Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Deploy infrastructure to LocalStack using IaC tools. Use when users want to deploy Terraform, CDK, CloudFormation, SAM, or Pulumi to LocalStack, or need help with the lstk proxy commands (lstk terraform, lstk cdk, lstk sam, lstk aws) or the pulumilocal wrapper.
Design an iconic, memorable logo with full creative freedom, then turn the final mark into an app asset package (iOS, Android, macOS, Windows, favicons, PWA, social) and, on request, a brand guidelines document. Use when the user asks for a logo, brand mark, wordmark, app icon, visual identity, or brand guidelines.
Maintain the LovStudio website's partners section AND align partner logo rows on event posters / hero strips: reuse lovstudio-find-logo for brand logo discovery, normalize collected logos to a 240px-tall content canvas (retina-ready), rasterize SVGs via rsvg-convert before normalizing (so SVG viewBox padding gets cropped), strip embedded background rects from icon-style SVGs, composite icon + wordmark when only an icon is available (using brand fonts), wrap logos in a fixed-size grid box (96×30 with subtle border) for stable matrix layouts, replace existing logos with user-provided files, append new partners to the PARTNERS array with i18n taglines across zh-CN/en/ja/th, and audit the section for dead URLs / missing files / missing translations. Also handles cross-asset visual height parity (multi-logo strips on dark backgrounds, "logo 不等高", unified-color filter recipe). Trigger when the user mentions "合作伙伴", "partners", "trusted by", "新增 logo", "标准化 logo", "替换 logo", "审计合作伙伴", "维护合作伙伴", "logo 不一样高", "logo 对齐", "logo 大小不一致", "logo 颜色不统一", "logo 不清晰", "logo 糊了", "矩阵格子", "等宽 box", "图标加文字", "compose wordmark".
Review pull request feedback with discerning judgment. The lynx scans comments, identifies legitimate concerns, addresses minor issues directly, and plans responses to significant feedback. Use when responding to PR reviews and addressing reviewer concerns.
lyt series cross-border e-commerce knowledge check skill. Uses a concrete scenario question to test the user's conclusions, evidence, causal chains, applicable boundaries, and verification actions, without requiring rote memorization of fixed answers; it prioritizes checking the current lyt-learning content, and can also check product selection, traffic, advertising, data, content, supply chain, and business assumptions. When the user pushes back on the diagnosis, it follows a conclusion-stability protocol and does not change its position just because the user insists.
lyt series business learning skill. Handles only learning topics related to cross-border e-commerce, TikTok Shop, e-commerce operations, product selection, advertising, data, content, supply chain, business models, or AI workflows; it must reject non-business and non-e-commerce topics. Used when the user says "teach me a topic", "continue to the next article", "write the next article based on my feedback", "create a continuous learning plan", or "save the course"; it breaks the topic into a series of continuous learning articles, adjusts difficulty based on the previous round of feedback, and forms a "learn, check, fill gaps, learn again" loop with lyt-knowledge-check. Trigger methods: /lyt-learning, "teach me a topic", "continue to the next article", "write the next article based on my feedback", "create a continuous learning plan"
List, fetch, patch, fully update, delete, and stop queued calls for Bolna v2 voice agents. Use when the user wants to inspect agent configuration, change prompts or voices, back up an agent, decommission an agent, or cancel all queued calls for one agent.
Search, buy, list, and delete Bolna-hosted phone numbers (DIDs). Covers US (Twilio) and India (Plivo, Vobiz) regions; pattern / region filtering; `$5/month` flat pricing; the buy → inbound-setup wiring; and India regulated 140/160-series compliance prerequisites. Use when the user wants to purchase a dedicated outbound caller ID, set up an inbound line, inspect their DID inventory, or understand which Indian region/provider to pick. For SIP-trunk DIDs (BYOT), use `setup-sip-trunk` instead.
Create, list, patch, delete, and inspect usage for Bolna enterprise sub-accounts. Sub-accounts provide isolated workspaces with auto-provisioned API keys (prefixed `sa-`), per-tenant agents/calls/phone-numbers/batches, and per-sub-account usage reporting for billing. Use for agencies, multi-tenant platforms, departments, regions, or regulated data boundaries. **Enterprise feature** — requires org admin access.
Manage DNS records, TTL strategies, and DNS-as-code automation for infrastructure. Use when configuring domain resolution, automating DNS from Kubernetes with external-dns, setting up DNS-based load balancing, or troubleshooting propagation issues across cloud providers (Route53, Cloud DNS, Azure DNS, Cloudflare).
Trigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "explain like 3Blue1Brown", (4) User wants to plan a Manim video or animation sequence, (5) User asks to "compose" or "plan" a math/science visualization. Transforms vague video ideas into detailed scene-by-scene plans (scenes.md). Conducts research, asks clarifying questions about audience/scope/focus, and outputs comprehensive scene specifications ready for implementation with ManimCE or ManimGL. Use this BEFORE writing any Manim code. This skill plans the video; use manimce-best-practices or manimgl-best-practices for implementation.
Sets up tracking, dashboards, attribution, and experiment infrastructure. Triggers for 'GA4', 'GTM', 'analytics', 'dashboard', 'attribution', 'measurement', 'tracking setup', 'UTM', or 'experiment infrastructure' — not CRO hypotheses themselves.
Material Design 3 (Material You) design system knowledge for modern web and Angular applications. Use when implementing Material Design 3 theming, components, typography, color systems, dynamic color, accessibility patterns, or migrating from Material Design 2. Covers design tokens, theming APIs, and Material You principles.
.NET MAUI runtime permissions guidance — checking and requesting permissions, PermissionStatus handling, custom permissions via BasePlatformPermission, platform-specific manifest/plist declarations, and DI-friendly service patterns. USE FOR: "request permission", "check permission", "PermissionStatus", "runtime permission", "BasePlatformPermission", "custom permission", "Android manifest permission", "Info.plist permission", "permission denied handling". DO NOT USE FOR: geolocation-specific permissions (use maui-geolocation), camera/photo permissions (use maui-media-picker), or notification permissions (use maui-local-notifications).
.NET MAUI Shell navigation guidance — Shell visual hierarchy, AppShell setup, tab bars, flyout menus, URI-based navigation with GoToAsync, route registration, query parameters, back navigation, and navigation events. USE FOR: "Shell navigation", "GoToAsync", "AppShell", "tab bar", "flyout menu", "route registration", "query parameters navigation", "back navigation", "Shell tabs", "URI navigation", "navigation events". DO NOT USE FOR: deep linking from external URLs (use maui-deep-linking), data binding on pages (use maui-data-binding), or dependency injection setup (use maui-dependency-injection).
Structure and format meeting notes following PM best practices. Use when asked to create meeting notes, format discussion notes, capture action items, or document decisions from any meeting type. Produces structured notes with decisions, action items (owner + deadline), open questions, and next steps.
Automatically generates meeting minutes in French from a Teams transcript (.vtt) and optionally an attendance report (.csv). Then optionally offers to create GitLab/GitHub follow-up issues from the minutes. Agnostic by default, with an auto-detected enriched mode for the hexagone-monorepo project. Use when the user provides one or two Teams file paths in the prompt and asks to generate minutes.
MERN stack patterns including React with Vite, Express middleware, MongoDB schemas, API Gateway architecture, session management, error handling, and testing strategies. Activate for MERN development, microservices architecture, and full-stack JavaScript applications.
Expert guidance for creating stunning, professional 2025 UI designs using Tailwind CSS and shadcn/ui. Ensures clean minimal aesthetics, 8px grid consistency, mobile-first responsive patterns, and WCAG accessibility compliance. Use when designing interfaces, reviewing UI, creating components, or when visual design needs modern professional standards.
INTERPRETS the latest public news / 消息面 for ONE user-specified stock: extracts key events, judges impact direction (bullish/bearish/neutral/多空研判), returns a structured digest with evidence links. Output is ANALYSIS/CONCLUSION, not a raw news list. TRIGGER when: single stock + interpretation verb (解读/解析/分析/研判/怎么看/如何看/看法/点评/总结/摘要/归纳/概括/提炼/消息面分析/利好利空/多空研判/ interpret/analyze/summarize/digest/impact analysis/takeaway). SKIP: raw news listing (最新新闻/最新消息/latest news without interpretation verb) → moomoo-news-search; community sentiment/评论/情绪 → moomoo-comment-sentiment; bare ticker without interpretation verb; multiple stocks; price/quote/K线/异动/trade. Hard rule: 新闻/消息/news alone NEVER triggers — interpretation verb MUST be present
Networking systems for multiplayer building games. Use when implementing networked construction, delta synchronization, client prediction, or conflict resolution. Server-authoritative model with optimistic client prediction for responsive gameplay.
Based on the East Money database, supports natural language search across the latest announcements, research reports, financial news, exchange updates and official policies, covering global market assets. It can be used for hotspot detection, sentiment monitoring, quick research report reviews, in-depth announcement reading and investment decisions. Natural language search for financial information, covering authoritative sources including news, announcements, research reports, and policies. Supporting global market assets, it is applicable to event tracking, market sentiment monitoring, announcement analysis, and investment decision-making, helping users obtain authoritative financial information and capture timely market signals.
Make printable technical documents in the style of Apollo-era NASA paperwork. The model is an Apollo Operations Handbook "Systems Data" page with a typed running head, numbered paragraphs, Leroy-lettered line drawings and schematics, a performance data table, NOTE/CAUTION/WARNING notices, a Flight Data File checklist card, a black thumb tab and a dated footer, rendered to an A4 or US Letter PDF. Use this whenever someone asks for NASA-style, Apollo-style, retro aerospace or "mission manual" documentation. Also use it for a technical explainer, spec sheet or one-pager that should look like vintage engineering paperwork, for a handbook page explaining a product, codebase, system or fictional gadget, or for "another one of those NASA pages", even if they never say Apollo or handbook.
Neta character-forging skill - guides users through creating or updating anime/cultural IP/original character (OC) VToken (virtual Token, TCP). Includes the full creation flow with visual preview, character documents, and backstory confirmation. Use this skill when users want to create a new character, modify an existing character, or start character design.
Best practices for building integrations with NetBox REST and GraphQL APIs. Use when building NetBox API integrations, reviewing integration code, troubleshooting NetBox performance issues, planning automation architecture, writing scripts that interact with NetBox, using pynetbox, configuring Diode for data ingestion, or implementing NetBox webhooks and branching workflows.
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices. Use when creating Node.js servers, REST APIs, GraphQL backends, or microservices architectures.
Programmatic access to Google NotebookLM via the notebooklm-py CLI and Python API. Use this skill whenever the user wants to create notebooks, add sources (URLs, YouTube, PDFs, files), generate audio overviews/podcasts, videos, slide decks, quizzes, flashcards, infographics, reports, mind maps, or data tables from their research materials. Also use when the user mentions NotebookLM, wants to turn documents into podcasts, generate study materials, or automate any NotebookLM workflow — even if they don't explicitly say "NotebookLM". Triggers on: podcast from documents, audio overview, NotebookLM, notebook research, generate quiz from PDF, flashcards from notes, study materials, deep dive audio.
(NS) Generate structured requirements.md from scope descriptions, stack context, and design briefs for a product version. Use when starting a new version, the user asks for requirements, RF/features document, or before task generation when requirements.md is missing — even if they only describe the feature in chat. Follow SDD planning gates in ns-harness. Do NOT generate task files (use ns-sdd-task-generator).
This skill should be used when managing objectives - coherent goals that require 2+ plans/PRs to complete. Use when users want to create multi-plan tracking documents, log progress across related PRs, capture lessons learned, or coordinate work that spans multiple erk-prs. Objectives are human-first coordination documents, not executable plans.
This skill should be used when the user asks to "review a PR", "review pull request", "PR review", "check this PR", "analyze PR changes", "review PR #123", "what's wrong with this PR", "is this PR safe to merge", "review my changes", "review local changes", "review my code", "review staged changes", "review my diff", or needs expert code review with architectural analysis, defect detection, and security scanning. Supports both remote PRs and local changes (staged/unstaged). Uses Octocode MCP tools for deep code forensics and holistic evaluation.
Offload heavy builds, full test suites and parallel experiments from the local machine to Vercel Sandboxes with the `vercel sandbox` CLI. Use when a local machine is overloaded or shared by several agents, when a test suite should be sharded, or when many tasks should run side by side without consuming local CPU, memory or disk.
Generate covers for Xiaohongshu and Bilibili AI tool walkthrough videos, with script mode and autonomous Agent mode, real video evidence, three aspect-ratio outputs, and an optional creator avatar. Trigger only when the user explicitly mentions oil-cover, $oil-cover, uses oil-cover, or names this Skill; do not auto-trigger for ordinary cover, thumbnail, or video cover requests.
Use this if the user wants to connect to Ollama or leverage Ollama in any shape or form inside their project. Guide users integrating Ollama into their projects for local AI inference. Covers installation, connection setup, model management, and API usage for both Python and Node.js. Helps with text generation, chat interfaces, embeddings, streaming responses, and building AI-powered applications using local LLMs.
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.