 4 - marielynneblock BundleNetworkx
Comprehensive toolkit for creating, analysing, and visualising complex networks and graphs in Python. Use when working with network/graph data structures, analysing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualising network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.
Audited 4 - marielynneblock BundleFda Database
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
Audited 4 - marielynneblock BundleOpen Notebook
Self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use when organising research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 16+ AI providers including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral with complete data privacy through self-hosting.
Audited 4 - marielynneblock BundleBrenda Database
Access BRENDA enzyme database via SOAP API. Retrieve kinetic parameters (Km, kcat), reaction equations, organism data, and substrate-specific enzyme information for biochemical research and metabolic pathway analysis.
Audited 4 - marielynneblock BundleBiorxiv Database
Efficient database search tool for bioRxiv preprint server. Use this skill when searching for life sciences preprints by keywords, authors, date ranges, or categories, retrieving paper metadata, downloading PDFs, or conducting literature reviews.
Audited 4 - marielynneblock BundleOpenalex Database
Query and analyse scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analysing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.
Audited 4 - marielynneblock BundleScientific Writing
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.
Audited 4 - marielynneblock BundleStatistical Analysis
Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.
Audited 4 - swan-gtm SkillPersonalization Hooks
Use this skill when turning prospect research into opening lines, choosing between a strong hook (verbatim quote) and a lite hook (conceptual tie), connecting personalization to relevance, or crafting personalized first lines for cold email and LinkedIn.
Audited 236 - swan-gtm SkillAccount Intelligence
Pull a decision-ready intelligence brief on any target account. Takes a company name, domain, or Lusha company ID plus a one-line research context — QBR, competitive deal, cold outbound, or inbound triage. Returns firmographics, buying signals, key contacts verified via Lusha, recent news and scoops, and ranked next actions — all framed by your stated purpose. Requires a Lusha connection.
Audited 236 - swan-gtm BundleAeo Visibility Tracking
Use this skill when the user wants to measure or improve how their brand shows up in AI-generated answers — "do we appear in ChatGPT answers," "track our AEO score," "which sources do AI engines cite for our category." Seeds the prompts buyers actually ask, tracks brand visibility per engine and country over time, and mines the citation sources to show where content effort moves the score.
Audited 236 - swan-gtm SkillCitation Gap Outreach
Use this skill when the sources behind AI answers are known and the brand needs to get into them — "AI keeps citing these directories and the brand is not there," "turn the citation analysis into an outreach plan," "get named where the engines already read." Converts cited-source gaps into a ranked get-listed plan with the right ask per source type and a re-measure loop proving each placement moved answers.
Audited 236 - bg-szy BundleNature Polishing
Polish, restructure, or translate academic prose into concise Nature-leaning English while preserving facts, evidence boundaries, terminology, and citation intent. Use for manuscript paragraphs, abstracts, introductions, Results, discussions, conclusions, titles, Methods, Chinese drafts, proofreading, language editing, and general academic or scientific writing. Also use to shorten bloated Results, allocate evidence across main text, captions, and Supplementary Information, prevent reviewer-driven revision accretion, reduce repeated statistics or claims, and apply paragraph-necessity checks. Covers LaTeX layout or typesetting fixes such as sparse pages, stranded headings, oversized or split figures, float errors, multi-panel arrangement, and sparse Supplementary Information via references/latex-layout.md. Trigger on 学术写作、科研写作、论文润色、SCI写作、英文论文润色、语言润色、润色、改写、学术英语、排版.
Audited 6 - gaelic-ghost BundleSelect Analysis Path
Choose the smallest useful reverse-engineering workflow from an artifact's format, runtime, platform, available evidence, and research question. Use when Codex must decide between metadata inspection, static analysis, decompilation, disassembly, symbol or crash correlation, resource inspection, dynamic analysis, version comparison, or a tool-specific workflow for binaries, bundles, assemblies, firmware, or generated analysis output.
Audited 10 - knuckles-team BundlePaper Scan
Parallel execution workflow for paper scan using the Unified Parallel Engine
Audited 5 - knuckles-team SkillContent Outline Builder
Turn an approved content brief and source packet into a structured, evidence-aware outline with a thesis, section purposes, claim placement, and source mapping. Use when a user has a topic, audience, objective, and research but needs the argument organized before drafting. Do not use to research sources, write the full draft, or publish content.
Audited 5 - okhp3 BundleOkhp3 Askjamie Chatgpt Migrate
OverKill Hill P³ ChatGPT project migration. Use when migrating, preserving, extracting, inventorying, normalizing, reconciling, or incorporating ChatGPT project threads, conversation exports, or complete chat histories into a repository. Also activate when a user needs a lossless thread archive, project-to-export crosswalk, provenance ledger, or public-safe distillation workflow. This is the authoritative capture and reconciliation process for ChatGPT project material in this repo -- use it even when the user asks only to "save", "review", or "summarize" a large set of threads.
Audited 3
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 networkx, stock-footage-brief, meta-analysis-finder. 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.