Research Claude Skills
2 269 research skills from 396 authors. They find sources and get you up to speed on unfamiliar ground. Half of them fit into 2 278 tokens or less — that is what one costs your context window when the agent loads it. 663 ship runnable scripts rather than instructions alone. 4 of them cannot work without an MCP server, most often rube. We also found 264 copies of these same skills sitting in other people's repositories — counted once here, not 264 times.
2 269 unique 396 authors 1 169 updated this month 93 from vendors
> Research a company or idea, define the Ideal Customer Profile, and route to the right next step — either mapping the TAM or finding leads/prospects directly. The entry point for any "find me leads", "map my market", or "who should I sell to" request. Auto-loads when a user provides a company URL or idea and asks for leads or market mapping.
> Fills in missing data for inbound leads — researches the company, identifies the person's role and seniority, finds other stakeholders at the company, checks for existing CRM relationships, and updates the lead record. Produces enriched lead data ready for qualification or outreach. Tool-agnostic.
Builds personalized demo assets for top prospects using the founder's product API/MCP/SDK. Researches prospect, proposes demo concepts, builds working prototype, tests it, and generates comparison report with live demo link.
Find attendees at conferences/events, research their companies, qualify against ICP, and launch outreach
Extract leads from conferences, meetups, hackathons, and podcasts by analyzing speaker lists, sponsor lists, hackathon entries, and podcast guests. Discovers events via Sessionize, Confs.tech, Meetup, Luma, ListenNotes, and Devpost. Looks back 90 days and forward 180 days.
> Research LinkedIn profiles and write personalized messages for any LinkedIn message type — connection requests, InMails, DMs, message requests, post comments, and comment replies. Takes LinkedIn URLs as input, researches each person (profile data + recent posts via Apify), and generates messages tailored to each lead's background, interests, and recent activity. Exports tool-ready CSVs for Dripify, Expandi, Botdog, PhantomBuster, or generic format. No LinkedIn cookies or login required.
Web research API with OpenAI-compatible chat completions and async tasks
AI-powered web search, crawling, extraction, and deep research
Neural web search - find similar content, extract pages, and run deep research
Search the web, platforms, and datasets. Use when asked to search, find, look up, research, or discover information from the web, YouTube, Amazon, eBay, news, academic sources, or any online platform.
Web search, AI answers, content extraction, and async deep research
> Research a company's ideal customer profiles and build detailed synthetic buyer personas. Identifies 4-6 distinct buyer segments through web research, then creates rich, realistic personas with demographics, motivations, skepticism profiles, decision criteria, and language patterns. Use when you need to understand who your buyers are at a deep level — their motivations, objections, and how they evaluate solutions.
> Discover all customers of a given company by scanning websites, case studies, review sites, press, social media, job postings, and more. Use when you need competitive intelligence on who a company sells to.
Research VCs, angels, and investors - portfolio, thesis, contact info
Research market trends, size, competitors, and growth opportunities
> Pre-sales-call intelligence composite. Deep dives on the person AND their company before a sales call, then maps findings to your product to generate talking points, objection prep, and a call strategy. Goes beyond generic attendee research — this is sales-specific intelligence that helps SDRs, AEs, and founders walk into calls with a plan. Tool-agnostic — works with any CRM, research source, and calendar.
> Searches and retrieves official Gradle User Guide, DSL Reference, and internal engine source code authoritatively; use for researching core Gradle features, verifying behavior, and deep-diving into internals. Do NOT use for project dependency source exploration (use `searching_dependency_sources`) or running builds.
> Provides expert build engineer guidance on Gradle Kotlin DSL scripts, plugin development, and deep internals research; use for build failures, compilation errors, dependency conflicts, or complex build authoring. Do NOT use for executing builds/tests (use `running_gradle_builds`/`running_gradle_tests`) or dependency graph auditing.
> Deep-dive audit using the full testsmells.org 19-smell academic catalog for tests in any language. Every finding maps to a named, citable smell from the research literature (Assertion Roulette, Duplicate Assert, Mystery Guest, Eager Test, Sensitive Equality, Conditional Test Logic, Sleepy Test, Magic Number Test, etc.) with research-backed severity. (RSpec/Minitest), Rust, Swift, Kotlin (JUnit/Kotest), PowerShell (Pester), C++ (GoogleTest/Catch2). INVOKE ONLY when explicitly asked for the testsmells.org 19-smell academic catalog or citable smell names from the literature. writing new tests (use code-testing-agent, or writing-mstest-tests for MSTest); running tests (use run-tests); framework migration.
| Transforms vague video ideas into detailed scene-by-scene plans (scenes.md). Conducts research, asks clarifying questions about audience/scope/focus, and outputs comprehensive scene specifications ready for implementation with ManimCE or ManimGL. Use this BEFORE writing any Manim code. This skill plans the video; use manimce-best-practices or manimgl-best-practices for implementation.
Investigate current challenges, limitations, and proposed solutions in Japanese NLP for a topic. Surveys the existing awesome-japanese-nlp-resources dataset to see what already exists, then web-researches known problems and ongoing efforts to produce a digestible issue report.
Analyze current trends in Japanese NLP for a topic. Surveys the existing awesome-japanese-nlp-resources dataset and augments it with up-to-the-minute web research to produce a digestible trend report.
Access research-grade sensor data using SensorKit for approved studies. Use when an app needs SensorKit entitlement setup, Research Sensor & Usage Data authorization, ambient light, recorded motion, device usage, keyboard metrics, visits, speech, face, wrist temperature, ECG, PPG, acoustic settings, or sleep-session data. Route ordinary motion to CoreMotion and health records/workouts to HealthKit.
This skill should be used when user asks to "fetch overleaf review comments", "address overleaf reviews", "apply overleaf comments", "review my overleaf paper", "sync overleaf feedback to local", "what comments are on my overleaf doc", or wants to act on Overleaf reviewer feedback in a local git-tracked LaTeX repo.
This skill should be used when user asks to "search for papers", "find research papers", "search arXiv", "search PubMed", "find academic papers", "search IEEE", "search Scopus", or "look up scientific literature".
This skill should be used when user encounters "paper-search MCP error", "Docker not found", "Docker not running", "paper search not working", or needs help configuring paper search integration.
Deep research and discovery before building something new. Explores local projects for reusable code, researches competitors, reads forums and reviews, analyses plugin ecosystems, investigates technical options, and produces a comprehensive research brief. Three depths: focused (30 min), wide (1-2 hours), deep (3-6 hours). Triggers: 'research this', 'discovery', 'explore the space', 'what should I build', 'competitive analysis', 'before I start building', 'research before coding'. Not for cited fact-checking research reports (a separate harness does those); this is pre-build product discovery.
Generate a reproducible final report, literature-outcome synthesis, JSON summary, and refreshed progress plot for a stopped or interrupted NVFLARE Auto-FL campaign.
专业 PPT 演示文稿全流程 AI 生成助手。模拟顶级 PPT 设计公司的完整工作流（需求调研到资料搜集到大纲策划到策划稿到设计稿），输出高质量 HTML 格式演示文稿。当用户提到制作 PPT、做演示文稿、做 slides、做幻灯片、做汇报材料、做培训课件、做路演 deck、做产品介绍页面时触发此技能。即使用户只说"帮我做个关于 X 的介绍"或"我要给老板汇报 Y"，只要暗示需要结构化的多页演示内容，都应该触发。也适用于用户说"帮我把这篇文档做成 PPT"、"把这个主题做成演示"等需要将内容转化为演示格式的场景。英文场景同样适用："make a presentation about..."、"create slides for..."、"build a pitch deck"、"I need a keynote for..."。隐式意图也应触发："帮我把这个数据可视化一下给老板看"、"我需要一份能拿去路演的东西"、"把这个报告做得好看点能展示"、"beautify my existing PPT"、"redesign these slides"。改善或美化现有 PPT 也属于此技能范畴。
> 给一句话或一段话，找出真实学术文献来反对它——相反结论、边界条件、替代解释、方法批评、复制失败。按威胁程度排序，每篇附一行"它如何威胁这个观点"和"怎么回应它"。底层走真实检索（scimaster-cli），绝不编造反例。 **以下情况请主动触发本技能**：用户想"提前挡住审稿人"、"找这个结论的反例"、"这个方向有没有争议"、"有没有跟这个相反的研究"、"帮我攻击这个论点"、"这个结论稳不稳"、"想知道有哪些反对意见"——即使用户没有说"bear-counter"，只要意图是**为一个观点寻找学术反对证据**，就使用本技能。bear-support 和 bear-counter 配对使用效果最好：对同一段话各跑一遍，就能同时看到正反两面。 不适用于：找支持文献（用 bear-support）、选题查重（用 bear-scoop）、概念地图（用 bear-map）、溯源演化史（用 bear-trace）。
> 给一个研究 idea，依次执行撞车检测、安静区支撑检索、潜在挑战检索，在一份综合报告里呈现这个 idea 的立项前证据格局——撞车风险在哪、安静区里有没有文献支撑、最需要提前想清楚的挑战是什么。底层走真实检索（scimaster-cli），绝不编造引用。 **以下情况请主动触发本技能**：用户想"开题前评估一下"、"这个 idea 值不值得做"、"立项前做个全面的文献调研"、"帮我评估这个研究方向"——即使没有说"bear-propose"，只要意图是**在正式投入一个研究方向之前做综合评估**，就使用本技能。 不适用于：只查撞车（用 bear-scoop）、只找支持（用 bear-support）、只找反对（用 bear-counter）、概念地图（用 bear-map）、溯源演化史（用 bear-trace）。
> 在你投入一个研究方向之前，先看看有谁已经在做同样的事。把 idea 拆成多个不同角度分别去检索，返回一张"邻近程度地图"，重点标出最危险的撞车候选。底层走真实检索（scimaster-cli），不做主观新颖性判断。 **以下情况请主动触发本技能**：用户说"这个选题有没有人做过"、"我会不会被抢发"、"这个方向还有空间吗"、"我的 idea 新不新"、"要不要查一下有没有撞车"、"这个想法是不是已经有人发了"——即使用户没有说"bear-scoop"，只要意图是**在提交或动笔前确认 idea 的独特性**，就使用本技能。加 `-r` flag 只看近两年和预印本，适合担心被抢发的场景。 不适用于：为已有观点找支持文献（用 bear-support）、找反对文献（用 bear-counter）、概念地图（用 bear-map）、溯源演化史（用 bear-trace）。
> 给一句话或一段话，找出真实学术文献来支持它，每篇文献附一行"它如何支撑这个观点"的说明。底层走真实检索（scimaster-cli），绝不从记忆编造引用——搜不到就如实说搜不到。 **以下情况请主动触发本技能**：用户想让某个观点"更有依据"、"更经得起质疑"、"加上文献支撑"、"找几篇论文"、"这个说法有没有研究"、"帮我查一下这个结论"、"审稿人会不会说没有引用"——即使用户没有说"bear-support"或"找文献"这几个字，只要意图是**为一个观点寻找学术支撑**，就使用本技能。 不适用于：找反对文献（用 bear-counter）、选题查重（用 bear-scoop）、概念地图（用 bear-map）、溯源演化史（用 bear-trace）。
> 给一个主题或一篇种子论文，向前挖掘它建立在哪些前驱工作上（逐层回溯），再向后补充最新进展，讲清楚这个问题从源头到现在是怎么演化的。底层走真实检索（scimaster-cli），每个节点都锚定真实检索到的论文。 **以下情况请主动触发本技能**：用户问"这个问题是怎么来的"、"帮我溯源这个方向"、"这个领域怎么发展的"、"这篇论文是建立在谁的基础上的"、"从头讲一下这个方向的历史"、"入门一个新领域想先了解演化脉络"——即使用户没有说"bear-trace"，只要意图是**理解一个研究问题或领域的来龙去脉**，就使用本技能。加 `-d N` 控制向前溯源的层数（默认 3 层）。 不适用于：为观点找支持文献（用 bear-support）、找反对文献（用 bear-counter）、选题查重（用 bear-scoop）、概念地图（用 bear-map）。
Compose or improve a publication-grade multi-panel scientific figure from a claim, concrete data paths, or an existing image. Use for figure outlining, parallel panel rendering, exact-grid composition, visual inspection, and adversarial figure review. Use figure-style for one standalone plot and paper-narrative for whole-paper figure ordering.
Use this skill whenever the user provides a scientific paper PDF and asks for a group-meeting literature report, journal-club slides, 文献汇报PPT, 组会PPT, paper presentation, article walkthrough, or to explain a paper with PowerPoint. The skill first reconstructs the paper's scientific logic, then builds author/background sections, chooses an evidence-driven slide outline, crops only main-text figure panels from the PDF, and creates an academic PPT with 10–30 slides including title and conclusion/discussion. Always use this skill for '把这篇论文做成PPT', '文献汇报', 'journal club', or '组会汇报', even if the user only says they need slides.
Find, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.
Configure the local wisp-science runtime — uv/Python bootstrap, Node+scimaster-cli for bear-* literature skills, pixi for bioinformatics multi-env analysis. Detect mainland-China network and apply mirrors. Use when Capabilities shows missing Python/uv/Node/sci/pixi, bootstrap errors, or the user asks to 配置环境 / install Python / uv / Node / pixi / set up the local environment. Not for remote GPU/SSH compute (use compute-env-setup).
Judge and reshape the story told by a manuscript and its figure deck. Use when revising paper structure, testing whether Figure 1 is a hook, ordering figures, moving panels, identifying missing analyses, or defining the claim passed to figure-composer.
Submit recoverable SSH-direct research Runs with live progress cards and model-free monitoring.
When the user wants to plan, implement, or optimize student and education discount programs. Also use when the user mentions "student discount," "education discount," "student plan," "for students," ".edu discount," "academic pricing," "student verification," "SheerID," "UNiDAYS," or "education program." For startup pricing page, use startups-page-generator.
When the user wants to add recommendations, links, or content to Grokipedia. Also use when the user mentions "Grokipedia," "GEO wiki," "AI encyclopedia," "suggest Grokipedia article," "Grokipedia citation," "Grokipedia listing," "AI search citation," "GEO visibility," or "Grokipedia optimization." For multi-platform parasite SEO strategy, use parasite-seo. For broad AI search visibility, use generative-engine-optimization.
When the user wants to improve E-E-A-T, add trust signals, or optimize for expertise and authority. Also use when the user mentions "E-E-A-T," "E-E-A-T signals," "experience expertise authority trust," "author bio," "YMYL," "trust signals," "expertise signals," "authority signals," "citations," "references," or "credibility." For headings, use heading-structure.
When the user wants to research keywords, find target keywords, or analyze search intent. Also use when the user mentions "keyword research," "keyword tool," "target keywords," "search volume," "search intent," "keyword difficulty," "topical map," "keyword clustering," "People Also Ask," "Google autocomplete," "autocomplete keywords," or "alphabet method." For clusters, use content-strategy.
When the user wants to find information sources for content ideation, competitor monitoring, or industry tracking. Also use when the user mentions "research sources," "information sources," "content ideation," "industry monitoring," "competitor monitoring," "market intelligence," "content research," or "topic research." For keywords, use keyword-research.
Run or resume a measured improvement loop in a local project. Use for benchmark-driven optimization, qualitative quality-gap research, packet logging, dashboard readouts, recovery, and review-branch finalization backed by autoresearch session files.
When the user wants to optimize any form that is NOT signup/registration — including lead capture forms, contact forms, demo request forms, application forms, survey forms, or checkout forms. Also use when the user mentions "form optimization," "lead form conversions," "form friction," "form fields," "form completion rate," or "contact form." For signup/registration forms, see signup-flow-cro. For popups containing forms, see popup-cro.
> Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for fake citations, validate references in a paper, or audit bibliography entries for accuracy.