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.
- brycewang-stanford SkillGetting Started With Research Superpowers
Introduction to literature search & review skills - systematic paper finding, screening, extraction, and citation traversal
Audited 5k - brycewang-stanford SkillCoding Guidelines
Standardized Python & Stata coding practices for empirical research projects
Audited 5k - brycewang-stanford SkillProject Structure
Project directory organization and script naming conventions for research
Audited 5k - brycewang-stanford SkillUnpaywall API
Find free legal full-text versions of scholarly articles via Unpaywall
Audited 5k - diegosouzapw BundlePlanning With Files
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Now with automatic session recovery after /clear.
Audited 87.5k - jantoniofc BundlePlanning With Files
Implements Manus-style file-based planning to organize and track progress on complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when asked to plan out, break down, or organize a multi-step project, research task, or any work requiring >5 tool calls. Supports automatic session ...
Audited 8 - thecraighewitt SkillOutbound Sequence
When the user wants to design a multi-channel outbound sequence or cadence. Also use when the user says 'build me a sequence,' 'create a cadence,' 'how many touches,' 'what's the right sequence,' 'multi-channel outreach plan,' 'design my outbound,' 'how should I follow up,' 'SDR playbook,' 'outbound motion,' 'sales sequence,' 'follow-up strategy,' 'prospecting cadence,' or 'drip sequence.' For individual channel content, see cold-email, cold-call, linkedin-outreach, or direct-mail. For research before sequencing, see lead-research.
Audited 172 - jacob-balslev BundleSemantic Relations
Use when typing edges in a knowledge graph or concept map, resolving synonym/antonym/polysemy/homonym confusion, testing whether a connection is IS-A, PART-OF, causal, thematic, or vague, explaining adjacent concepts, or auditing whether hierarchy and skill-boundary decisions use the wrong relation type. Covers taxonomic, associative, and thematic relations plus symmetry, asymmetry, transitivity, reflexivity, and irreflexivity. Do NOT use for formal ontology axioms with reasoning constraints, database foreign-key or junction-table design, or operational data correspondence across systems. Do NOT use for I need formal OWL axioms, class restrictions, and reasoning semantics on a knowledge base. Do NOT use for I need the physical database foreign keys and junction-table design for these relationships. Do NOT use for I need to connect external IDs from one platform to canonical IDs in our system operationally.
Audited 3 - outfitter-dev BundleTrails
This skill should be used when creating session handoffs, logging research findings, or reading previous trail notes. Triggers include "handoff", "session continuity", "log note", "trail notes", or when ending a session.
Audited 29 - rimagination BundleGood Story
Use when the user asks to find, sharpen, evaluate, rewrite, or explain the story in scientific or scholarly materials across disciplines, including manuscripts, grants, paper outlines, abstracts, figures, results, discussions, cover letters, research pitches, high-impact writing, journal fit, significance, novelty, mechanism, paper logic, or why a result matters.
Audited 148 - compozy BundleCy Create Spec
Create or update a requested CompozyOS spec and its applicable companion contracts, reusing current decisions and research. Not a prerequisite for ordinary coding tasks.
Audited 2.9k - tomevault-io BundleAnswer From Sources
Answers data-protection (GDPR) questions grounded in the regulation and supervisory guidance, with a citation for every claim. Use for questions about personal data, consent, or data-subject rights. Use when this capability is needed.
Audited 1 - tomevault-io BundleNiw National Importance Research
Researches authoritative U.S. government sources, national plans, and policy initiatives to build the national importance argument for an EB-2 NIW petition. Compiles a quotable source document matched to the petitioner's background. Use when this capability is needed.
Audited 1 - holobiomicslab SkillUpset Plot Generation
Use when after loading and filtering search results from two or more DIA-MS analysis tools at a specified Q-value cutoff, when you need to summarize which analytes are identified by all tools, by specific subsets, or uniquely by individual tools.
Audited 16 - holobiomicslab SkillTautomer Standardization
Use when ingesting raw SMILES strings from curated structure inventories where the same chemical may be represented in multiple tautomeric forms (e.g., keto–enol pairs, lactam–lactim forms) across different literature sources or input databases.
Audited 16 - holobiomicslab SkillGroup Comparison Statistics
Use when after data integration, batch correction, and sample separation when you have a feature-by-sample abundance matrix (finalData) and corresponding sample group labels (finalLabel), and your research goal is to identify which metabolites significantly differ between experimental groups for.
Audited 16 - holobiomicslab SkillVendor Format Routing Dispatch
Use when you have a collection of raw mass spectrometry data files from multiple instrument vendors (Agilent, Bruker, Thermo) and/or mzML exports that need to be converted to a standardized, cross-platform format for downstream software development, AI research, or multi-vendor meta-analysis.
Audited 16 - thomasmoreai SkillCitation Format
Normalize messy citation strings ("CVC 23152a", "California Vehicle Code Section 23152(a)") into canonical form ("Cal. Veh. Code § 23152(a)") before passing to harvester-query.
Audited 114 - thomasmoreai SkillHarvester Query
Use whenever the user asks about a motor-vehicle statute, citation, contributing factor, OR a Canadian personal-injury fact pattern — always query Specter's Harvester API before answering. The API auto-routes between two collections (US statutes + Canadian PI case law).
Audited 114 - vamseeachanta BundleMl Paper Writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
Audited 20 - paulasilvatech SkillRepo Story Time
Analyze a Git repository and create two archaeology deliverables: REPOSITORY_SUMMARY.md with technical architecture and THE_STORY_OF_THIS_REPO.md with a narrative from commit history. Use when asked to summarize a repo, explain its architecture, inspect git history, identify contributors, or tell the story of repository evolution.
Audited 21 - ferroxlabs BundleSource Evaluation
Evaluates source credibility and relevance using the CRAAP test (Currency, Relevance, Authority, Accuracy, Purpose) and SIFT method for learners assessing research sources. Produces a completed evaluation with credibility ratings -- not a tutorial on critical thinking. Use when a learner asks to evaluate a source, check if a source is credible, assess research quality, or determine if a source is suitable for academic work. Do NOT use for finding sources (use `literature-search`), for citation formatting (use `citation-management`), or for writing about sources (use `annotated-bibliography`).
Audited 618 - ferroxlabs BundleDropshipping Guide
Complete guide to building a dropshipping business covering product research methodology, supplier vetting processes, store setup, advertising strategy, margin calculations, customer service operations, returns handling, and scaling techniques. Use when the user asks about dropshipping guide or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists.
Audited 618 - plurigrid BundleZeroth Bot
Zeroth Bot - 3D-printed open-source humanoid robot platform for sim-to-real and RL research. Affordable entry point for humanoid robotics.
Audited 72 - ferroxlabs BundleFranchise Evaluation
Guided workflow for evaluating and launching a franchise business from initial research and self-assessment through Franchise Disclosure Document analysis, financing, location selection, and operational launch. Covers the complete franchise investigation process for first-time franchisees. Use when the user wants to franchise evaluation or needs a structured multi-step process for this goal. Do NOT use when the request is a single-step task or requires professional advice beyond educational guidance.
Audited 618 - ferroxlabs BundleClimate Science Explainer
Explains climate science concepts including the greenhouse effect, feedback loops, carbon cycle, evidence types, and climate modeling basics at a level appropriate for non-scientists. Gathers the user's specific question or topic area and produces a structured educational explanation with diagrams in text form and evidence references. Use when the user asks about how climate change works, greenhouse gases, feedback loops, climate evidence, or the science behind global warming. Do NOT use for policy recommendations or advocacy, carbon footprint calculation (use carbon-footprint-estimator), sustainability action planning (use other sustainability skills), or academic research methodology.
Audited 618 - newmindsgroup SkillUxui Principles
Evaluate interfaces against 168 research-backed UX/UI principles, detect antipatterns, and inject UX context into AI coding sessions.
Audited 2 - newmindsgroup BundleCitation Management
Manage citations systematically throughout the research and writing process.
Audited 2 - ferroxlabs BundleNonprofit Grant Writer
Guide to nonprofit and foundation grant writing including prospect research, letters of inquiry, full proposals, budgets, reporting, and funder relationship building. Focused on private foundations, community foundations, and corporate giving programs. Use when the user asks about nonprofit grant writer or needs help with related topics. Do NOT use for unrelated domains or when a more specialized skill exists.
Audited 618 - paulpas SkillSkill Development Workflow
Implements the complete skill creation lifecycle from research through validation, including Python-based quality gates, stub detection, and automated compliance checking against SKILL_FORMAT_SPEC.md requirements.
Audited 10 - nota-america BundleGpt 5 4 Prompting
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
Audited 93 - adu2021 SkillProgressive Citation Grounded Dialogue
Eliminate hallucination via four-stage progressive training: multilingual adaptation → English dialogue SFT → bilingual SFT → GRPO alignment. Achieve 0.0% hallucination rate for encoder-decoder models using structured citation markers and knowledge-source attribution, with automatic transfer of citation format across languages.
Audited 7 - ferroxlabs BundleIndustry Research Framework
Structures deep industry research covering key players, business models, trends, job market dynamics, and entry points. Produces a comprehensive research brief document for career decision-making. Use when the user wants to research an industry before a career move, understand a new market for job targeting, or conduct due diligence on an industry they are considering entering. Do NOT use for company-specific research before an interview (use company-research-guide), competitive analysis for business strategy (use competitive-analysis), or market research for a product (use market-research skills).
Audited 618 - adu2021 SkillOpennovelty Scholarly Assessment
Build agentic systems for transparent, evidence-based novelty analysis of research submissions through four-phase pipelines: contribution extraction, prior work retrieval, hierarchical comparison, and structured reporting with explicit citations—enabling fair peer review at scale.
Audited 7 - nota-america BundleOpenrlhf Training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Audited 93 - cslawyer1985 BundleLegal Review
核验 AI 生成的法律法规和案例引用的准确性。利用元典 Open API 对法规、法条、案例进行逐条比对。当用户提及"复核""核查""核验""验证法律引用""review citation""fact-check legal""verify legal"时,或 AI 生成了包含法律法规、案例时触发。
Audited 926
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 trails, answer-from-sources, planning-with-files. 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.