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.
-
majiayu000 Bundle Nw Diverger Review CriteriaReview criteria for the nw-diverger-reviewer — validates JTBD rigor, research quality, option diversity, taste application correctness, and recommendation coherence in DIVERGE wave artifacts
567 -
majiayu000 Bundle Research First DevelopmentBuild knowledge bases that build software — research before code, teach before execute
567 -
majiayu000 Bundle Zenn Context Driven WritingUse when preparing context and drafts for experience-based Zenn articles. Parallel research + context file pattern.
567 -
majiayu000 Bundle Deep Research API LandscapeUse when building automated research systems. Official Deep Research APIs (OpenAI, Gemini, Perplexity) over browser automation.
567 -
majiayu000 Bundle Research Proposal GeneratorGenerates a comprehensive research proposal design based on input literature, including hypothesis, mechanism verification, and budget. Use when the user wants to design a research project from a paper.
567 -
majiayu000 Bundle Fda DatabaseQuery openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
567 -
majiayu000 Bundle Citation Bibliography GeneratorFormat citations in APA, MLA, Chicago, IEEE, Harvard styles from structured data, DOI/ISBN lookup, or manual entry. Generate bibliographies with auto-sort.
567 -
majiayu000 Bundle Nsfc Research Foundation Writer为 NSFC 正文"(三)研究基础"写作/重构,并同步编排"工作条件"和"研究风险应对",用证据链证明项目可行、资源条件对位研究内容、风险预案可执行。适用于用户要写/改"研究基础、前期工作、可行性分析、工作条件、平台团队、风险应对"等场景。
567 -
majiayu000 Bundle Petase 2024 2025 Literature ScanUse PubMed & Scholar Gateway to extract PETase (and PET hydrolase) variants and effects from 2024–2025 papers into a standardized table with citations.
567 -
majiayu000 Bundle Political Attack NeutralizationNeutralize workplace political attacks using the MOAR framework from Gartner research
567 -
majiayu000 Bundle Obsi Knowledge HarvesterStandards for migrating topic notes from Projects/Inbox to the Knowledge Base.
567 -
majiayu000 Bundle Zettelkasten MethodologyComplete guide to Zettelkasten note-taking methodology. Use when creating notes, establishing connections, or building knowledge management systems in Obsidian. Covers atomic notes, literature notes, MOCs, and linking strategies.
567 -
majiayu000 Bundle Github Issue And Pr WorkflowList and search issues, PRs, commits; summarize status and reviews
567 -
majiayu000 Bundle QverisFind third-party APIs and connect to them in code to assist users in various fields such as finance, economics, healthcare, sports, scientific research, and more
567 -
majiayu000 Bundle 00 Meta Chain Flow 150[00] META. Orchestrate skills into dynamic chains for complex tasks. Analyzes the task, discovers available skills, builds an optimal chain, explains why each skill is needed, and executes step-by-step with user confirmation. Use for any complex task requiring multiple thinking/research/analysis steps. Triggers on "plan this", "how to approach", "what's the strategy", "build a plan", or any multi-step problem requiring skill orchestration.
567 -
majiayu000 Bundle Tiktok Shop Product ResearchProduct research for TikTok Shop — viral potential scoring, creator demand, category analysis
567 -
majiayu000 Bundle Self HealAutonomous diagnose-research-fix-verify loop — up to 5 attempts before human escalation
567 -
majiayu000 Bundle Walkeros Create DestinationUse when creating a new walkerOS destination. Example-driven workflow starting with research and examples before implementation.
567 -
majiayu000 Bundle Competitive Account ResearchGenerate a comprehensive account brief by combining company enrichment, decision-maker mapping, and engagement history from Amplemarket.
567 -
majiayu000 Bundle Scientific Problem SelectionThis skill should be used when researchers need help with research problem selection, project ideation, troubleshooting stuck projects, or strategic research decisions. Use this skill when users ask to pitch a new research idea, work through a project problem, evaluate project risks, plan research strategy, navigate decision trees, or get help choosing what research problem to work on. Typical requests include "I have an idea for a project", "I'm stuck on my research", "help me evaluate this project", "what should I work on", or "I need strategic advice about my research".
567 -
majiayu000 Bundle Context ContinuityHigh-fidelity context transfer protocol for moving conversations between AI agents. Preserves decision tempo, open loops, and critical context with graceful degradation. Use when the user says "transfer," "handoff," "continue this in another chat," or needs to work around context window limits. Produces structured artifacts (Minimal ~200 words, Full ~1000 words). DO NOT trigger on simple "summarize our conversation" requests—only when transfer intent is explicit.
567 -
majiayu000 Bundle Knowledge CurationContext priming before work (bd prime) and self-reflection after completion to extract patterns, gotchas, and decisions into the knowledge base.
567 -
majiayu000 Bundle Blockchain Rpc Provider ResearchSystematic workflow for researching and validating blockchain RPC providers. Use when evaluating RPC providers for historical data collection, rate limits, archive access, compute unit costs, or timeline estimation for large-scale blockchain data backfills.
567 -
majiayu000 Bundle RecoveryWorkflow recovery protocol for resuming workflows after context loss, session interruption, or errors. Handles state reconstruction, artifact recovery, and seamless workflow continuation.
567 -
majiayu000 Bundle Biomedical Science WriterDraft biomedical research manuscripts from research data. Use when user wants to write a research paper, has a project folder with papers, data, figures, and a GitHub repository link. Orchestrates context-ingestion, scoping, literature-review, code-analyzer, results-interpreter, synthesis, and assembler sub-skills.
567 -
majiayu000 Bundle General Development RulesCore development principles for CUI projects - when to ask users, research best practices, tool usage, and dependency management
567 -
majiayu000 Bundle Github Prior Art ResearchWhen asked implementation questions or tool selection questions like "how do I implement", "what's the best way to", "how should I", "which library", "what tool should I use", or "how might we", search GitHub for prior art, code examples, and proven approaches before proposing solutions
567 -
majiayu000 Bundle Nutrition Science FoundationsFoundational concepts in nutrition science — macronutrients, micronutrients, energy balance, Atwater factors, reference intakes (DRI/RDA/AI/UL), food composition tables, and the methods of human nutrition research. Grounds the rest of the department in a shared vocabulary and in the measurement limits of the field, including controlled-trial history, observational-study limits, and the biochemical basis for calorie accounting. Use when a question asks what something "is" nutritionally, how energy and nutrients are measured, or what the reference numbers mean.
567 -
majiayu000 Bundle Scientific Podcast SummaryAutomatically summarize scientific podcasts like Huberman Lab and Nature Podcast
567 -
majiayu000 Bundle Things Week Ahead DigestSummarize Things todos and recommend next actions using recent activity across projects, areas, and checklist-like notes, plus a week/weekend-ahead preview. Use when asked for Things planning digests, productivity check-ins, weekly previews, or automation that turns Things data into concise priorities.
567 -
majiayu000 Bundle Ln 312 Review Findings WorkerUse when an evaluation coordinator needs normalized findings from target artifacts and research evidence.
567 -
majiayu000 Bundle Multi Source Signal SynthesiserSynthesises user signals from multiple research sources into a unified, weighted insight brief. Use when you have data from interviews, support tickets, NPS verbatims, app reviews, or sales calls and need to reconcile contradictions, surface the underlying need behind requests, or answer 'what are users really telling us'. Produces ranked insights with confidence ratings, source weighting rationale, divergent signal analysis by user segment, and a research gap identification section.
567 -
majiayu000 Bundle Elite Longterm MemoryUltimate AI agent memory system. Combines bulletproof WAL protocol, vector search, git-based knowledge graphs, cloud backup, and maintenance hygiene. Never lose context again. For Clawdbot, Moltbot, Claude, GPT agents.
567 -
majiayu000 Bundle Vibe Session Context FlushPerforms smart context summarization when the context window is approaching capacity. Identifies what to keep, what to summarize, and creates a compact resume state.
567 -
majiayu000 Bundle Experimental Research MetacognitionDo experiment-driven research (hypotheses → minimal repros → evidence) and continuously improve research skills + tooling. Use when behavior is uncertain, contested, or performance-sensitive.
567 -
majiayu000 Bundle City Tourism Website BuilderResearch and create modern, animated tourism websites for cities with historical facts, places to visit, and colorful designs.
567
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 competitive-account-research, research-first-development, zenn-context-driven-writing. 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 skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.