Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Comprehensive guide for deploying Docker Compose stacks on Dokploy (self-hosted VPS deployment platform). Use this skill whenever the user mentions Dokploy, deploying Docker Compose to a VPS, deploying applications with docker-compose.yml on a self-hosted server, or when troubleshooting Docker Compose stacks running on Dokploy. Covers both Compose (stack) and Application (Git) deployment types, volume strategies, networking, environment variables, init containers, healthchecks, domains with Traefik, and troubleshooting common errors like EAI_AGAIN, permission denied, unhealthy containers, and JWT/config issues. Also applies when deploying any multi-service Docker Compose stack to Dokploy.
Turns a topic into a ranked reading list of the best papers plus a two-column, arXiv-ready literature-review/survey draft grounded in verified citations. Use when a researcher says "write a survey on X", "do a literature review of X", "give me a ranked reading list on X", "what should I read on X first", "draft a survey paper for arXiv", or "two-column related-work survey on X". Searches across DBLP/Crossref/Semantic Scholar/arXiv, ranks candidates by citation impact, venue strength, recency, and citation-graph centrality, clusters them into a taxonomy, verifies every reference, and writes an original-prose survey (intro, taxonomy, per-theme synthesis, open problems) where each claim cites a real, resolved paper. Never fabricates citations, never copies source text — original synthesis only; the author stays the author. Trigger words - survey, literature review, reading list, ranked papers, what to read, arxiv survey, two-column review.
Take real control of the desktop - list and focus windows, type, paste, click, scroll, and screenshot - on Windows, macOS or Linux, and drive other coding-agent sessions running in terminals. Use when asked to set up the screen or the day, open and arrange a set of apps or repos, prepare or run a live demo before recording, test a desktop application that has no headless harness, launch or steer a Claude Code session in another window, or capture what is on screen as evidence. Triggers on "set up my screen", "get my demo ready", "drive the screen", "control my desktop", "open these repos and start", "test this desktop app", "run this on my machine and show me". Not for browser automation, which has its own headless tooling.
Use this skill to configure Education Cloud domains (Student Success, Recruitment & Admissions, Academic Operations, Alumni Relations, Student Management, or Mentoring) through conversational setup. Triggers when a user wants to enable or configure Education Cloud features. Guides step-by-step: enables Person Accounts prerequisite, activates target domain, then configures domain sub-features. Covers support processes, case record types, success teams, care plans, applications, admissions, course catalog, alumni engagement, fundraising, enrollment, programs, and mentoring. Explains each feature, confirms before proceeding, verifies every change took effect, and warns that domain and feature toggles are IRREVERSIBLE. DO NOT TRIGGER for metadata generation, custom objects, or package deployment — this configures existing platform features via org settings, not metadata files.
Native UI integration for Electrobun desktop applications including ApplicationMenu, ContextMenu, system Tray, native dialogs, keyboard shortcuts, and platform-specific UI patterns. This skill covers creating application menus with submenus and accelerators, context menus triggered by right-click, system tray icons with menus, file/folder dialogs, message boxes, notification systems, global keyboard shortcuts, menu item roles, dynamic menu updates, platform-specific menu conventions (macOS menu bar, Windows system menu), drag-and-drop integration, and native theming. Use when implementing application menus, adding system tray functionality, creating context menus, showing file pickers, implementing keyboard shortcuts, displaying notifications or dialogs, or building platform-native UI experiences. Triggers include "menu", "tray icon", "context menu", "file dialog", "shortcuts", "accelerator", "native dialog", "system tray", "notification", "menu bar", or "right-click menu".
Migrate to the next major version of @elevenlabs/client, @elevenlabs/react, and @elevenlabs/react-native. Use when updating code that uses Conversation, Input, Output, useConversation, ElevenLabsProvider, ConversationProvider, or related APIs from these packages. Also trigger when users mention upgrading ElevenLabs packages, fixing breaking changes after an npm update, moving to the latest ElevenLabs SDK, or encountering type errors or runtime errors after updating @elevenlabs/* dependencies.
Answer questions about company policies, benefits, and procedures. Trigger with "what's our policy on", "how does PTO work", "benefits question", "expense policy", "remote work policy", or any question about company rules, perks, or procedures.
ALWAYS-ON: audits plans and code for KISS, YAGNI, DRY, SOLID, and testability; maintains .heyeddi/docs/engineering/. Use on every chat that plans or changes code, before merge, refactor, ADRs, or reuse-catalog work. Not for visual UX (ux-flow-auditor) or full CI (pre-merge-gate includes this audit).
Read, write, and edit EPUB2/EPUB3 ebooks as an EPUB file format expert. Extract text, metadata, structure, and knowledge from EPUB files for enrichment or memory. Create valid EPUBs from scratch. Validate against the EPUB specification. Use when the user mentions epub, ebook, EPUB file, ebook format, read epub, write epub, create ebook, extract from epub, epub to text, or ebook structure. Do not use this skill for unrelated requests; route to the nearest named specialist.
Creates Excalidraw diagrams programmatically. Use when the user wants flowcharts, architecture diagrams, system designs, or any visual diagram instead of ASCII art. Outputs .excalidraw files that can be opened directly in Excalidraw or VS Code with the Excalidraw extension.
Creates studio-quality motion design videos with code (Remotion/React), licensed music, synchronized SFX, optional voice (ElevenLabs or a local TTS model selected based on the hardware), and automated lint and QA gates before delivery. Use for requests involving motion design, motion graphics, animated video, explainers, product or launch videos, animated reels or TikToks, kinetic typography, animated logos, UI animation, loops, video narration or voiceover, or techniques such as keyframing, zoom in and zoom out, motion smooth, morphing, rigging, frame by frame, cel animation, stop motion, rotoscopia, motion tracking, match moving, compositing, motion 3D, speed ramp, match cut, overshoot, parallax, and transitions. Also for animated video, kinetic typography, product launch video, explainer with voiceover, and text-to-speech narration.
AI film director for scene blocking, shot composition, visual storytelling. Use when: directing, blocking, shot design, coverage, cinematography. Generates image prompts for scenes. Keywords: film, directing, blocking, shots, visuals.
Reproduce, inspect, diagnose, and fix Flutter failures in a running app using logs, debugger attachment, DevTools, framework diagnostics, and minimal experiments. Use for runtime exceptions, incorrect live state, hangs, lifecycle failures, or failures that require execution evidence; route benchmarked jank to flutter-performance and planned device-flow verification to flutter-device-testing.
Run repeated build -> QA -> retro -> re0-work cycles while preserving learning and letting code die. Use for long agentic projects where progress must be measured by quality-cleared templates, reusable modules, and eliminated anti-patterns rather than hours spent or features accumulated.
Guides digital forensic evidence collection following NIST SP 800-86 and RFC 3227 order of volatility. Auto-invoked when the user needs to collect forensic evidence, preserve chain of custody, capture volatile data, create disk images, or handle cloud forensics. Produces an evidence collection plan with volatility-prioritized acquisition steps, integrity verification, and chain-of-custody documentation.
Manage a website built with Frappe Builder on a Frappe site from outside the editor. Use to create or edit Builder pages, build or change Builder components (props, scripts, data), retheme a site, build data-driven or dynamic-route pages from the site's DocTypes, make forms that save, add page scripts, or publish, when the site runs the Builder app.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Guide for creating distinctive, production-grade frontend interfaces. Covers visual design systems, typography, color, motion, spatial composition, and web interface standards. Use when designing UI, establishing design systems, or reviewing visual quality of frontend code.
Unusual Derivatives Activity (衍生品异动): detects unusual derivatives signals for a user-mentioned stock with `get_derivative_unusual`, including 牛熊证街货比例、牛熊证街货价格区间、期权大单、隐含波动率、期权量价、期权情绪、期权综合信号 and their unusual changes. Use when the user asks about 期权、衍生品、牛熊证、IV、隐含波动率、PCR、期权大单、期权异常成交、聪明钱、smart money、unusual options activity、做多做空情绪、波动率溢价、期权市场怎么看、有没有大单押注、大资金押注、适不适合卖期权，or gives a broad 异动 request such as “英伟达异动”、“NVDA 异动”、“腾讯有没有异动/异常” without narrowing the dimension. For broad 异动 requests, use together with `futu-unusual-technical-signal-alerts` and `futu-unusual-capital-flows`. Before calling the CLI, first normalize the user-mentioned stock name, Chinese company name, English company name, or ticker into a standard symbol such as `US.NVDA` or `HK.00700`.
Technical Signal Alerts (技术面异动): detects technical unusual signals for a user-mentioned stock with `get_technical_unusual`, including K-line patterns and indicator events such as CCI, KDJ, RSI, BIAS, ARBR, VR, PSY, OSC, WMSR, MACD, BOLL, and MA. Use when the user asks about technical conditions, recent technical signals, K-line patterns, pattern recognition or breakouts, golden/death crosses, overbought/oversold conditions, or any listed indicator, or gives a broad 异动 request such as “英伟达异动”、“NVDA 异动”、“腾讯有没有异动/异常” without narrowing the dimension. For broad 异动 requests, use together with `futu-unusual-capital-flows` and `futu-unusual-derivatives-activity`. Before calling the CLI, first normalize the user-mentioned stock name, Chinese company name, English company name, or ticker into a standard symbol such as `US.NVDA` or `HK.00700`.
Invoke when the user wants to brainstorm game ideas, explore concepts, run structured ideation, or develop a new game concept from scratch. Triggers on: "game idea", "brainstorm", "concept", "ideation", "what if", "game concept", "pitch". Do NOT invoke for reviewing existing designs (use game-design-review) or market analysis (use game-market-research). Part of the AlterLab GameForge collection.
Best practices for GameMaker Language (GML) development, covering scripts, object events, rooms, data structures, and performance-minded game code. Use when writing GML scripts or object event code in GameMaker Studio, structuring create/step/draw events, managing rooms and instances, building state machines for gameplay, or optimizing GML for performance.
Turn a 5-second voiceover script, opinion statement, or abstract concept into an editorial halftone paper-collage assemble-from-empty B-roll video. Use when the user requests "collage b-roll", "paper collage B-roll", "halftone collage", "collage video", "gbro-collage-broll", or asks to convert voiceover lines into animated editorial collage visual metaphors. Enforces a 3-gate approval workflow (metaphor confirmation -> still frame confirmation -> video generation via Gemini Omni Flash).
Creative technologist specializing in algorithmic art, shaders, and generative systems Use when "generative art, creative coding, processing, p5.js, shader art, algorithmic art, art from code, nft art, creative-coding, generative, shaders, processing, p5js, algorithmic-art, nft-art" mentioned.
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
Portable Git workflow skill for AI coding agents that turns messy AI-generated changes into clean Git history. Use for smart Conventional Commits, logical commit splitting, branches, checks, pull and push, GitHub PRs and issues, secret scanning, commit planning, Git status and history, repository diagnosis, and merge or rebase conflict resolution with Claude Code, OpenAI Codex, Cursor, and other Agent Skills-compatible tools.
Google Search Console indexing assistant. Use when the user wants to track page indexing status, compare sitemap against GSC indexed pages, manage submission tracking, or move false positives (pages indexed per URL Inspection but not yet in GSC export) to the indexed list. Maintains two tracking files (indexed.md, to-index.md) with prioritization support.
Use when managing Halo posts, single pages, categories, or tags from the terminal. This includes listing, creating, updating, deleting, exporting, importing, or any content management operation for Halo CMS. Trigger this skill whenever the user mentions Halo posts, pages, categories, tags, or content management in a CLI context, even if they do not explicitly mention 'content'.
Reference library of 35+ hook and headline tactic types. Use this skill when a user asks for hooks organized by tactic, wants to know which tactic to use for a given situation, or requests hooks "by tactic type." This skill defines what each tactic is and when to deploy it. Always pair with the Hook Writing Skill for execution — tactics define the frame, psychological triggers are the mechanism inside the frame.
Diagnose performance issues on Amazon SageMaker HyperPod clusters — uneven NCCL bandwidth across nodes and poor filesystem throughput. Read-only. Surfaces host-side signals (Xid, ECC, NVLink, EFA reachability, FSx saturation) and routes to the appropriate sibling skill (hyperpod-node-debugger, hyperpod-nccl, hyperpod-version-checker, hyperpod-issue-report) for any remediation. Triggers on uneven NCCL across nodes, straggler node, FSx slow, checkpoint slow, dataloader slow, filesystem bottleneck, FSx throughput, cross-AZ latency, topology mismatch.
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.
Integrate InFlow stablecoin payments into any project. Use this skill when the user wants to: accept payments, add a checkout, request a payment, build a payment flow, integrate InFlow, accept USDC/USDT/EURC/PYUSD, set up consumer login via InFlow, register users with InFlow, handle payment webhooks, create spending policies for autonomous agents, build a 0-click headless payment flow, or add InFlow checkout to a marketplace app (note: native multi-recipient splits are not supported by the InFlow API). Also trigger on: 'add inflow', 'inflow payment', 'inflow checkout', 'stablecoin payment', 'crypto payment', 'accept stablecoins', 'pay with usdc', 'inflow webhook', 'inflow login', 'inflow policy'.
Use this skill when writing code that reads, writes, syncs, or reacts to data in an external app. Applies to SaaS products, internal tools, scripts, batch jobs, and CLIs. The skill uses Membrane as the integration engine — it handles OAuth and credential lifecycle (authentication, token refresh, reconnect), exposes vendor operations through a uniform interface, delivers events via webhooks, generates connectors on demand for apps not yet in the workspace, and captures every action run and raw API exchange in structured logs. Works against any external app.
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.