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.
- xjtulyc SkillSystematic Review
Use this Skill when conducting a systematic literature review following PRISMA 2020: PICO framework, database search strategy, title/abstract screening, full-text eligibility, data extraction, and GRADE evidence grading.
Audited 35 - dreamlab-ai BundleCodex Companion
OpenAI Codex / GPT-6 Astra integration for Claude Code. Use when the user says "consult with openai", "talk to codex", "ask gpt-6", "get a second opinion from openai", "delegate to codex", "openai review", or "codex rescue". Provides code reviews, adversarial reviews, rescue operations (when Claude is stuck), and GPT-6 Astra task delegation with structured prompting. Runs the baked Codex CLI under the current profile; auth resolves from ~/.codex ([consultants.codex]) wired by the entrypoint. NOT for non-code tasks (research/content/design → dedicated skills), simple one-off edits Claude can finish alone, or DeepSeek reasoning (→ deepseek-reasoning). From openai/codex-plugin-cc.
Audited 23 - conectlens BundleMobile App Product Owner
Use when planning mobile app features, roadmaps, or research-backed product decisions for apps/mobile.
Audited 18 - coco-research SkillPmstudio Changelog
Create or update a structured change log for a product or platform. Use when someone asks to "create a change log", "log this change", "what changed", "update the change log", "release notes", or "changelog". Reads project memory (CLAUDE.local.md Recent Changes) and meeting notes to build chronological change records. Supports init (backfill from memory), update (append new entries), and release (summarize for a version).
Audited 631 - plamentsv SkillCross Chain Timing
Type Thought-template (instantiate before use) - Research basis Multi-block arbitrage windows, bridge latency exploitation
Audited 315 - benbrastmckie SkillSkill Physics Research
Research physics formalization tasks using domain context and codebase exploration. Invoke for physics-language research involving dynamical systems, chaos theory, and related formalization.
Audited 446 - peterbamuhigire Bundle10 AI Hallucination Slo Doc
Use when defining an AI hallucination SLO for factuality, citation validity, abstention, severity, sampling, error budget, and release response; use saas-slo-and-error-budget-doc for ordinary service reliability.
Audited 31 - starchild-ai-agent Skill6522 Employee Mode
Work as the user's analyst in the established Giles mode: execute requested research, drafting, analysis, and follow-through while accepting direct management and career coaching. Use when the user asks for Giles, employee mode, an analyst deliverable, delegated execution, progress reporting, or feedback framed for a talented junior employee.
Audited 33 - malekokour BundleReview Uspi Section 2 Dosing
Reviews US prescribing information Section 2 dosing content against the evidence behind it, in both directions. It traces every dose adjustment to a supporting exposure finding and checks direction and magnitude rather than the presence of a citation, then runs the reverse check that finds the real defects - exposure findings with neither an instruction nor an explicit statement that no adjustment is needed. It also checks administration conditions against the biopharmaceutics evidence and compares the Highlights dosing summary against the full section. Use it for draft or approved Section 2 content, or a proposed dosing change. Example: "Please draft or approved Section 2 content." Do not use for Section 12 content, for Section 7 interaction entries, for registration dose justification, for non-US labels, for drafting wording, or to select or approve any dose or adjustment.
Audited 6 - archsightlabs SkillCogp Sushi
通达中文表达(苏轼) / Expansive Chinese expression (Su Shi)。用于在困境、转折和复杂议题中保持开阔、亲近、弹性和中文表达气韵。
Audited 29 - archsightlabs SkillCogp Orwell
清晰写作(奥威尔) / Clear writing (Orwell)。用于去除空话、委婉遮蔽、抽象堆叠、政治化语言和表达诚实性。
Audited 29 - archsightlabs SkillCogv Simaqian
司马迁口吻 / Sima Qian voice。用于人物、转折、成败因果和有分寸历史评判的风格化表达。
Audited 29 - archsightlabs SkillCogv Caoxueqin
曹雪芹口吻 / Cao Xueqin voice。用于细腻关系、暗线、盛衰感和含蓄中文叙事的风格化表达。
Audited 29 - archsightlabs SkillCogp Qian Zhongshu
类比与反讽(钱钟书) / Analogy and irony (Qian Zhongshu)。用于识别互文、错配类比、知识炫耀、表达反讽和高阶写作分辨。
Audited 29 - minimax-ai BundlePaper Search
当需要真正执行文献数据库 API 检索时加载:构建检索式(布尔组合、字段限定)、 调用 OpenAlex / Crossref / arXiv 接口、遵守请求礼仪(限速、UA、指数退避)、 把返回解析为统一 PaperDocument。通常由 literature-search 调用,不直接面向用户。 同义场景:检索执行、API 查询、文献接口调用、query 构建、检索脚本运行、 接口限速与重试、检索结果解析。
Audited 13.8k - minimax-ai SkillResearch Lifecycle
当用户提出研究主题、想开始一项新研究、问"接下来该做什么"、或要求继续上次的研究流程时使用。本技能是科研工作台的元路由器:把一个研究主题拆解为 question(问题界定)→ literature(文献调研)→ hypothesis(假设形成)→ experiment(实验/计算)→ analysis(数据分析)→ writing(写作成稿)六个阶段,逐阶段调用相应插件的 skill 执行,每个阶段结束经 stage-gate 门禁审批后进入下一阶段。同义触发场景:开始研究、开题、走流程、研究流程、lifecycle、继续上次的研究、阶段推进、研究项目管理、六阶段、从选题到成稿。
Audited 13.8k - marucie SkillLjg Paper Flow
Paper workflow: read papers + cast cards in one go. Takes one or more arxiv links, paper URLs, PDFs, or paper names. For each paper, runs ljg-paper (generates org analysis) then ljg-card -l (generates long reading card PNG). Use when user says '论文流', 'paper flow', '读论文并做卡片', '论文卡片', or provides multiple papers wanting both analysis and cards.
Audited 3 - marucie SkillPaper Write
本科与硕士学位论文全流程撰写辅助。支持大纲审核(理工科/文科)、结构仿写(通用章节/实验章节/绪论/摘要)、参考文献获取、融合、润色、缩写、扩写、防 AIGC、中英互译、结构化信息提取。当用户提到论文撰写、大纲审核、论文章节仿写、参考文献、论文润色、防 AIGC、论文翻译时使用。
Audited 3 - nirholas SkillVc Research Intelligence
Analyze VC research reports from a16z, Paradigm, Messari, and top-tier firms. Extract actionable insights, identify emerging trends, and map technology outlooks to product strategy and investment decisions.
Audited 656 - changhochien SkillIdea Generation
Use when financial-services work requires idea Generation.
Audited 8 - changhochien SkillSector Overview
Use when financial-services work requires sector Overview.
Audited 8 - changhochien SkillEarnings Preview
Use when financial-services work requires earnings Preview.
Audited 8 - changhochien SkillCatalyst Calendar
Use when financial-services work requires catalyst Calendar.
Audited 8 - vignesh2027 SkillMeeting Analyzer
Activates MeetingAnalyzer for extracting intelligence from meeting transcripts, notes, and recordings. Use when you need to extract action items with owners and due dates, identify decisions made, summarize key discussion points, detect unresolved conflicts or blockers, or generate a structured meeting follow-up email.
Audited 4 - vignesh2027 SkillQuant Researcher
Activates QuantResearcher for academic quantitative research and paper writing. Use when you need to formulate testable research hypotheses, select appropriate econometric or statistical methodology, synthesize existing literature on a topic, interpret statistical results in academic and business terms, or structure an academic paper (abstract through conclusion) following journal standards.
Audited 4 - naveedharri BundleNewsletter
Iterative newsletter writing workflow for Ben Van Sprundel's audience. Use when Ben wants to write a newsletter from research, an insight, an idea, or a YouTube video transcript. This is a CREATIVE, STEP-BY-STEP process. Never output a complete newsletter immediately. Each step requires suggestions, user decision, then progression to next step. Pairs with /research upstream and /image downstream. Triggers: newsletter, write newsletter, email content, repurpose video, insight to newsletter.
Audited 84 - yogsoth-ai BundleConsequence Following
Follow a provocation's logical consequences step by step to extract viable insights and new research directions.
Audited 512 - yogsoth-ai BundleGap Keyword Extraction
Extract gap-indicating sentences and phrases from papers/reviews. Identifies linguistic markers of research gaps (e.g., "remains unclear", "has not been explored", "limited understanding").
Audited 512 - yogsoth-ai SkillQuestion Reformulation
Reframe research questions using abstraction laddering, HMW formulation, and Socratic probing. Find the most productive level and framing for investigation.
Audited 512 - yogsoth-ai BundleCritical Path Identification
Identify which input uncertainties contribute most to output uncertainty and compute EVPI for research prioritization.
Audited 512 - yogsoth-ai BundleGoverning Variable Surfacing
Apply Argyris framework to identify governing variables — the unstated rules driving behavior in a research field.
Audited 512 - yuping322 BundleMacro Liquidity Monitor
Track macro liquidity indicators (rates, inflation, credit, central bank stance) and summarize implications for assets/sectors. Use when the user asks about liquidity conditions or policy-driven market impacts.
Audited 23 - richard0901 BundleSci Bioinformatics 18
Use when the project reaches 18-SCI生信结果主线提炼器 in the SCI original bioinformatics research workflow.
Audited 1 - richard0901 BundleSci Retrospective 04
Use when the project reaches 04-SCI回顾性研究问题构建器 in the SCI original retrospective research workflow.
Audited 1 - richard0901 BundleSci Clinical 05
Use when the project reaches 05-SCI临床研究文献检索式生成器 in the SCI original clinical research workflow.
Audited 1 - richard0901 BundleSci Bioinformatics 06
Use when the project reaches 06-SCI生信文献筛选与证据提取器 in the SCI original bioinformatics research workflow.
Audited 1
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 systematic-review, codex-companion, ljg-paper-flow. 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.