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 Plan Findings ResumeTriage findings from a plan into issues and research. Reads findings/ from a plan directory, decides what becomes an issue or research update, and writes them to the appropriate locations.
567 -
majiayu000 Bundle Pr Review ExtractionExtract and summarize review comments from GitHub PRs. Use when analyzing PR reviews, checking unresolved issues, or responding to CodeRabbit feedback.
567 -
majiayu000 Bundle Project OrganizationExpert guidance for setting up and organizing research software projects following Sam Abbott's established patterns for R packages, Julia packages, and research projects
567 -
majiayu000 Bundle Research MethodologyEthan Perez's tips for empirical alignment research - velocity, experimentation, collaboration
567 -
majiayu000 Bundle Gsd Research SynthesizerSynthesizes research outputs from parallel researcher agents into SUMMARY.md. Spawned by /gsd:new-project after 4 researcher agents complete.
567 -
majiayu000 Bundle Researchers VerifierQuality control, citation validation, fact-checking before human review
567 -
majiayu000 Bundle Researching CodebaseThis skill should be used when the user asks to "research the codebase", "understand how X works", "explore the code", "gather context", "investigate the implementation", "analyze the architecture", or invokes the rpikit:research command. Provides methodology for thorough interrogation and codebase exploration before planning or implementation.
567 -
majiayu000 Bundle Reviewer 2 SimulatorCritiques your paper draft as a skeptical reviewer would. Use when asked to review a paper draft, find weaknesses in a paper, prepare for peer review, anticipate reviewer criticism, or stress-test research before submission. Identifies weak claims, missing baselines, unclear explanations, and overclaims.
567 -
majiayu000 Bundle Rpi Setup Humanlayeruse this skill when a user asks to set up RPI or a "research plan implement" workflow, or to do anything related to RPI skills. if the user says the acronym "RPI" or "rpi" or "humanlayer", you MUST use this skill! Example questions - "I want to set up rpi for ticket eng-1234" - "Whats the next rpi step for eng-5678"
567 -
majiayu000 Bundle Synthesis FrameworksMaster research synthesis including qualitative analysis, affinity diagramming, theme identification, pattern recognition, and insight extraction. Use when synthesizing research, analyzing interviews, identifying patterns, extracting insights, organizing findings, or translating research into action. Covers synthesis methods, affinity mapping, thematic analysis, and insight generation techniques.
567 -
majiayu000 Bundle Troubleshooting DocsCapture problem solutions in searchable knowledge base
567 -
majiayu000 Bundle Video Research SkillAnalyze YouTube videos to generate viral video ideas and scripts. Use when given YouTube URLs to research, when asked to analyze competitors, generate video ideas from existing videos, or create a script based on what works. Accepts 1-10 YouTube video links.
567 -
majiayu000 Bundle Opinion SummarySummarizes U.S. transactional legal opinions into executive-ready briefs preserving issues, analysis, conclusions, qualifications, and key authorities. Triggers when asked to summarize a legal opinion, opinion memorandum, legal analysis memo, or produce an executive opinion recap.
567 -
majiayu000 Bundle AI Research AnalystProduces executive-level research — market sizing, competitor mapping, trend analysis, and strategic intelligence — grounded in cited sources with the confidence in each claim made explicit. Use this to analyze a market or industry, map competitors, evaluate a market-entry or build-versus-buy decision, produce a research brief, or assemble evidence for a decision. Also use when comparing options that need a structured, evidence-based verdict rather than an opinion.
567 -
majiayu000 Bundle Content RepurposingUse when the user wants to turn public social videos, transcripts, posts, or creator research into reusable content assets such as LinkedIn posts, X threads, short-form scripts, newsletters, blog outlines, carousels, or content calendars.
567 -
majiayu000 Bundle Longbridge ResearchInstitution ratings, consensus price targets, EPS/revenue forecasts, finance calendar, shareholder data, fund holders, insider trades (SEC Form 4), short interest, industry rankings, peer group analysis via Longbridge. Frameworks: investment proposals, coverage initiation, stock research, competitive analysis, financial planning, and DeFi/on-chain analysis. Triggers: "机构评级", "目标价", "一致预期", "EPS预测", "内部人交易", "空头", "行业排名", "投资提案", "首次覆盖", "竞争格局", "财务规划", "DeFi收益", "链上数据", "機構評級", "目標價", "一致預期", "內部人交易", "空頭", "投資提案", "首次覆蓋", "競爭格局", "鏈上數據", "analyst rating", "price target", "consensus", "insider trades", "short interest", "coverage initiation", "DeFi yield", "on-chain", "earnings calendar", "finance calendar", "财报日历", "下周谁财报", "下周财报", "下周有哪些财报", "哪些财报", "谁财报", "FOMC", "非农", "股东", "谁持有", "股東", "基金持仓", "基金持倉", "機構評級", "目標價", "財務規劃"
567 -
majiayu000 Bundle Video UnderstandingAnalyze a video into a structured understanding index: scene detection, ASR transcript, per-scene visual (VLM) analysis, silence windows, a fused timeline, and a narration-writing brief. Use to understand / index / summarize what happens in a video, or as the first stage of the video-recap bundle before writing narration. Input: a video file. Output: scenes.json, asr_result.json, vlm_analysis.json, silence_periods.json, timeline_fusion.json, agent_narration_brief.md. 触发词: 视频理解, 视频分析, 视频索引, video understanding, analyze video, 看懂视频.
567 -
majiayu000 Bundle Analyze EquationsParse and interpret mathematical equations from research papers. Use when extracting formulas for implementation.
567 -
majiayu000 Bundle Research 150Deep research workflow for this project using 150% scope (100% core + 50% boundary), evidence-based reasoning, and structured investigation notes. Use when the task requires investigation, root-cause analysis, or mapping unknown areas. Always maintain a research log file that captures findings, hypotheses, and next branches; use web.run when external verification is needed.
567 -
majiayu000 Bundle Shipflow EndEnd a task — summarize what was done, mark task done in TASKS.md, update CHANGELOG.md. Does NOT commit or push. Use when finishing a task but not ready to ship.
567 -
majiayu000 Bundle Phase TransitionTransition between session phases (RESEARCH → PLAN → IMPLEMENT → REVIEW → VERIFY)
567 -
majiayu000 Bundle Specsafe ExplorePre-spec exploration. Research and spike before creating formal spec.
567 -
majiayu000 Bundle Writing Hugo BlogCreate Hugo blog posts in Chinese. Triggers when user asks to write a blog post, create a draft article, or convert research into blog format. Follows a structured workflow: explore blog config, understand content formats, gather topic requirements, generate draft, and review writing quality.
567 -
majiayu000 Bundle Youtube CompanionWrite Substack newsletters that accompany YouTube videos. Use when user has a YouTube video (transcript, outline, or link) and needs the companion newsletter with video embed, summary sections, and resources. Different from standalone newsletters - these drive to and summarize video content.
567 -
majiayu000 Bundle Analyzing Kb GapsUse when you have Knowledge Base exports and want to identify user pain points, missing articles, and AI assistance opportunities.
567 -
majiayu000 Bundle Cultural ResearchUse this to autonomously populate Martinique_DB. Takes a cultural topic from the 6 CoT circles, runs a deep research loop using gpt-researcher or web search, structures findings into DB-ready entries, and loops until coverage is sufficient.
567 -
majiayu000 Bundle Document ResearchDeep search, synthesis from knowledge base
567 -
majiayu000 Bundle Fieldwork MethodsField observation, data collection, and research methods for geographic inquiry. Covers site selection and sampling strategies, field observation techniques (landscape reading, transects, quadrats), survey and interview methods for human geography, GPS and field mapping, environmental monitoring and instrumentation, data recording and field notebooks, ethical considerations in fieldwork, and the integration of field data with GIS analysis. Use when planning geographic field research, designing data collection protocols, evaluating field evidence, or connecting field observations to broader geographic analysis.
567 -
majiayu000 Bundle Open Source LibrarianResearch external libraries with evidence-backed responses and GitHub permalinks. Use when investigating library APIs, implementation patterns, or historical context for open source dependencies.
567 -
majiayu000 Bundle Optimization ModelingWhen the user wants to build optimization models, solve mathematical programming problems, or find optimal solutions. Also use when the user mentions "linear programming," "integer programming," "mixed-integer programming," "constraint optimization," "mathematical optimization," "operations research," "optimal solution," or "decision optimization." For network design specifically, see network-design. For routing, see route-optimization.
567 -
majiayu000 Bundle Pacer Learning SystemA learning methodology skill based on Dr. Justin Sung's PACER system for effective information retention and application. Use when helping users (1) learn new material efficiently, (2) take notes or summarize content, (3) create study plans, (4) review or memorize information, (5) understand how to retain knowledge better, or (6) process educational content like books, lectures, courses, or articles.
567 -
majiayu000 Bundle Pokemon Deck BuilderUse when building, analyzing, or optimizing Pokemon TCG Pocket decks. **Activates when user mentions:** - Deck building ("build a deck", "create deck") - Deck analysis ("analyze my deck", "check deck") - Synergy finding ("what works with X", "synergies") - Optimization ("improve my deck", "fix my deck") - Energy calculations ("energy curve", "energy needs") **Provides:** Complete deck construction with validation, energy curve analysis, synergy recommendations, and optimization suggestions. References proven deck archetypes and meta strategies from comprehensive research. **Key benefit:** Legal, optimized, competitive-ready 20-card decks with detailed strategy explanations and improvement recommendations.
567 -
majiayu000 Bundle Production API TesterLive testing and validation of production research API for strategy optimization loops
567 -
majiayu000 Bundle Research BrainstormerTransform research ideas into actionable experiments with hypotheses, iteration rewards, and completion criteria. Use when brainstorming experiments, designing research plans, converting vague ideas into structured plans, or needing fast feedback signals for implementation. Triggers on phrases like "brainstorm experiments", "design an experiment", "what should I test", "turn this idea into an experiment", or "help me plan research".
567 -
majiayu000 Bundle Research Fact CheckerResearch topics, verify facts, check historical accuracy, and validate technical details. Use when writing non-fiction, historical fiction, or any content requiring factual accuracy.
567 -
majiayu000 Bundle Research Git PatternsGit-aware skill for finding implementation patterns and retrieving story context from git history. Use when searching for similar implementations or understanding how a feature was built. To use this skill, you must have a story ID (e.g., "US-001-auth-login-admin"). Use research-user-stories skill to find the story ID.
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 pacer-learning-system, plan:findings:resume, pr-review-extraction. 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.