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 Ralph Specum ResearchThis skill should be used only when the user explicitly asks to use `$ralph-specum-research`, or explicitly asks Ralph Specum in Codex to run the research phase.
567 -
majiayu000 Bundle Research Gap Analyzerプロジェクト プロジェクトの機能(docs/features/)とリサーチ(docs/research/)文書を分析し、高収益/高LTV/低離脱達成のためのリサーチギャップを識別し、欠落したP0/P1リサーチを自動実行する。
567 -
majiayu000 Bundle Bioinformatics ExperimentThis skill should be used when conducting bioinformatics research, planning experiments, running analyses, or managing scientific projects. Triggers include requests like "研究を始める", "実験する", "新しい実験を計画", "Start research", "Plan experiment", "Run analysis", or "What's the current research status?".
567 -
majiayu000 Bundle Doc Research ImprovementsResearch-driven critique and enhancement of Amelia architecture or ideas docs. Use with GPT-5.2 when given a design/architecture doc to analyze concepts, find sources, and propose improvements plus OSS candidates.
567 -
majiayu000 Bundle Full Video Workflow SkillComplete pre-production workflow that chains research, project creation, script generation, and presentation in one seamless flow. Use when starting a new video from competitor research all the way through to a ready-to-record script.
567 -
majiayu000 Bundle Hypothesis Testing EngineTake any claim and design + execute a complete research protocol to test it. Apply scientific method automatically: design study, gather data, run analysis, provide verdict with confidence level.
567 -
majiayu000 Bundle Implementation CheckpointGenerate standardized checkpoint reports for multi-phase implementation projects. This skill should be used when pausing implementation at strategic milestones (phase completion, user story completion, critical features) to create comprehensive progress reports with task breakdowns, metrics, knowledge base entries, and resume instructions.
567 -
majiayu000 Bundle Perplexity Researcher ProComplex research requiring deeper analysis, multi-step reasoning, and sophisticated source evaluation for technical, academic, or specialized domain queries needing expert-level analysis, high-stakes decisions, or multi-layered problem solving.
567 -
majiayu000 Bundle Pubmed Gene Drug Research使用 NCBI 擴展資料庫(Gene、PubChem、ClinVar)進行基因功能、藥物化合物、遺傳變異的跨資料庫研究。
567 -
majiayu000 Bundle Recruitment Source FinderThis skill should be used when users need to find relevant sources from the sources.md knowledge base for recruitment-related topics. Parses and filters the comprehensive sources.md file to return targeted sub-lists of resources based on topic queries, making research more efficient.
567 -
majiayu000 Bundle Ref Development StandardsCore development principles for Plan-Marshall projects - when to ask users, research best practices, tool usage, and dependency management
567 -
majiayu000 Bundle Requirement ClarificationGenerate clarifying questions from research findings. MUST be used before planning phase. Validates requirements are complete and unambiguous before technical work begins.
567 -
majiayu000 Bundle Research And Fact CheckerPerforms accurate research and fact-checking using reliable sources. Ideal for validating claims, clarifying complex topics, summarizing findings, and ensuring information accuracy.
567 -
majiayu000 Bundle Research Question RefinerHelps transform a vague research interest into a concrete, tractable research question. Use when asked to refine a research idea, develop a research question, scope a research project, or figure out what to work on. Walks through systematic refinement with feasibility analysis.
567 -
majiayu000 Bundle Ruby On Rails DevelopmentRails skills router and knowledge base. Routes your request to the appropriate specialist skill. Contains core Rails principles and conventions. Use when unsure which specialist to choose or for general Rails questions.
567 -
majiayu000 Bundle Skills Proficiency MapperProficiency calibration specialist to plan skill progression the way a civil engineer thinks about load-bearing capacity—**measured, validated, and progressive**, by applying 40+ years of CEFR research, 70+ years of Bloom's taxonomy, and modern DigComp frameworks to create internationally recognized, measurable proficiency progressions.
567 -
majiayu000 Bundle Specstory Session SummarySummarize recent SpecStory AI coding sessions in standup format. Use when the user wants to review sessions from .specstory/history, prepare for standups, track work progress, or understand what was accomplished.
567 -
majiayu000 Bundle User Feedback InterpreterComprehensive UX research assistant that analyzes user feedback from surveys, reviews, and interviews to identify trends, cluster themes, surface friction points, and generate actionable product roadmaps. Use when analyzing user feedback, conducting UX research, evaluating product performance, prioritizing features, or transforming qualitative/quantitative feedback into strategic insights.
567 -
majiayu000 Bundle Using Perplexity PlatformPerplexity Sonar API development with search-augmented generation, real-time web search, citations, and OpenAI-compatible Chat Completions. Use for AI-powered applications requiring up-to-date information, research assistants, and grounded responses with sources.
567 -
majiayu000 Bundle Implementing TasksImplements tasks from .plans/ directories by following implementation guidance, writing code and tests, and updating task status. Use when task file is in implementation/ directory and requires code implementation with comprehensive testing. Launches research agents when stuck.
567 -
majiayu000 Bundle Method DevelopmentDesign and iterate on new research methods with structured checkpoints, baselines, and validation.
567 -
majiayu000 Bundle Chatkit Backend AdapterModify OpenAI ChatKit starter to use FastAPI backend instead of OpenAI API, including citation support and error handling.
567 -
majiayu000 Bundle Create Release NotesGenerate user-facing release notes when the user asks to write release notes, document a release, summarize changes for users, or prepare a changelog between versions
567 -
majiayu000 Bundle Video Podcast MakerUse when the user gives a topic and wants an automated video podcast created, or asks to learn visual design patterns from a reference video/image. Produces 4K video via research → script → TTS → Remotion → MP4 + BGM.
567 -
majiayu000 Bundle Claude Code ActionKnowledge base for creating and configuring Claude Code Action GitHub workflows
567 -
majiayu000 Bundle Fractal ThinkingAdaptive recursive thought engine for deep exploration. Invoked by other skills (brainstorming, fact-checking, debugging, deep-research) when they need to deeply explore uncertainty, systematically decompose complex questions, or gain certainty about multi-faceted problems. Triggers: "think deeply about", "explore this recursively", "I need certainty about", "decompose this question", "what am I missing". Also invoked programmatically with a seed, intensity, and checkpoint mode. NOT for: simple questions with known answers, linear task execution, or file-by-file code review.
567 -
majiayu000 Bundle Comprehensive EnrichmentEnrich any person or company from any identifier — email, name, LinkedIn URL, domain, company name, Twitter/X handle. Use when asked to enrich, look up, or research a lead, contact, person, or company.
567 -
majiayu000 Bundle Domain Authority AuditorUse when auditing domain authority, trust, or citation credibility; runs 40-item CITE scoring with veto checks (TRUSTED/CAUTIOUS/UNTRUSTED). Not for page-level content quality — use content-quality-auditor; not for backlink profiling alone — use backlink-analyzer. 域名权威/网站可信度
567 -
majiayu000 Bundle Nw At Completeness CheckCanonical AT completeness gate — research-anchored 7-category taxonomy (C1-C7) + 15-item mechanical checklist. Paradigm-neutral. Drives acceptance-designer reviewer verdict deterministically.
567 -
majiayu000 Bundle Account Research BriefUse when preparing to engage a target account, researching a company before outreach, or building pre-call intelligence. Triggers: 'research this company', 'account brief for [company]', 'company research', 'what do I need to know about [company]', 'pre-outreach research'.
567 -
majiayu000 Bundle AI Creative StrategistResearch-powered creative strategy with visual previews. Use when you need to figure out WHAT to create before creating it. Researches competitors, captures references, generates visual direction previews, and outputs comprehensive briefs. Triggers on: creative strategy, what visuals should I create, creative brief, visual direction. Outputs briefs with actual preview images for feedback.
567 -
majiayu000 Bundle Generate Stock ReportsGenerates comprehensive reports on recent company developments using web search. Use when analyzing stocks, researching companies, evaluating investments, or when users mention company names, stock tickers, market analysis, or financial research.
567 -
majiayu000 Bundle Tracking Research GapsManages research gaps and needed information. Use when user says 'show research gaps', 'what research do I need', 'track research needs', or after drafting chapters that contain [RESEARCH: ...] markers.
567 -
majiayu000 Bundle Technical Debt ManagerAnalyze repo for technical debt, research language-specific best practices, create prioritized GitHub issue
567 -
majiayu000 Bundle Update Dotfiles TrendsResearch latest trends in dotfiles, tooling, and suggest improvements
567 -
majiayu000 Bundle Apa Citation GeneratorGenerates accurate APA 7th edition reference list entries and in-text citations from bibliographic details, URLs, or quoted text.
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 ralph-specum-research, research-gap-analyzer, bioinformatics-experiment. 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.