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.
- microsoft SkillMass Change
Research and plan a large-scale change, then execute it in parallel across isolated agents that each open a PR.
Audited 195k - google-gemini BundleScript Writing
Generate the AI Talk Radio show script from research using the Interactions API.
Audited 3.8k - zhanlincui BundleCareer Os Router
Use when a career request may require choosing, sequencing, or resuming one or more Career OS skills across profile, project, story, resume, target research, interview preparation, practice, live support, or debrief.
Audited - skillmedev SkillJob Interview Prep
Prepares a candidate for a specific job interview - company research checklist, a STAR story bank mined from their resume and mapped to common competencies, a questions-to-ask bank, salary-question deflection lines, and a mock-interview loop. Use when a user says "I have an interview next week, help me prepare", "help me practice answers for this interview", "what should I ask the interviewer", "build me STAR stories from my resume", or "they're going to ask about salary, what do I say". Do NOT use for negotiating after an offer arrives - use salary-negotiation instead - and do NOT use for fixing the resume itself - use resume-reviewer instead.
Audited 24 - microsoft BundleMsresearch Bioemu
Microsoft Research's BioEmu — generates protein conformational ensembles from amino acid sequence on a local GPU. Use when users mention BioEmu by name, want to predict protein dynamics or flexibility from sequence, or are setting up / running / troubleshooting BioEmu locally.
Audited 195k - cslawyer1985 BundleZhihe Legal Research
连接智合AI法律大模型平台进行法律研究。本技能应在用户需要进行法律问题研究、查找法律法规、检索类似案例、或获取法律研究报告时使用。需要智合AI平台会员账号。
Audited 926 - alirezarezvani BundleResearch Finance
Manage R&D program budgets with F&A splits, track burn rate and runway against milestones, and route capitalize-vs-expense decisions to a named finance owner.
29.8k - alirezarezvani BundleNotebooklm
Browser-automates Google's NotebookLM to read notebooks, add sources, generate Studio outputs (Audio/Video Overviews, Mind Maps, Reports), and create new notebooks.
Audited 29.8k - nvidia BundleNv Generate Ct Rflow
Generates synthetic CT volumes and masks using NVIDIA's rectified-flow pipeline for medical imaging research.
Audited 23k - affaan-m SkillSearch First
Research existing tools, libraries, and patterns before writing custom code by invoking a researcher agent.
Audited 303k - antigravity BundleAI SEO
Optimize content for AI search and LLM citations across AI Overviews, ChatGPT, Perplexity, Claude, Gemini, and similar systems.
Audited 49.7k - openai BundleNotion Meeting Intelligence
Prepare meeting materials by gathering context from Notion, drafting agendas and pre-reads, and enriching with Codex research.
Audited 28.8k - openai BundleNotion Research Documentation
Search Notion pages, synthesize findings, and publish structured briefs, summaries, comparisons, or reports with citations and source links.
Audited 28.8k - k-dense-ai BundleScientific Schematics
Create publication-quality scientific diagrams using AI generation with smart iterative refinement and quality review.
Audited 57.3k - gonglingrui BundleKnowledge Query
专注于竖屏短剧知识库查询和信息检索,提供专业知识服务。适用于查询剧本桥段、高能情节、创作技巧、商业运营等专业知识
Audited 495 - seb1n SkillSummarization
Summarize text using extractive, abstractive, hierarchical, and multi-document techniques, producing concise outputs at configurable detail levels. Use when the user requests summarization or provides relevant inputs for this workflow.
Audited 255 - seb1n SkillLiterature Review
Conduct a structured literature review on a given topic by defining a search strategy, applying inclusion and exclusion criteria, extracting key findings, and synthesizing results into a coherent academic review. Use when the user requests literature review or provides relevant inputs for this workflow.
Audited 255 - seb1n SkillKnowledge Graph Creation
Build structured knowledge graphs from unstructured text by extracting entities, mapping relationships, generating graph triples, and visualizing the result. Use when the user requests knowledge graph creation or provides relevant inputs for this workflow.
Audited 255 - maragudk SkillDiary
Write and maintain an implementation diary capturing what changed, why, what worked, what failed (with exact errors and commands), what was tricky, and how to review and validate. Activates proactively during non-trivial implementation work (new features, bug fixes, refactors, research spikes). Does not activate for trivial tasks like one-line fixes, config tweaks, or quick questions.
Audited 30 - magnus919 BundleSkillopt
Run controlled skill optimization cycles on any skill document. Uses kanban-based pipelines with validation gates — the methodology from Microsoft Research's SkillOpt (arXiv 2605.23904).
Audited 343 - ferroxlabs BundleGrant Writer
Professional grant writing guide covering prospect research, letters of inquiry, full proposal development, budget construction, evaluation plans, compliance requirements, and post-award management for successful funding acquisition. Use when the user asks about grant writer, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of grant writer or requires a different specialized skill.
Audited 618 - ferroxlabs BundleEssay Outline
Creates detailed essay outlines with thesis statements, topic sentences, evidence placeholders, and conclusion structure for learners planning academic essays. Produces a complete skeleton the learner can fill in -- distinct from writing skills that produce finished text. Use when a learner asks to outline an essay, plan an academic paper, structure their writing before drafting, or organize their arguments. Do NOT use for writing the full essay (use writing category skills), for research paper structure (use writing `research-paper-structure`), or for creative writing outlines (use writing category skills).
Audited 618 - ferroxlabs BundleAb Test Design
Designs A/B tests with hypothesis, control and variant definitions, primary metric, sample size calculation, test duration, and analysis plan using experimentation methodology. Use when the user asks about A/B testing, experiment design, split testing, hypothesis testing, or controlled experiments. Do NOT use for statistical analysis of completed tests (use a statistics skill), survey design (use employee-survey or user-research-plan), or feature prioritization (use prioritization-framework).
Audited 618 - ferroxlabs BundleT Shirt Designer
Complete t-shirt design guidance covering design for print methods (DTG, screen print, sublimation), mockup creation, print-on-demand platforms (Printful, Redbubble, Merch by Amazon), niche research and market strategy, marketplace optimization, file preparation, and building a sustainable apparel design business. Use when the user asks about t shirt designer or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists.
Audited 618 - ferroxlabs BundleThesis Statement
Crafts focused, arguable, specific thesis statements for academic papers, essays, and dissertations. Distinguishes between descriptive and argumentative thesis types and tests for strength. Use when the user asks to write a thesis statement, develop a central argument, or create the core claim for an academic paper or essay. Do NOT use for full paper structure (use research-paper-structure), abstract writing (use abstract-writing), or non-academic arguments (use different writing skills).
Audited 618 - ferroxlabs BundleNote Synthesis
Synthesizes and connects concepts across multiple sets of notes for learners, identifying patterns, contradictions, and relationships between sources. Produces an integrative summary that goes beyond individual note sets. Use when a learner asks to connect ideas across notes, synthesize multiple readings, find patterns across study materials, or integrate notes from different lectures or sources. Do NOT use for single-source note taking (use `cornell-notes`), for concept mapping of one topic (use `concept-mapping`), or for academic literature review (use `literature-search`).
Audited 618 - ferroxlabs BundleAbstract Writing
Writes structured academic abstracts that state the problem, method, key findings, and implications in 150-300 words. Enforces findings-first writing over coverage descriptions. Use when the user asks to write an abstract for a research paper, thesis, conference submission, or journal article. Do NOT use for executive summaries (different format), paper introductions (use research-paper-structure), or literature review summaries (use literature-review).
Audited 618 - ferroxlabs BundleNon Fiction Author
Complete research-to-manuscript workflow for non-fiction books, covering topic validation, audience definition, competitive analysis, research methodology, outline construction, writing schedule, manuscript structure, and citation management. Use when the user asks about non fiction author or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists.
Audited 618 - ferroxlabs BundleQualitative Coding
Produces a qualitative coding scheme for interview transcripts or open-text survey responses. Includes initial code list, code definitions, example quotes per code, inter-rater reliability protocol, and thematic synthesis template. Use when the user asks to analyze interview data, code open-ended survey responses, build a coding scheme for qualitative research, or synthesize themes from text data. Do NOT use for survey design (use survey-design), automated sentiment analysis (use sentiment-analysis-guide), or large-scale text mining (use text-mining-protocol).
Audited 618 - ferroxlabs BundleDocumentary Filmmaker
Complete documentary filmmaking guide covering research methodology, interview preparation and technique, B-roll strategy, verite shooting, narrative structure for non-fiction, ethical considerations, archival material use, post-production workflow, festival strategy, and distribution for independent documentarians. Use when the user asks about documentary filmmaker or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists.
Audited 618 - haibarakiku BundleProsecutor Assistant
Prosecutor assistant specializing in case preparation, legal research, and prosecution support. Use when preparing criminal cases, researching case law, or supporting prosecution efforts
Audited 6 - mkurman BundleScientific Brainstorming
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Audited 327 - ferroxlabs SkillSalary Negotiator
Complete salary negotiation guide covering market rate research, total compensation analysis, negotiation scripts, counter-offer strategies, benefits negotiation for PTO, remote work, and equity, negotiation psychology, when to walk away, and annual review preparation. Use when the user asks about salary negotiator, or needs help with complete salary negotiation guide covering market rate research, total compensation analysis, negotiation scripts, counter-offer strategies, benefits negotiation for pto, remote work, and equity, negotiation psychology, when to walk away, and annual review preparation. Do NOT use when the request requires professional specialized advice or falls outside the scope of salary negotiator.
Audited 618 - minimax-ai SkillLiterature Search
当用户需要检索学术文献、按主题找论文、收集综述素材、查询某篇文献的元数据或 DOI、追踪某方向最新进展或预印本、做开题文献调研时使用。同义场景:文献检索、 论文搜索、查文献、找论文、文献调研、资料收集、题录补全、 "帮我找关于 X 的论文""这个主题有哪些代表性工作""查一下这篇文献的 DOI 和出处"。
Audited 13.8k - mitchuski SkillAgentprivacy Wiki Dream Cycle
The standing research loop that keeps the static guide rebound to the source. Each relevant /mitch repo "dreams" about itself — a deep multi-lap pass that diffs the repo's canon against the live FedWiki, writes a standing `chronicles/DREAM-<date>.md` (its resumable work-ledger), and feeds a single confirm-able GATE document. The First Person ticks the GATE; builders write the approved canon into ~/.wiki; the snapshot publishes it. Activates when planning what to fill into the guide next, running a daily research cycle, fanning out per-directory gap analysis, or turning "what's missing" into ordered next actions. Four stages — RESEARCH → GATE → BUILD → SNAPSHOT — looped until comfortable to push. Authored by the Chronicler 🧙📖, kept by the Librarian 🗃️.
Audited 1 - markoblogo BundlePersonal Workspace Router
Design or maintain a local personal AI workspace that routes requests to isolated domains and professional role profiles. Use when one personal operator spans projects, career, publishing, research, coaching, fitness, finance, and internal development without mixing all context or memory.
Audited 16
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 career-os-router, notebooklm, research-finance. 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.