Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Trigger this skill when the user needs to find similar cases, related judgments, or adjudication rules relevant to the current legal issue. Typical triggers include: the user explicitly asks for similar cases or precedents; needing prior rulings to support a legal argument; case prediction requiring reference to comparable judgments; drafting legal documents requiring citations of authoritative cases; analyzing judicial practice trends on a legal issue; comparing the positions of different courts or different periods on the same issue. Keywords include but are not limited to: similar cases, related judgments, case retrieval, adjudication rules, comparable cases, guiding cases, typical cases, judicial views, adjudication gist, etc.
Use when exposure, outcome, covariate or eligibility definitions and cutoffs need a citable basis before the protocol. Reads the data dictionary first, then maps each variable to a guideline or published definition and the database columns in a citation-backed table.
Control native macOS apps that have no API and leave reproducible evidence: capture a specific window (even when occluded in the background), click and type, probe whether an app can be automated, control Chromium-embedded apps via CDP with zero focus, run product testing and multi-model batch runs. For browser work use huashu-chrome; for browsing old screenshots use disk-keeper.
Read and write to the user's JDex — their Johnny.Decimal index. Use this skill whenever the user mentions their JDex, asks to check, fetch, or update their own documentation, references a Johnny.Decimal ID (e.g. 12.34, W0189), invokes you from a folder with an ID in its name, asks to find a file or document, asks to file, name, or rename a file (e.g. "file this", "name this", "put this download away"), asks to move in to their system or to put their existing files into it (e.g. "move me in", "sort out my Downloads"), asks where a document belongs in their JD system, or asks a factual question about their own life or business (e.g. "where does X money go?", "what's the process for Y?", "trace where Z ended up"). The JDex is their knowledge base — treat any investigative or research question about their own information as a JDex lookup first.
Based on the body of an NSFC proposal and the application code recommendation library, gives you 5 sets of application code 1/2 (primary/secondary) recommendations with reasons; output to NSFC-CODE-vYYYYMMDDHHmm.md (read-only, does not modify the proposal)
Use when the user wants to operate or validate web pages with the locally logged-in Chrome (including testing their own site, E2E, screenshots), read logged-in admin backends, scrape data that has no API, fill out forms, or troubleshoot OpenCLI doctor, session, or adapter failures, or explicitly mentions opencli, browser automation, or tab stealing. For public text, use HTTP first; route topic research to agent-reach; route SEO and keyword decisions to rankup; route backlink selection, submission, and Semrush/Similarweb report interpretation to backlink; this Skill only handles browser driving, sessions, and data retrieval mechanisms.
Comprehensive research and synthesis agent specializing in multi-source information gathering, critical analysis, and integrated knowledge synthesis. Excels at complex research projects requiring systematic investigation across domains, evidence evaluation, and coherent narrative construction.
Load when reflecting on AI collaboration quality or tracking growth over time. Analyzes session history to surface how deeply you think with AI tools and whether your orchestration sophistication matches your cognitive depth. Provides actionable nudges to push toward more strategic work.
Generate evidence-tracked research ideas through an arXiv-based, skill-native Scispark workflow. Use when Codex needs to turn a research keyword, question, paper set, Zotero/library material, or arXiv results into structured facts, testable hypotheses, an initial research idea, technical optimization, mechanism-of-action analysis, human-AI collaboration review, or optional academic slides. Also use when the user mentions Scispark, 科研想法生成, 研究假设生成, 机制优化, MoA, literature-backed idea generation, or 从关键词到研究方案.
Finds high-leverage intervention points in complex systems by mapping feedback loops, identifying system archetypes (fixes that fail, shifting the burden, tragedy of the commons, limits to growth), and ranking interventions by Meadows' leverage hierarchy. Use when problems involve interconnected components with feedback loops, delays, or emergent behavior; when past solutions failed or caused unintended consequences; when identifying where to push for maximum effect; or when user mentions systems thinking, leverage points, feedback loops, causal loop diagrams, stocks and flows, or complex systems.
Use for latest/current/recent/today/yesterday/tomorrow questions, changing models, versions, prices, schedules, executives, laws, weather, scores, or other time-sensitive facts. Ground answers in clock and timezone, verify live when needed, and convert relative dates. Do NOT use for stable history.
Prepare the first working session with a contracted supplier against a fixed day budget: reads the agreed offer or contract, then builds a branded session workbook whose day-budget sheet totals against the contracted ceiling, an internal prep brief, a supplier agenda and a post-session note template. Use for kick-off or delivery-session prep with a supplier, or day-budget splits over a signed offer. Distinct from tor-procurement (writes the ToR), selection-toolkit (panel scoring), procurement-offer-review (one incoming offer), implementation-pack (donor grants IPPF receives), and meeting-notes mode 2 (1-1 prep).
The standing craft of a Chief Product Officer — every strategic question answered in four steps (diagnosis, at least two options with tradeoffs, a clear stance, next steps) under four golden rules. Load it as context when acting as CPO of a workspace; it is also activated by `role: cpo` in that workspace's node.
Fetches a legal open-access copy of a paper from its DOI or arXiv ID — resolves through Unpaywall, arXiv PDF/HTML, and the open-access ACM Digital Library. Use when the user wants to fetch, download, read, or get the PDF or full text of a specific paper. Single polite fetch, transient processing only: it never stores paper text in the repo, never bypasses paywalls, and never uses shadow libraries. For finding papers by topic or venue, use find-papers first; this skill starts from an identifier.
Access Google Workspace (Drive, Docs, Sheets, Gmail, Calendar, Chat, Meet, Admin) via the `gws` CLI. Use this skill when the user wants to read, write, or manage Google Docs, Sheets, Drive files/folders, Gmail messages, Calendar events, or any other Google Workspace resource. Triggers on: Google Docs, Google Sheets, Google Drive, Google Calendar (via gws), Google Chat, Google Meet, spreadsheet operations, document editing, file uploads, sharing permissions, Gmail triage, or any mention of `gws` commands.
Search and retrieve Japanese National Diet (国会) meeting minutes via the official NDL Kokkai API (no auth required). Covers all Diet sessions since 1947, supports keyword search, speaker lookup, meeting-level retrieval, and date/session/issue filtering. Useful for political research, legislative tracking, speech analysis, and any task involving Japanese parliamentary records. 国会発足（1947 年）以降の日本の国会議事録を NDL 国会会議録検索システム API 経由で検索・取得するスキル。発言・会議・キーワード検索および期間/回次/会派による絞り込みに対応。Use this skill when researching Japanese Diet debates, MP statements, or parliamentary records. Not for the Imperial Diet (帝国議会（貴族院を含む）, before 1947-05), which is served by the separate NDL Imperial Diet API.
Operate Open WebUI models, chats, knowledge bases, channels, messages, threads, and files using OPEN_WEBUI_API_KEY. Use when listing models, reading or updating chat history, working with knowledge bases, fetching channel messages, or posting Markdown to Open WebUI.
Reads and analyzes academic papers (arXiv preprints, conference / journal PDFs, Zotero items) at three configurable depths: quick skim (2 min), standard read (10 min), or deep analysis (30 min). Produces structured digests covering problem, method, key innovation, results, limitations, reproducibility, hidden assumptions, and connections to the user's other work. Use when the user shares an arXiv link, PDF, or paper title and asks to read / summarize / digest / TL;DR / analyze / review / critique / explain / break down a paper, asks about a paper's contributions / methods / results / equations / figures, wants to compare two papers side by side, or needs a reading note for their records.
The first Outlook calendar CLI built for AI agents on personal Microsoft 365 accounts — with offline conflict... Trigger phrases: `what's on my calendar today`, `find me an hour next week`, `do I have any conflicts`, `what meetings haven't I responded to`, `prep me for my next meeting`, `schedule a meeting on my Outlook calendar`, `use outlook-calendar`, `run outlook-calendar`.
Autonomous web research agent — takes a research question, uses ScraperAPI to discover and scrape relevant sources, uploads content as file artifacts to the Anthropic Files API, then feeds everything to Claude for synthesis into a cited research report. All in one flow. Use when user asks: "research X for me and give me a cited report", "investigate Y online and summarize what you find", "do a deep dive on Z using real web sources", "find information about X across multiple websites and cite your sources", "run the scraperapi research agent on this topic". Produces a structured markdown report with inline citations and a numbered source list. Invoke whenever the user wants multi-source web research that requires scraping real pages, not just answering from memory. Note: Transmits user-supplied queries, URLs, and content to ScraperAPI; uploads scraped content to the Anthropic Files API.
Official Youdao Note skill supporting basic operations such as note CRUD (create/read/update/delete), to-do management, web clipping, note search, and folder management. To build a knowledge base or wiki, use the youdaonote-llm-wiki skill instead of this skill.
Download live chat transcripts from YouTube videos. Use when the user asks for live chat, chat messages, or chat replay from a YouTube video and provides a YouTube URL (youtube.com/watch?v=, youtu.be/, or similar). Works with live streams and past streams that have chat replay enabled.
Multi-platform, multi-channel notification skill for AI code agents. Sends notifications (sound, macOS alert, Telegram, Email, Slack, Discord, DingTalk) when the agent needs user interaction or completes a task. Supports Claude Code, GitHub Copilot CLI, Cursor, Codex, Aider, and OpenCode.
Query the Semantic Scholar academic corpus through AI2's Asta MCP server: keyword or title search with venue and date filters, who-cited-a-paper traversal, author profiles and publications, DOI/arXiv/PMID lookup, and ~500-word full-text snippets for evidence, with citation counts and h-index. Use when the user asks for papers on a topic, who cited a paper, an author's work, recent literature since a date, or a venue-scoped paper list. Requires the Asta MCP server.
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.