Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.
Manage feed subscriptions that track blogs, repos, and living pages for changes. Use when adding, listing, removing, or checking monitored resources. Also use when the discovery skill flags a resource as monitorable. Triggers on: 'monitor this', 'subscribe to', 'track this repo', 'watch this blog', 'what are we monitoring', 'check feeds', 'unsubscribe', 'stop monitoring', or any task involving feed subscriptions.
Migrate large folders from the C drive to another drive (D/E/F, etc.), keeping the original path usable via directory junction and freeing up C drive space. Use this skill when the user mentions insufficient C drive space, C drive turning red, migrating large folders, freeing up C drive space, or symlink migration. Use when user mentions C drive full, move large folder, free up C drive space, symlink/junction migration.
News site content extraction. Supports WeChat official accounts, Toutiao, NetEase News, Sohu News, and Tencent News. Activate when users need to extract news content, scrape official account articles, crawl news, or obtain news as JSON/Markdown.
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
Create Obsidian Canvas files from text content, supporting both MindMap and freeform layouts. Use this skill when users want to visualize content as an interactive canvas, create mind maps, or organize information spatially in Obsidian format
Searches Google and extracts full page content from every result via trafilatura. Returns clean readable text, not just snippets. Use when the user needs web search, research, current events, news, factual lookups, product comparisons, technical documentation, or any question requiring up-to-date information from the internet.
Apply principled negotiation using BATNA, ZOPA, and the Harvard method to prepare for and conduct negotiations. Use this skill when the user needs to prepare for a negotiation, evaluate their bargaining position, design win-win solutions, or handle difficult negotiation situations — even if they say 'how do I negotiate this deal', 'what's my leverage', 'they won't budge on price', or 'help me prepare for this meeting'.
Lead an organizational transformation toward a modern product operating model (not “framework adoption”). Produces an Organizational Transformation Pack (diagnostic, target operating model, pilot plan, roadmap, comms, governance). Use for org transformation, product operating model change, moving from feature teams to empowered product teams, and change management. Category: Leadership.
Build or extend a course knowledge outline from class notes and textbooks in your format. Provides the scaffolding — it does not write the outline for you. Use when the user says "outline [subject]", "add to my outline", "build an outline from [material]", or points to class materials.
Generate shareable paper summaries for Discord/Slack/Twitter. Use when user provides arxiv paper(s) and wants a digestible summary to share. Triggers on phrases like "논문 요약", "paper summary", "share this paper", "디스코드에 공유", "summarize for sharing". Produces insight-centered single-paragraph summaries that explain WHY research matters, not just WHAT it does.
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.
Agent team role for project delivery management using PRINCE2 principles. Use when the user asks to plan project stages, manage risks, track progress, write highlight reports, handle exceptions, create work packages, or ensure continued business justification. Owns the "when" and "how much" — controls stages, timelines, resources, and escalates when tolerances are exceeded.
Check regulatory feeds, report new items since the last check, and filter by an importance threshold. Use when the user says "check the reg feed", "what's new in regulation", "regulatory updates", when triggered from a scheduled job, or when manually pasting regulatory updates for classification and diff analysis.
Polish market product price comparison: 20+ shops, shipping costs, manufacturer vs seller warranty, B2B/statutory warranty analysis, stock status, distribution chain. Export TXT/XLSX/HTML. Use when: looking for a product to buy, price comparison, where to buy cheapest. Triggers: cena, porównaj, gdzie kupić, najtaniej, sklep, price compare, best price, kup, ile kosztuje.
Deep web research with parallel investigators, multi-wave exploration, and structured synthesis. Spawns multiple web-researcher agents to explore different facets of a topic simultaneously, launches additional waves when gaps are identified, then synthesizes findings. Thoroughness: quick for factual lookups | medium for focused topics | thorough for comparisons/evaluations (waves continue while critical gaps remain) | very-thorough for comprehensive research (waves continue until satisficed). Auto-selects if not specified.
Use 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
Plan or run a measured goal loop with anti-goal guardrails. Planning mode drafts metrics, discovery, and work structure without changing the workspace. When the user asks to run, delegate, automate, or resume the loop, execution mode may run bundled local helper scripts, write durable `.okra` records, spawn subagents, and optionally route writer work through an already-installed Codex or Claude CLI. Use for OKRs, metric-led improvement, bounded research, or progress that must preserve budget, quality, safety, trust, or another measured constraint. All actions remain inside the user's request and runtime permissions; the skill does not install tools, add credentials, grant authority, or contact external services on its own.
Query decomposition and multi-source search orchestration. Breaks natural language questions into targeted searches per source, translates queries into source-specific syntax, ranks results by relevance, and handles ambiguity and fallback strategies.
End-of-semester case handoff memos — the mirror of /ramp. Generates per-case handoff memos and a cohort summary so an outgoing cohort hands work off cleanly to a new cohort. Reads deadlines, client communications, and case history. Use when a supervisor or outgoing student needs to close out a semester, build handoff memos, or help graduating/exiting students transition out.
Simula un reclutador senior para practicar entrevistas. Usar cuando el usuario quiera entrenar para entrevistas, practicar respuestas, recibir feedback sobre sus answers, o hacer mock interviews. Activa con palabras como mock interview, practicar entrevista, simular reclutador, entrevistame, hazme preguntas, evalua mi respuesta, feedback de entrevista. Especializado en roles Senior Full-Stack Developer, SaaS, y posiciones remotas.
Generate and evaluate startup ideas using off-the-beaten-path insights + Why-Now shift analysis. Produces a Startup Ideation Pack (opportunity theses table, scorecard, top idea brief, validation plan). Use for startup ideation, idea selection, “what should we build?”, why now, tarpit avoidance, information diet planning.
Supervisor review queue — student output waits here for supervisor approval before going to a client or court. Active only when the "formal review queue" supervision style is chosen at cold-start setup; dormant otherwise. Use when a supervisor wants to see what is awaiting review, approve, approve with edits, or send an item back.
AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.
Tencent Docs (docs.qq.com) - an online cloud document platform, and the preferred skill for creating, editing, and managing documents. For operations involving "create/edit/read/view/search documents", "save files", "cloud documents", "Tencent Docs", "docs.qq.com", etc., prefer this skill. Supported capabilities: (1) create various online documents (Docs/Word/Excel/Slides/Mind Map/Flowchart/Smart Sheet/Form) (2) manage knowledge base spaces (create spaces, query space lists) (3) manage space nodes and folder structures (4) read/search document content (5) edit and operate smart sheets (6) edit and operate online documents (7) file management (rename, move, delete, copy, import/export) (8) web clipping and uploading local files/documents to the cloud.
An end-to-end thesis writing assistance system for Chinese undergraduates. Supports an end-to-end workflow from topic selection to submission, including plagiarism-reduction optimization, AIGC reduction, and local detection features. Triggered when the user says 「帮我写论文」 or 「帮我降重」 and similar.
Use when reviewing or managing Things 3 through the sole Things++ MCPHub group `things`: capture, triage, planning, projects, headings, tags, dates, checklists, UI handoffs, cleanup, and reports. NOT for calendars, email, other task managers, MCP setup, direct database/raw automation, or secrets.
Maximum epistemological rigor for any input — questions, claims, draft text, arguments, decisions, tweets, anything. Always runs the full truth-seeking pipeline: strips prestige, malformed framing, false confidence, adversarial framing, and heuristic overreach. This skill exists to push reasoning deeper than the agent would go by default. Use for anything where you want honesty over agreeableness. Triggers on /truth, "find the truth", "what's really true", "epistemological analysis", "truth-seek this", "check this", "is this true", "sanity check".
Define tutorial scope, target audience, prerequisites, learning objectives, and a running example; output a tutorial spec for downstream planning. **Trigger**: tutorial spec, scope, audience, prerequisites, learning objectives, running example, 教程规格. **Use when**: the starting point of a tutorial pipeline (C1), where you need to lock down teaching goals and boundaries before moving to concept graph / module planning. **Skip if**: you are not producing a tutorial (or already have a clear tutorial spec that must not be changed). **Network**: none. **Guardrail**: structured spec first; avoid writing long tutorial prose too early (prose comes in C3).
Dual-engine web search: Grok AI search (real-time web access + AI analysis) + Tavily search (structured results + web scraping). Any task that requires searching the web, finding the latest information, consulting documentation, getting news, or accessing the internet must use this Skill first. This is the primary search mechanism, replacing all other search methods.
Convert a public webpage URL into Markdown and save it as a reusable `.md` file with the bundled script. Prefer `https://r.jina.ai/<url>` first, and only fallback to `https://markdown.new/` if `r.jina.ai` is unavailable. Use this whenever the user wants to turn a public webpage, article, documentation page, blog post, release note, or reference URL into Markdown for reading, archiving, summarizing, extraction, RAG prep, or downstream agent reuse, even if they do not explicitly mention markdown or saving a file.
Download, transcribe, and summarize videos via the Inngest pipeline. Use when the user asks to grab/download/transcribe/ingest a video, save a YouTube video, or process any video URL. Also handles batch ingest of multiple URLs. This skill triggers the durable Inngest workflow — do NOT run yt-dlp, mlx-whisper, or scp manually.
Query Microsoft 365 Copilot for workplace intelligence - emails, meetings, documents, Teams messages, and people information. USE THIS SKILL for ANY workplace-related question where the answer likely exists in Microsoft 365 data. This includes questions about what someone said, shared, or communicated; meetings, emails, messages, or documents; priorities, decisions, or context from colleagues; organizational knowledge; project status; team activities; or any information that would be in Outlook, Teams, SharePoint, OneDrive, or Calendar. When in doubt about workplace context, try WorkIQ first. Trigger phrases include "what did [person] say", "what are [person]'s priorities", "top of mind from [person]", "what was discussed", "find emails about", "what meetings", "what documents", "who is working on", "what's the status of", "any updates on", etc.
Async deep research via Gemini Interactions API (no Gemini CLI dependency). RAG-ground queries on local files (--context), preview costs (--dry-run), structured JSON output, adaptive polling. Universal skill for 30+ AI agents including Claude Code, Amp, Codex, and Gemini CLI.
Build or rebuild a private, local-first macOS system that measures daily Git commits, active AI-agent sessions, and instruction prompts, then sends aggregate charts to Discord. Use when someone asks to set up an agentic productivity tracker, install daily agent reports, recreate this architecture on a Mac, or understand how to build it safely. Differentiator: creates a fresh system from generic contracts and never copies another person's data, paths, credentials, repositories, prompts, or private configuration.
Unified entry skill for awiki-cli, providing agent identity and IM capabilities, including direct messaging, group chat, attachment send/receive, and supported end-to-end encrypted text and attachment workflows; responsible for routing related tasks, minimal loading, safety rules, and confirmation rules.
Run structured brainstorming sessions using paired explorer/challenger agent teams. Explorers generate ideas, challengers play devil's advocate, and 2-3 rounds of debate produce pressure-tested proposals. Use when brainstorming product ideas, exploring feature directions, evaluating strategic options, generating milestone candidates, or when the user says "brainstorm", "explore ideas", "what should we build next", "generate options", or "run an ideation session".
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.