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.
- mkurman BundleResearch Lookup
Look up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.
Audited 327 - mkurman SkillReview Mining
When the user wants to research customer pain points, complaints, or sentiment using review platforms like Trustpilot, G2, Capterra, or app stores. Also use when the user mentions "what are users saying", "competitor reviews", "pain points", or "voice of customer research".
Audited 327 - mkurman BundleGdm Science Bundle
Vendor of the google-deepmind/science-skills bundle (37 skills for scientific research). Use when a user asks about any of: AlphaGenome single-variant effect analysis (RNA-seq / DNase / ChIP / TF effects, splicing disruption, UBERON/CL ontology resolution for non-coding variants), AlphaFold DB fetch and analyze, ChEMBL bioactivity queries, ClinicalTrials.gov lookups, ClinVar variant interpretation, dbSNP, EMBL-EBI Ontology Lookup Service (OLS4), ENCODE cCREs, Ensembl REST, Foldseek structural search, gnomAD, GTEx, Human Protein Atlas, InterPro, JASPAR transcription-factor profiles, literature search (arXiv / bioRxiv / EuropePMC / OpenAlex), NCBI sequence fetch (EFetch), openFDA, OpenTargets, PDB, protein sequence MSA / similarity search, PubChem, PubMed, PyMOL structural visualization, QuickGO, Reactome, STRING, UCSC conservation & TFBS, UniBind, UniProt, or any workflow combining them. Always read the per-skill SKILL.md under skills/<name>/ and invoke Python only through `uv run`.
Audited 327 - mkurman BundleNeurokit2
Comprehensive biosignal processing toolkit for analyzing 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 327 - s3yed SkillTravel Booking
Research and book multi-leg travel (flights, ferries, trains, buses) via online aggregators using browser tools. Covers itinerary construction, transfer timing, and presenting realistic connection options.
Audited - synthetic-sciences SkillExport
Package results with provenance, reproduction instructions, declared gaps, and the requested output format.
Audited 4.4k - synthetic-sciences SkillReview
Independently review code, results, claims, or an artifact and return prioritized, evidence-backed findings.
Audited 4.4k - aeondave BundleEdr Evasion Dev
Auth/lab dev: Windows + Linux detection-resilience research; syscall dispatch, stack/call-chain spoofing, sleep-state, memory permissions, ETW/AMSI + eBPF/io_uring/LD_PRELOAD telemetry tradeoffs, kernel-visible signals, and cross-platform loader OPSEC with signal-cost budgeting.
Audited 37 - aeondave BundleStack Spoofing Dev
Auth/lab dev: Windows call-stack research; unwind metadata, synthetic frames, NtContinue, thread-pool traces, gadget constraints.
Audited 37 - aeondave BundleIndirect Syscall Dev
Auth/lab dev: Windows syscall-dispatch research; SSN resolution, indirect gates, ntdll stubs, gadget scanning, stack-spoof integration.
Audited 37 - aeondave BundleHeap Exploitation Dev
Auth/lab dev: heap exploitability research; glibc/musl/Windows allocators, UAF/double-free/overflow models, heap shaping, mitigations.
Audited 37 - aeondave SkillSocial Engineering Technique
Authorized simulation: social-engineering methodology; pretexts, email/voice/physical exercises, target research, metrics, scope controls.
Audited 37 - purpleailab SkillWindows Driver Assessment
Defensive Windows internals and driver exposure assessment for owner-authorized systems and disposable research VMs.
Audited 6.6k - purpleailab SkillReverser Virtualized Protectors
VMProtect, VMP2, Themida, and CodeVirtualizer reversing workflow using Radare2/Ghidra facts and Back Engineering Labs research guidance.
Audited 6.6k - netvar1337 BundleEac Ban Stack
EAC/EasyAntiCheat ban-stack research: HWID serials, server-side trust, usermode telemetry, kernel driver signals, FN-class ban discussions.
Audited - xjli360 BundleSealeap Xiezhi Amazon Three Factor Opportunity Screen
Apply a tunable low-volume, higher-price, low-review screen to surface unfamiliar Amazon niches for deeper research. Use when the candidate universe is too large and the user needs a fast, explicitly non-final first pass.
Audited 426 - xjli360 BundleSealeap Xiezhi Amazon Cross Category Attribute Keyword Resea
Use material, feature, audience, occasion, style, and scenario keywords to discover Amazon opportunities across categories. Use when category-first filters are too narrow or the team wants to reuse a supply capability across multiple demand contexts.
Audited 426 - pooriaarab SkillKnowledge Organization
Use when the user wants to organize their knowledge, files, or notes across multiple platforms (local, iCloud, Google Drive, Notion, GitHub, Notes app). Triggers: 'organize my knowledge', 'second brain', 'unified folder structure', 'sync iCloud and Drive', 'context graph', 'personal knowledge base', 'everything in sync'.
Audited 1 - iamwaqargulzar BundleVoice Dossier Builder
Use when the user asks to "codify how our founder sounds", "build a founder voice dossier", or "set our content pillars"; runs an 80%-extraction interview over the user's OWN posts, emails, and decks (never competitor scraping, never an invented persona) and produces the versioned voice record — a per-platform register map (incl. 小红书/微信公众号), banned phrases, per-context disclosure lines (the ECHO C2 upstream), a few-shot bank built exclusively from own posts, and 3-5 content pillars with Estimated %-allocations — submitted via memory/events/channels.ndjson for channel-registry to store as voice-dossier.md, the record every Craft-phase skill reads first. Not for the brand-level voice canon — use brand-language-codifier; not for audience/persona research — use audience-mapper. 声音档案/品牌语气/创始人语气/内容支柱/披露声明
Audited 8 - iamwaqargulzar BundleDomain Authority Auditor
Use when auditing domain authority, trust, or citation credibility; runs a peer-relative 40-item CITE profile with evidence coverage and verified manipulation/penalty veto checks. Not for page-level content quality — use content-quality-auditor; not for backlink profiling alone — use offsite-signal-analyzer. 域名权威/网站可信度
Audited 8 - deciqai BundleDeep Work
Activate when: user says 'I can never find time for focused work', 'I feel busy but produce nothing', 'I keep getting interrupted', 'I want to protect my focus time', 'flow state', 'deliberate practice', 'Cal Newport', or asks how to make progress on hard cognitive work (research, writing, engineering, strategy). Do NOT activate when: the role is genuinely high-coordination with no discrete focus windows (ER medicine, real-time trading desk), or user is in a short-term emergency where availability must dominate. More: deciqai.com/s/deep-work
Audited 14 - argentaios SkillArgentos Project Credibility Review
Evaluate a startup/open-source project or AI product by cross-checking the website narrative against repositories, docs, demos, activity, and implementation evidence. Use when the user asks what you think of a product/project URL, especially if it has GitHub links or open-source claims.
Audited 128 - sam6dvpte34 SkillLinkedin Event Scraper
Collect event details and attendee leads from LinkedIn — event name, date, host, attendees, contact signals. Use when the user wants to prospect event attendees or monitor industry events.
Audited 7 - lamm-mit BundleCommodity Profile
Generate comprehensive one-page commodity profiles with production, trade, risk, research, policy, and web intelligence data
Audited 251 - sam6dvpte34 SkillShopify Store Lead Builder
Collect Shopify store leads from Shopify — store URL, niche, products, contact signals. Use when the user wants to build a list of Shopify stores for outreach or research.
Audited 7 - sam6dvpte34 SkillShopify Storefront Scraper
Collect storefronts from Shopify — store name, branding, featured products, ratings. Use when the user wants to research brand storefronts or competitive assortment.
Audited 7 - sam6dvpte34 SkillTiktok Shop Seller Scraper
Collect seller data from TikTok Shop. Use when the user wants to research or export seller content.
Audited 7 - sam6dvpte34 SkillEcommerce Storefront Scraper
Collect storefront data from any ecommerce site — store name, featured products, ratings. Use when the user wants to research a brand storefront or competitive assortment.
Audited 7 - sam6dvpte34 SkillYahoo Auctions Japan Scraper
Collect scraper data from Yahoo Auctions Japan. Use when the user wants to research or export scraper content.
Audited 7 - sam6dvpte34 SkillNaver Shopping Review Scraper
Collect reviews from Naver Shopping — text, rating, author, date, verified status. Use when the user wants to collect reviews for sentiment analysis or quality research.
Audited 7 - sam6dvpte34 SkillConsumer Affairs Review Scraper
Collect reviews from ConsumerAffairs — text, rating, author, date, verified status. Use when the user wants to collect reviews for sentiment analysis or quality research.
Audited 7 - sam6dvpte34 SkillAmazon Price Availability Monitor
Collect price availability monitor data from Amazon. Use when the user wants to research or export price availability monitor content.
Audited 7 - sam6dvpte34 SkillEcommerce Question Answer Scraper
Collect Q&A threads from any ecommerce product page — questions, answers, author, helpful votes. Use when the user wants customer Q&A for product or content research.
Audited 7 - sam6dvpte34 SkillTiktok Shop Creator Affiliate Scraper
Collect TikTok Shop creator affiliates from TikTok Shop — creator name, followers, niche, affiliated products. Use when the user wants to find TikTok Shop creators for affiliate or partnership research.
Audited 7 - daemon-blockint-tech BundleCustomer Ops Specialist
Manage customer operations across success, support, and revenue operations. Cover customer onboarding, health scoring, renewal management, ticket triage, SLA management, knowledge base development, billing operations, dunning, refunds, and customer metrics. Triggers on "customer onboarding", "support ticket triage", "billing inquiry", "churn analysis", "health score", "SLA management", "dunning process", "customer success playbook", "renewal management", "CSAT review", or "customer ops". Exec/VIP and public community escalation program: community-executive-escalations-program-manager. Monetization product (pricing, paywalls): product-management-monetization.
Audited 14 - mariourquia BundleReforecast
Produces a reforecast that inherits actuals through the as-of month, preserves or revises forward-looking assumptions with citation, and surfaces the delta vs. budget and vs. prior forecast. Includes forecast-accuracy calibration and NOI sensitivity.
Audited 51
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 travel-booking, knowledge-organization, deep-work. 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.