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.
- aifinlab BundleGlobal Citation Traceback
用于引用追溯场景。适用于金融工作中的基础任务单元。
Audited 274 - amey-thakur SkillReading Papers
Read research papers efficiently in passes, separating claims from evidence and assessing reproducibility. Use when extracting value from academic papers without reading every one cover to cover.
Audited 14 - amey-thakur SkillPivot Tables
Summarise and cross-tabulate large tables quickly with pivots, keeping the source data clean and the refresh reliable. Use when aggregating data by category, period, or dimension.
Audited 14 - cslawyer1985 BundleLegal Citation Manual
法学引注手册——中国法学学术引注规范。融合《法学引注手册》(2019年版)体例,覆盖法律法规、司法案例、期刊论文、学术著作、网络文献等各类中英文法学文献的引注格式。适用于法学论文写作、学术发表、法律文书起草。北大法律人出品。
Audited 926 - haibarakiku BundleGrant Reviewer
Senior Grant Reviewer with 20+ years evaluating research proposals for major funding agencies (NIH, NSF, DOE, DOD). Use when reviewing grant applications, scoring proposals, or developing funding strategies
Audited 6 - haibarakiku BundleLab Technician
Expert laboratory technician specializing in experiment execution, sample preparation, equipment operation, and accurate data recording
Audited 6 - onfire7777 BundleGh Fix CI
Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions. Uses `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treats external providers (for example Buildkite) as out of scope and reports only the details URL. Do NOT use for addressing PR review comments (use gh-address-comments) or general CI outside GitHub Actions.
Audited 17 - onfire7777 SkillTavily Web
Web search, content extraction, crawling, and research capabilities using Tavily API
Audited 17 - onfire7777 BundleResearch Claim Map
Use when verifying claims before decisions, fact-checking statements against sources, conducting due diligence on vendor/competitor assertions, evaluating conflicting evidence, triangulating source credibility, assessing research validity for literature reviews, investigating misinformation, rating evidence strength (primary vs secondary), identifying knowledge gaps, or when user mentions "fact-check", "verify this", "is this true", "evaluate sources", "conflicting evidence", or "due diligence".
Audited 17 - haibarakiku BundleVisiting Scholar
Expert visiting scholar specializing in cross-institution research collaboration, academic exchange programs, fellowship applications, and host institution integration
Audited 6 - haibarakiku BundleInvestment Analyst
Expert Investment Analyst with deep expertise in equity research, fundamental analysis, valuation methodologies (DCF, comparable analysis, precedent transactions), investment thesis construction, and due diligence. Specializes in identifying variant perception and generating alpha through rigorous research. Use when: equity-research, valuation, fundamental-analysis, financial-modeling,
Audited 6 - haibarakiku BundleInstrument Manager
Senior instrument manager with 10+ years experience in centralized research facility management. Expert in HPLC, GC-MS, NMR, TEM, SEM, confocal microscopy, and other major analytical instruments
Audited 6 - haibarakiku BundleGraduate Supervisor
Expert-level Graduate Supervisor with deep knowledge of doctoral mentoring, thesis supervision, research methodology guidance, and academic career development
Audited 6 - onfire7777 BundleScientific Critical Thinking
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence quality (GRADE, Cochrane ROB), for critical analysis of scientific claims.
Audited 17 - haibarakiku BundleParalegal
Senior paralegal specializing in legal research, document preparation, and case management. Use when conducting legal research, drafting legal documents, or managing case files
Audited 6 - haibarakiku BundleTech Transfer Manager
Expert technology transfer manager specializing in patent portfolio management, technology commercialization, industry partnerships, and intellectual property licensing
Audited 6 - haibarakiku BundleEngineering Consultant
Expert engineering consultant specializing in technical feasibility studies, project assessment, design review, and engineering solution development
Audited 6 - haibarakiku BundlePrincipal Investigator
Expert-level Principal Investigator skill covering research design, grant writing (NIH/NSF/ERC), experimental methodology, statistical analysis planning, manuscript writing, peer review, and lab management
Audited 6 - yogsoth-ai SkillSnowball
Citation-chain-driven literature survey starting from seed papers. Traces research lineage in both forward (who cited this) and backward (what this cited) directions until saturation. High deep-read ratio (67%). Use when the user already has key papers and wants to find everything connected to them — ancestors, descendants, and branch points.
Audited 512 - yogsoth-ai SkillCold Start
Full crystallization strategy for users who have no research direction at all. Covers actor profiling, landscape reconnaissance, direction narrowing, obstacle analysis, goal decomposition, and north-star synthesis. Use when the user's first message reveals zero specificity about what they want to research.
Audited 512 - yogsoth-ai SkillDesign Fmea
Strategy: Research design-level FMEA — function analysis, failure mode identification, severity/occurrence/detection scoring per AIAG-VDA 2019.
Audited 512 - yogsoth-ai SkillProcess Fmea
Strategy: Research execution process FMEA — analyzes how the research process itself can fail during execution, distinct from design-level failures.
Audited 512 - yogsoth-ai SkillAsk Constraints
Understand hard boundaries on the user's research — target venues, methodology preferences, areas to avoid, advisor/team requirements. Not limited to ML/AI — works for any research domain.
Audited 512 - yogsoth-ai SkillAxis Extraction
Tactic for systematically extracting axes of variation from literature — identify how practitioners compare approaches.
Audited 512 - cslawyer1985 BundleOpenclaw Indian Advocate
AI legal assistant for Indian advocates and lawyers. Use this skill whenever an Indian advocate needs help with legal work: drafting legal notices, vakalatnamas, plaints, written statements, bail applications, affidavits, petitions (writ, civil, criminal), FIR complaints, legal opinions, or any Indian court document. Also triggers for Indian statutes (IPC/BNS, CrPC/BNSS, IEA/BSA, Companies Act, GST, Arbitration), case law research, client intake, cause list management, court diary, fee notes, legal memos, or reading/analysing uploaded case files, judgments, charge sheets, or client documents. Triggers on: "my client", "HC", "SC", "district court", "sessions court", "NCLT", "DRT", "tribunal", "advocate", "vakil", "matter", "brief", or any Indian legal proceeding. Handles post-2024 BNS/BNSS/BSA reforms with dual-citation of old and new laws automatically.
Audited 926 - cslawyer1985 BundleCementops Msha Compliance
Prevent MSHA citations at cement plants before the inspector arrives. Free CementOps Compliance Suite skill. 30 CFR Part 56 hazard classification, stop-work authority, citation defense strategies, walk-through prep checklists, and rebuttal letter drafting.
Audited 926 - yogsoth-ai SkillExecuting Specs
Execute a Research Spec step by step, respecting context protocol, deviation limits, and backtrack rules. Supports multi-session recovery.
Audited 512 - yogsoth-ai SkillSpec Self Review
Quality gate for Research Specs. Checks for placeholders, consistency, scope, ambiguity, context protocol, and quantification. Mandatory before user review.
Audited 512 - yogsoth-ai SkillCitation Chaining
Forward and backward citation tracing tactic — expand paper coverage by tracing citation networks in both directions from seed/key papers. Alternates forward (who cited this) and backward (what this cited) passes until saturation.
Audited 512 - yogsoth-ai SkillLiterature Survey
Autonomous Literature Survey Campaign — 5 research paradigms (scoping, systematic, deep, narrative, snowball) with quantitative budget enforcement. Selects and executes the right survey paradigm based on research intent.
Audited 512 - yogsoth-ai BundleScenario Planning
What might the future look like — construct multiple future scenarios, assess research approach robustness under different assumptions
Audited 512 - yogsoth-ai BundleSpice Application
SOP: Apply the SPICE framework to structure an evaluation research question
Audited 512 - yogsoth-ai BundleQuestion Synthesis
SOP: synthesize all intermediate products into a final research-question set
Audited 512 - yogsoth-ai BundleFeasibility Scoring
SOP: assess the attackability of a research gap, identify bottlenecks, and output a feasibility score
Audited 512 - yogsoth-ai BundleLandscape Synthesis
Evaluate each candidate research field on maturity, competition, entry barrier, and publication opportunity. Synthesizes broad-web-search results into a structured FieldPanorama. Must consider both niche approaches AND direct frontal competition in hot fields.
Audited 512 - yogsoth-ai SkillLiterature Overview
Quick landscape scan — discover papers on a topic without full-text reading
Audited 512
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 reading-papers, global-citation-traceback, pivot-tables. 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.