Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
A complete coaching skill for Taiwanese nurses writing evidence-based nursing reports (evidence-based reading reports, evidence-based case analyses), designed for N1–N4 promotion in the nursing clinical ladder system and for the review formats of the Taiwan Nurses Association and the Taiwan Evidence-Based Nursing Association. Trigger this skill whenever the user mentions "實證護理報告", "實證案例分析", "實證讀書報告", "N2 報告", "N3 報告", "N4 報告", "護理進階報告", "護理升等", "PICO", "5A 步驟", "CASP 評讀", "護理 EBP", "EBN", "evidence-based nursing", "實證照護", "證據等級", "文獻評讀", or whenever a nurse asks about promotion writing, turning a clinical question into an evidence-based topic, evidence search strategies, CASP appraisal forms, Oxford levels of evidence, APA 7th edition format, applying an evidence-based intervention to a case, challenging nursing routines, or dispelling nursing myths. Even if the user only casually asks "我要寫報告", "我要升 N3", "幫我找主題", "幫我設 PICO", or "這篇文獻要怎麼評讀", you should proactively activate it to provide complete structure, sentence patterns, and writing strategies with the highest review pass rate.
Search scientific papers and retrieve structured experimental data extracted from full-text studies via the BGPT MCP server. Returns 25+ fields per paper including methods, results, sample sizes, quality scores, and conclusions. Use for literature reviews, evidence synthesis, and finding experimental details not available in abstracts alone.
Apply Theory of Constraints (TOC) to identify and manage system bottlenecks. Use this skill when the user needs to find what limits throughput, optimize a constrained process, apply the Five Focusing Steps, or implement Drum-Buffer-Rope scheduling — even if they say 'our output is stuck', 'what's the bottleneck', or 'why can't we produce more'.
ALWAYS use this skill before answering brainstorming, ideation, prompt crafting, or open-ended exploration requests. Transforms vague requests into actionable outputs via adaptive guided questioning — triages into Prompt Mode (craft/improve prompts), Explore Mode (brainstorm ideas), or Focused Mode (specific problem strategies). Trigger when user says: "brainstorm", "ช่วยคิด", "help me think", "I have an idea", "improve this prompt", "let's explore", "I want to build", "I'm thinking about", "brainstorm วิธี", "ช่วยคิดหน่อย", "อยากทำ", "ยังไม่รู้จะทำอะไร", "not sure about the approach", "help me figure out", "what should I". Also trigger for: side projects, career decisions, project planning, migration strategies, architecture decisions, cost optimization, or any request where the user hasn't decided direction yet and would benefit from structured discovery. Do NOT skip — adapts depth automatically (2-7 questions) and produces BETTER results by asking targeted questions first.
Use the cbrain CLI to work with your organization's knowledge brain: search semantically, read and write company knowledge, and inspect the current identity. Use this skill when answering questions about the company's people, projects, customers, meeting notes, policies, or past decisions, or when saving new meeting notes, documents, or conclusions to the shared company knowledge base. Mandatory discipline: identify the brain first → search before answering (never fabricate) → cite every conclusion with [[source]] → treat anything not found as nonexistent.
Log client communications — phone, email, text, letter, meeting, voicemail. Append-only per matter, with dated entries, direction, medium, summary and action items. Works with /client-letter and /status client. Use when logging a call or client email, reviewing the communications log, or asking "what did we last tell [client]"
Cold-call preparation — anticipate the questions the professor may ask and drill them with Socratic follow-ups, flagging your weak spots to review before class. Use when the user says "prep for tomorrow's class", "cold call [case]", "what might [professor] ask on [case]", or points to assigned reading.
Review open comment periods, record decisions, track deadlines. Use when a draft's comment window is open and you need to surface deadlines, decide whether to file comments, or record a submitted/not-filed/withdrawn decision (--decide CMT-ID).
Shape a fuzzy or half-formed idea through Socratic dialogue — crystallized intent, not solutions or a plan yet. Use when the user has vague product intent and needs clarity before design pressure-testing or implementation. Not for design-tree pressure-tests (grill), written plan review (second-opinion), or code-path hunches (investigate).
Daily journal management for the my-vault Obsidian vault. Use for morning routines, daily reviews, quick journal updates, checking yesterday's entry, or setting today's highlight. Triggers on "good morning", "daily review", "journal", "what did I do", "highlight".
Track case deadlines — add, cross-matter rollup reports, update, complete, close. Warn at configurable thresholds (default 14/7/3/1 days); overdue items stay flagged until resolved. An operational record of clinic workload. Use when a student or supervisor needs to add a deadline, see what's due this week, get a deadline report, or update a case deadline.
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs
Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs
Analyze past exams from the same instructor to surface patterns — subject weightings, recurring issue traps, preferred case-hypothetical types, the ratio of policy vs. rule analysis — and forecast what this year's exam is likely to emphasize. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
Kick off workforce expansion planning in a new province/municipality or region — gather baseline information, run the labor dispatch vs. business outsourcing vs. direct employment structure framework analysis, draft a cross-functional question list, surface region-specific risk flags, and create an ongoing tracking file. Use when someone says "we're hiring in [region]", "expanding to [province/municipality]", or "first hiring in [region]".
Update the status of an in-flight cross-region workforce expansion project — recalculate items that are now unblocked, flag any that are overdue, surface the next priority. Use when work has progressed since the last session and the expansion tracking file needs to reflect the current state.
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.
Reference: shared gap and comment-tracking framework supporting /regulatory-legal:gaps and /regulatory-legal:comments. Tracks open policy gaps and their remediation status, pulls gaps from policy-diff, surfaces open and upcoming items, routes them to owners, and notifies gap owners through enterprise messaging tools, with confirmation before each send. Loaded by the gaps and comments skills before substantive work.
Connect to Dedao Brain via the official getnote CLI to handle browser authorization, connection diagnostics, CLI upgrades, and to save, query, search and manage real notes. Use when the user wants to save links/images, upload files to the knowledge base, check file limits, read highlights/germination reports/timelines, organize the knowledge base/folders, subscribe to creators, manage tags, or explicitly asks to log in, diagnose, or upgrade; it will not install or update the Skill on its own.
Apply ethnographic methods including prolonged engagement, participant observation, thick description, and netnography to study cultures and communities. Use this skill when the user needs to design fieldwork with immersive observation, interpret cultural practices through thick description, study online communities via netnography, or when they ask 'how do I study a culture or community', 'what is participant observation', or 'how do I apply ethnography to online settings'.
Render and view webpages using a headless browser (Playwright) to fetch JS-rendered HTML, extract visible text, and optionally save full-page screenshots. Use when a user asks to “无头浏览器打开/查看网页”, needs the rendered DOM instead of raw curl HTML, or wants a screenshot of a page.
Apply Socratic questioning — systematic inquiry via clarification, assumption-probing, evidence-testing, perspective-shifting, implication-tracing, and meta-questions — to coach learning or surface hidden assumptions in a person's reasoning. Use this skill when the user is explicitly facilitating learning, coaching a person through their own thinking, or needs a structured questioning sequence to probe a held belief, even if they say 'play devil's advocate on this claim' or 'how should I coach my team through this problem via questions'. Do NOT use for open-ended brainstorming, information gathering, or requirements-discovery question lists where no belief is being probed.
Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.
Reference: implementation-planning framework for international hiring — EOR vs. entity decision framing, cross-functional triggers for tax/finance/HR, structured outside-counsel briefing requests, and a persistent gap tracker. Loaded by /expansion-kickoff and /expansion-update; not invoked directly.
Query an in-progress investigation log — what witnesses said, where statements contradict each other, what evidence gaps exist, and what the most probative evidence is on each issue. Use when a lawyer needs to query the investigation record without re-reading every entry.
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
Teach users any decomposable subject or system through “orientation → minimal example → expand component by component → visualize the whole.” Use when the user wants to learn a framework, library, algorithm, protocol, business process, or concept by starting with the smallest runnable or hands-on demo, understanding each component step by step, and then seeing the overall structure. Triggers: “teach me XXX,” “learn XXX with a minimal demo,” “teach me XXX from scratch,” “learn XXX step by step,” “learn XXX with a minimal example,” “learn-by-minimal XXX.” Also applies to requests like “I want to understand how React/Vue/TCP/quicksort/the order placement flow is put together.” Not for pure fact lookups, code debugging, one-off questions, or simple questions that don't need structured, progressive learning.
Check in-progress leave for deadline warnings and decisions that need to be made. Surfaces only the leave that needs action, with the reason — not a status dashboard. Recommended weekly, or whenever a lawyer needs to know which leaves have upcoming approval, certification, or expiry deadlines.
Activates when the user is about to apply a successful methodology (someone else's or their own past one) to a new scenario. Typical trigger signals: "company X succeeded with method X, we should try it too", "this worked for me before, let's keep doing it", "the industry best practice is Y". When not to invoke: the user faces a recurring instance of the same kind of problem and needs execution, not methodology selection. Difference from "contradiction analysis": this skill emphasizes "each problem differs in nature and needs a different method", while the latter emphasizes "find the single most important problem".
Karl Marx's persona and thinking operating system. A deep distillation based on primary classics such as Das Kapital, The Communist Manifesto, and The German Ideology, historical context, records of his collaboration with Engels, and contemporary applications. Includes 5 core mental models, 8 decision heuristics, a complete expression DNA, and an Agentic research protocol (for any topic, first investigate material conditions, class dynamics, and economic data, then conduct dialectical critique). Use for: critique of contemporary capitalism, class analysis, theoretical consulting, and academic document creation (seamlessly integrated with docx). Trigger words include "用Marx视角", "马克思会怎么分析", "切换到Marx.skill", "辩证批判", "历史唯物主义视角".
Two-tier memory system that makes Claude a true workplace collaborator. Decodes shorthand, acronyms, nicknames, and internal language so Claude understands requests like a colleague would. CLAUDE.md for working memory, memory/ directory for the full knowledge base.
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.