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.
-
kangwang42 Bundle Research Visuals 2默认使用 imagegen 为论文、PPT、标书、报告、README 和网页生成或重绘科研非统计视觉,覆盖医学、公共卫生、计算机科学、人工智能与机器学习中的流程、路线、结构、框架、机制、模型架构、系统图、时间线、图形摘要、封面和网页内容图。先区分内容图、真实截图与氛围图,再按研究领域读取对应 reference;统计数据图转 publication-figures,科研原始图像不得生成式重绘,现有 UI 优先复用。只有 imagegen 实际不可用、用户明确要求 SVG/矢量源、编辑现有 SVG 或交付格式强制矢量时才转 svg-diagrams,不以生成结果不准确或不好看作为改用 SVG 的理由。
-
kangwang42 Bundle Evidence Research 2科研决策的证据检索、来源身份核验、证据评价与适用性判断技能。触发场景:(1) 快速核验单个事实、单篇引文、标题、DOI 或 PMID;(2) 查找最新证据、指南、方法依据或真实引文;(3) 构建结局指标、选择量表、制定异常值规则;(4) 试新方法、比较指标或判断跨领域方法能否迁移。 自动选择 rapid verification 或 formal evidence review。两种模式均核验来源身份;只有 formal 模式要求完整检索方案和证据汇总表。不负责统计模型实跑或论文正文生成,不得以文献替代项目数据核验,不得编造来源或研究结论。
-
kangwang42 Bundle Publication Figures 2为 R 或 Python 真实数据选择、绘制、返工和审查发表级统计图、数据图,包括森林图、生存曲线、ROC、热图、模型诊断和由多个子图组成的图件,并控制尺寸、字体与配色。任何 ggplot/matplotlib 统计出图均使用;流程、机制、框架和技术路线转 research-visuals。开工先遵循 biostat-principles。
-
kastalien-research Skill Taste 2Run a taste evaluation on a research proposal or technical direction. Determines whether to proceed, simplify, defer, or kill before committing research effort.
-
kastalien-research Skill Research Task 2Execute a research task using compositional workflow planning. Characterizes the task, selects an approach from a library of research strategies, executes it, and self-evaluates output quality.
-
kastalien-research Skill Thoughtbox Research 2Structured research using Thoughtbox IRCoT (Interleaved Retrieval and Chain-of-Thought). Triggers on: "research", "investigate", "explore", "literature review", "what do we know about".
-
borkweb Bundle Writing Commits 2Use this skill to create git commits and write concise, plain-language commit messages that summarize intent and outcomes rather than code actions. Invoke it for ANY of these user goals: committing code changes, crafting or suggesting commit messages, describing diffs for commit purposes, or formatting commits in conventional/angular style. Common triggers: 'commit this', 'commit them', 'write a commit message', 'what should the commit message be', 'help me with the commit', or any variant where the user has finished coding and wants to record their changes in git. Also invoke when users mention pushing code and need the commit authored first, when they ask to split changes into separate commits, or when they ask to summarize what changed for a commit. Exclude: pull requests, code review, changelogs, reverting commits, git log analysis, writing docs about commit conventions.
-
a-v-ershov Bundle Create User Flows 2Map how users actually move through the product to get value — the customer journey and the step-by-step flows for each feature, informed by conventional patterns for the category and an adversarial review pass. Use after define-product-requirements (reads product-requirements.research.md) and before design-architecture. Writes a source-cited .dev-skills/project-spec/user-flows.research.md plus a short human summary; an independent reviewer returns findings and the phase applies them in place. The second product-layer step: it describes the experience (WHAT the user does), never the technical HOW and never visual UI design.
-
a-v-ershov Bundle Define Code Style 2Define the project's development style guide once the stack is chosen: how code is organized (module/folder architecture), named, commented and documented, how errors are handled, and how tests are written. For each dimension where the chosen stack offers real alternatives it weighs the top 2–3 idiomatic options with trade-offs and recommends one; everything else inherits the stack's canon with a citation. Use after design-architecture and before design-dev-architecture. Writes a source-cited code-style.research.md, a short human summary, and the distilled code-style.md guide that implement-feature, verify-feature, refactor and write-tests follow on every task.
-
a-v-ershov Bundle Define Product Requirements 2Turn a validated idea into the product definition: who it is for, and the full set of features being built — backed by real-world research (comparable products, table-stakes features) and an adversarial review pass. The committed set holds at most 15 features: sub-capabilities fold into the feature they belong to, and whatever does not earn a place is cut into non-goals rather than deferred. Use after validate-idea and before create-user-flows and design-architecture. Writes a source-cited product-requirements.research.md plus a short human summary. Defines the product layer (WHAT and for WHOM) — never the technical HOW, which is design-architecture's.
-
fabioc-aloha Skill Act Feasibility Spike 2Frames disposable feasibility experiments through explicit questions, research, approval, observable evidence, and a clear verdict.
-
qa-aman Bundle Youtube Transcript 2Fetch transcripts from YouTube videos. Use when user says "get transcript", "fetch transcript", "YouTube transcript", "pull captions", "what does this video say", or pastes a YouTube URL and wants the text content extracted. Also use when user wants to research or summarize a YouTube video.
-
kyrie66nb Skill Autoresearch 2[OMX] Stateful validator-gated research loop with native-hook persistence
-
kyrie66nb Skill Idea Creator 2Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
-
eugenezhangco-spec Skill Deep Research 2Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.
-
zhnnky329 Skill Reference Manager 2Manage and verify references for mathematical modeling contest papers, generating BibTeX entries, checking citation completeness, and ensuring all references are traceable to actual sources.
-
arogyareddy Skill Search First 2Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Systematizes the "search for existing solutions before implementing" approach. Use when starting new features or adding functionality.
-
open-curiosity Skill Yc CLI 2Operator's guide to the YC CLI (`yc`) for the Gini batch demo — scoped to the yc commands the demo actually uses: the validated browser-forward login flow (tmux + browser_connect) and investor research against Bookface. Assumes yc is installed but NOT logged in yet. Load before staging or running the demo.
-
wirasm Skill Prp Codebase Question 2Research codebase questions using parallel agents - documents what exists, not what should change. Use when the user asks how the codebase works, where something lives, or invokes $prp-codebase-question.
-
yejiming Skill Web3 Safe Guide 2Use this skill when the user asks beginner-friendly Web3 questions such as '帮我研究一下XXX这个币', '最近什么币在涨', '聪明钱在买什么', '巨鲸在买什么', '这个币安全吗', '我想买一点XXX', '帮我查一下行情', '最近有什么机会', '跟着大户买什么好', '这个信号准不准', '交易费用大概多少', 'what should I buy', 'is this token safe', 'what are whales buying', 'show me trending tokens', 'help me research a token', 'is this a scam', 'how much will the gas cost'. This skill wraps multiple onchainos CLI tools into a beginner-friendly experience with automatic safety scoring, smart money signal momentum tracking, gas estimation, and step-by-step swap guidance. It requires onchainos CLI to be installed. Always respond in the same language the user uses (Chinese or English).
-
aizech Bundle Radiology Research 2Access and synthesize medical imaging research literature. Use when user mentions "recent research on", "literature review", "published studies", "evidence for", or needs to find relevant research.
-
aizech Bundle Cross Reference Linking 2Links current findings to priors, related literature, and correlated data. Use when user mentions "compare to priors", "find prior studies", "correlate with", "longitudinal comparison", or needs historical context.
-
awaik Bundle Demand Research 2Исследовать поисковый спрос через LidFly Wordstat: сезонность, упущенный спрос, интент, регионы и каннибализация. Использовать для проверки спроса и подготовки рекомендаций без client_login или connection_id Директа.
-
blockscout Skill Research Scope 5Investigate and document the intended scope of a codebase topic through interactive discussion, then persist a durable research note under .memory-bank/research/ once the human confirms the framing
-
blockscout Skill Research Scope 6Investigate the intended scope of a codebase topic through discussion with a human, propose a research-note outline, and only create a .memory-bank/research file after explicit human confirmation.
-
blockscout Bundle Implementation Plan 6Turn an approved task-analysis result into a shared technical design and coding-ready implementation handoff. Use when Codex has an existing task folder under `tmp/tasks/`, plus a selected solution and related codebase research, and needs to produce `implementation-plan-X.md` and `coding-task-X.md` before writing code.
-
blockscout Skill Implementation Plan 7Turn an approved task-analysis result into a shared technical design and coding-ready implementation handoff; use when Claude has an existing task folder under `tmp/tasks/`, plus a selected solution and related codebase research, and needs to produce `implementation-plan.md` and `coding-task.md` before writing code
-
blockscout Skill Implementation Plan 8Turn an approved task-analysis result into a shared technical design and coding-ready implementation handoff. Use when Cursor has an existing task folder under `tmp/tasks/`, plus a selected solution and related codebase research, and needs to produce `implementation-plan.md` and `coding-task.md` before writing code.
-
blockscout Skill Research Scope 7Investigate and clarify a reusable codebase topic through dialogue, then create or update a `.memory-bank/research` note only after explicit human confirmation.
-
deepleaper Bundle Duckduckgo Search 2Free web search via DuckDuckGo — text, news, images, videos. No API key needed. Prefer the `ddgs` CLI when installed; use the Python DDGS library only after verifying that `ddgs` is available in the current runtime.
-
ed3dai Skill Investigating A Codebase 2Use when planning or designing features and need to understand current codebase state, find existing patterns, or verify assumptions about what exists; when design makes assumptions about file locations, structure, or existing code that need verification - prevents hallucination by grounding plans in reality
-
ed3dai Skill Researching On The Internet 2Use when planning features and need current API docs, library patterns, or external knowledge; when testing hypotheses about technology choices or claims; when verifying assumptions before design decisions - gathers well-sourced, current information from the internet to inform technical decisions
-
educlopez Bundle Panda Kb 2Curated knowledge base for the Panda theme by SunnyToo on PrestaShop 8 and 9 — 54 module fiches, 19 demos catalog, scraped official docs, and the Easy Builder track (steasybuilder + steasy_trans_panda). Use when answering questions about Panda-specific modules (`st*` prefix), SunnyToo widgets, Easy Builder layouts, or "what can Panda render". For PrestaShop platform-level questions (Symfony, Twig BO, Smarty syntax, hooks core, theme.yml mechanics, migration 8→9) use the `prestashop-kb` skill instead.
-
educlopez Bundle Prestashop Kb 2Curated knowledge base for the PrestaShop platform — versions 8 and 9. Covers theme mechanics (theme.yml, parent-child, template inheritance, assets), Smarty templating + PS extensions ({l}, {hook}, {widget}), hooks (overview + listings), modules architecture (config.xml, controllers, lifecycle), install vs distribution (PS 9 source clone), and version migration PS 8 → 9 (Symfony BO, Twig, upgrade process). Use for platform-level PrestaShop questions independent of any specific theme. For Panda-theme-specific questions (`st*` modules, SunnyToo, Easy Builder) use the `panda-kb` skill instead.
-
educlopez Bundle Elementflow Kb 2Curated knowledge base for ElementFlow — an Elementor-based page-builder theme/module for PrestaShop (backed by the `stsitebuilder` module: header, footer, home, category, product-page, and CMS-page builders, plus a widget library). Use when answering questions about ElementFlow-specific widgets (Newsletter, Container, Grid, PrestaShop module, Image, Registration/Login/ Sign-in forms, Custom template, Tabs & megamenu, Divider, Product name/ comment/gallery, Search, Text editor, Slider, Accordion), the page builders (product/category miniature, product/category page, shopping cart, header, mobile menu, CMS page), or ElementFlow-specific features (sticky header, wishlist, shortcodes, display conditions, drag & drop editor, sidebar/popup, side cart, SVG icons, checkout/my-account child theme, blog, JS events). Also trigger for install/upgrade/demo-import/dev-to-production questions about ElementFlow, or when the user mentions `stsitebuilder`, `st_site_builder`, or a project using the ElementFlow child theme. Tri
-
howarewoo Bundle Woostack Bootstrap 2Bootstrap a genuinely greenfield web, mobile, desktop, API, or daemon project from scratch—gather requirements, research current technologies, approve the design, collision-check the target, and scaffold app-local code with shared packages only when needed. Linear, Plane, or GitHub artifacts are optional.
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 research-visuals, evidence-research, publication-figures. 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.