Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA/AMA/Vancouver), figures/tables, reporting guidelines (CONSORT/STROBE/PRISMA), for research papers and journal submissions.
Choose an external search tool based on the question type. For technical questions about code, libraries, frameworks, SDKs, CLI, APIs, and cloud services, prioritize the find-docs skill; for other open-web searches, prioritize Exa WebSearch; to open or read a specific URL, use OpenAI official Web Search. Silently switch sources if the preferred tool has insufficient quota or is unavailable. This skill does not handle local file searches or code-hosting repository tasks.
Web search and content extraction via SearXNG metasearch engine. Use when you need to search the web, look up documentation, research APIs, find current information, or extract content from URLs. No API keys required, no rate limits, privacy-preserving.
Use when asked to "shape up", "run a shaping session", "set an appetite", "scope a project without estimates", "betting table", or "ship in fixed cycles". Helps teams escape estimate-driven development and Scrum fatigue. The Shape Up method (created by Ryan Singer at Basecamp/37signals) uses fixed time boxes, variable scope, and collaborative shaping to ship meaningful work predictably.
Use when the user is setting strategy, making decisions, or running a company/team and needs a framework for what not to do. Typical triggers: "we want to try everything", "there are many opportunities but we don't know how to choose", "the company is growing too fast and feels out of control", "how do we avoid fatal mistakes". Not for: pure task planning (a to-do list) or information lookup. Core logic: what you don't do matters more than what you do — prevent fatal mistakes by actively building a "stop-doing list".
Apply systems thinking to leadership decisions and produce a Systems Thinking Pack (system boundary, actors & incentives map, feedback loops, second-order effects ledger, leverage points, intervention plan). Use for complex ecosystems, trade-offs, org/process redesign, and preventing unintended consequences.
AI Task Drill — a task breakdown assistant that guides people in breaking down tasks by task type and dividing which tasks should go to AI and which should be done by humans themselves. Supports four task types: direct problem solving, direct output generation, collaborative problem solving, and collaborative output generation, with detailed workflows and prompt strategies for each type. Use this skill when the user raises any task, needs help making a plan, or asks to break down work.
Web (re)search using Tavily APIs. Search the web, extract content from URLs, discover site maps, or get AI-synthesized research reports with citations. Use for factual search, current events, financial data, full content extraction, site map URLs, or comprehensive research reports. Topics: general, news, finance.
Plan trips with assumptions, not questions. Trip Planner extracts flight constraints from natural conversation, fills in the gaps with smart defaults, and returns structured flight recommendations with direct booking links. Assume first. Show your work. Book the flight. Just say "trip-planner" to get going.
Fetch web page content via Chrome DevTools Protocol (CDP). Full JS rendering, handles redirects (including Google News). Use when you need to read the text content of a web page, scrape articles, or extract information from URLs. Zero dependencies — Python 3 stdlib only. Cross-platform (Mac, Windows, Linux).
Create expert-level learning reports and tutorials from any domain, industry, technology, role, market, product idea, or vague field question. Use when the user wants to quickly build domain expertise, understand an industry, generate a structured expert study report, build a keyword library, design Feynman self-tests, or export the result as Markdown, DOCX, PDF, and HTML. Do not use for short factual answers, pure business model diagnosis, standalone beginner tutorials with no domain-structure research, simple file conversion, or unsourced opinion writing.
Generates business-oriented work reports for managers. Triggered when the user says "生成工作报告", "写工作报告", "汇总工作", or "生成工作总结". Not for generating technical changelogs, developer-facing commit summaries, project handover documents, or code review reports.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to “open a website”, “fill out a form”, “click a button”, “take a screenshot”, “scrape data from a page”, “test this web app”, “login to a site”, “automate browser actions”, or any task requiring programmatic web interaction.
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
Control a connected Android phone via ADB — tap, swipe, type, read the screen via the accessibility tree, take screenshots (for humans/vision models), and run shell commands. Use this skill whenever the user wants to interact with their Android device, automate phone tasks, read what's on the phone screen, check phone status, open apps, navigate the UI, or perform any mobile device operation. Use it for Android device operations or android-bridge troubleshooting; a generic mention of a phone or screen does not require this skill. Works with both text-only and vision-capable models
Intelligent grocery shopping assistant for iFood Mercado and other online grocery stores (Prezunic, Carrefour, Extra, etc). Use this skill whenever the user wants to: build a shopping cart, make a grocery list, compare prices across stores, plan weekly meals, repeat previous purchases, manage a shopping budget, get product substitution suggestions, create lists by context (breakfast, lunch boxes, barbecue, cleaning), or any task related to online grocery shopping. Also trigger when the user mentions: "compras", "supermercado", "mercado", "carrinho", "lista de compras", "iFood", "Prezunic", "receitas da semana", "marmita", "orçamento semanal", "produto mais barato", or asks to repeat/reuse a previous purchase. This skill combines browser automation (Chrome) with shopping intelligence — brand preferences, dietary restrictions, price history, and smart substitutions.
Jira and Confluence integration for Atlassian Cloud. Use when the user needs to search issues, manage sprints, read Confluence docs, create/update pages, work with epics and backlogs, or any Atlassian workflow. Triggers include "jira", "confluence", "sprint", "backlog", "ticket", "issue", "epic", or references to Atlassian content.
Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases
Case radar. Given something new (a new tool/concept/ecosystem), scan the ecosystem for fun real-world cases, focusing on capturing "real artifacts" (screenshots/source code/demos) rather than GitHub homepages, and output a browsable HTML case collection. Triggers when the user says "看看大家用 X 做了什么", "扫一下 X 生态", "市面上 X 有什么新玩法", "给我看 X 的真物案例", or "/case-radar". Not suitable for: ① in-depth research with an already clear goal (use the available research tools to study directly) ② writing articles/producing PRDs (use writing-assistant / prd-test-writer) ③ pure knowledge seeking that doesn't need HTML (just ask directly).
Analyze a provided resource through a Circuit lens. Use when the user provides or points to an article, pasted conversation, X thread, workflow example, GitHub repo, local codebase, product page, paper, or other outside reference and asks what Circuit can learn from it, whether it suggests a possible Circuit flow, whether Circuit can support the workflow today, what product or block changes would be needed, or whether the analysis should be added to Circuit's ideas or flow backlog.
Research customer questions by searching across documentation, knowledge bases, and connected sources, then synthesize a confidence-scored answer. Use when a customer asks a question you need to investigate, when building background on a customer situation, or when you need account context.
Track deep work sessions locally (start/stop/status) and generate a GitHub-contribution-graph style minutes-per-day heatmap for sharing (e.g., via Telegram). Use when the user says things like “start deep work”, “stop deep work”, “am I in a session?”, “show my deep work graph”, or asks to review deep work history.
Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.
Break a problem into hard constraints, conventions, and unknowns, then redesign options from fundamentals. Saves structured multi-file analysis under .hypercore/elon-musk/[topic-slug]/ with phase tracking. Use when current answers feel copied from industry defaults.
Turn messy logs, notebooks, run metadata, and partial conclusions into a clear research update with next actions. Use after intense experimentation, for lab notes, handoff, weekly updates, resuming interrupted work, or when run history needs to become decisions rather than scattered impressions.
Use a Gemini multi-agent architecture to fact-check Markdown documents sentence by sentence. Phase 1 uses gemini-2.0-flash to split sentences, classify them (factual/subjective) and extract claims; Phase 2 uses gemini-2.5-flash + Google Search to check every data point sentence by sentence. Triggered when the user asks to verify the accuracy of data in an article, validate factual claims in a document, or check whether numbers, dates or policy citations in a report are correct.
An intelligent file-organizing skill based on AI semantic analysis, dynamically creating Johnny Decimal categories according to file content. Triggers when the user mentions: "整理文件", "分类文件", "组织下载", "文件归档", "文件太多了", "下载文件夹很乱", "文件乱七八糟", "把文件按类别整理", "自动分类文件", "清理下载文件夹", "整理文档", "文件管理", "文件分类整理", or mentions needing to move files from one directory to another for categorization. Core features: AI analyzes file-name semantics and dynamically generates categories; uses the Johnny Decimal numbering system (XX.YY format); automatically detects duplicate files (MD5 algorithm); executes only after the user confirms the classification plan.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Perform complex, long-running research tasks using Gemini Deep Research Agent. Use when asked to research topics requiring multi-source synthesis, competitive analysis, market research, or comprehensive technical investigations that benefit from systematic web search and analysis.
Search Google Patents database for patent research, infringement risk checks, and competitive IP analysis. Use when user mentions: 专利, patent, 侵权, infringement, 知识产权, IP, 外观设计, design patent, 专利检索, patent search, 专利风险, patent risk, 专利分析, patent analysis, 专利布局, patent portfolio, 有没有专利, 会不会侵权, 能不能卖, FTO, freedom to operate, 规避设计, 专利壁垒, 技术壁垒, 权利要求, claims, 专利详情, 发明人, inventor, 受让人, assignee, 专利号, patent number, 说明书, description, 技术领域, 背景技术, 发明内容, 具体实施方式, PDF
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.