Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Restaurant Video Maker — Create Menu, Ambiance and Promo Videos for Restaurants. The seasonal menu drops Friday and all you own are iPhone shots of plated dishes under fluorescent kitchen light. A thirty-second clip of that duck confit with steam curling off the glaze would pack the dining room — but hiring a videographer for one dinner service costs more than the ingredients. Gather dish photos, dining- room b-roll, and the candlelit ambiance footage the hostess captured on her break. The AI corrects kitchen fluorescents to warm golden tones, pans slowly across each plate with appetizing motion, overlays dish names and prices in your menu typeface, and scores the piece with acoustic guitar that whispers "neighborhood gem." Render a thirty-second Reel tagging your location, a fifteen-second teaser for your Google Maps listing, and a widescreen loop for the TV behind the bar. Swap dishes when the chef rotates the carte without rebuilding anything. Crafted for independent bistros hyping nightly specials, fast-casual chains unifying location content, caterers assembling event lookbooks, and food truck operators who squeeze filming between lunch rush tickets. Supports mp4, mov, webm, jpg, png.
H3 prompt writing for minimalist/Apple-style product ads: product fidelity, English on-screen copy, anchored composition roles, and a beat sheet, producing a final prompt that can be fed to MiniMax H3. Applies to e-commerce/new product film prompts. Not for KOC talking-head scripts or post-production editing notes.
This skill should be used when the user asks to ingest, clean, validate, transform, version, monitor, or serve ML data and features. PROACTIVELY activate for: (1) data ingestion, preprocessing, feature engineering, leakage prevention, train/serving skew, (2) Spark, Dask, Polars, pandas, Ray Data, streaming pipelines, (3) Great Expectations, TFDV, Deequ, data quality and validation, (4) DVC, lakehouse tables, dataset versioning, lineage, reproducibility, (5) Feast, Tecton, Hopsworks feature stores, point-in-time joins, online/offline features. Provides: scalable, reproducible, leakage-safe ML data pipeline design.
Converts mobile workflow markdown into a self-contained Playwright test project with mobile viewports (Chromium + WebKit), authentication scaffolding, UX anti-pattern assertions, and CI workflow. Use when the user says "convert mobile workflows to playwright", "translate mobile workflows to CI", or "generate mobile playwright tests".
Brings the checked-out PR up to date after checking its intent against base changes. MODERNIZE rebases, re-runs checks, and force-pushes with a lease; REWORK or CLOSE stops. Use when the user says "modernize this PR", or when the user explicitly asks to bring a PR up to date or rebase it, or when landing-prs or watching-authored-prs calls it on a conflict. Never infer from a behind branch alone.
MongoDB schema design patterns and anti-patterns. Use when designing data models, reviewing schemas, migrating from SQL, or troubleshooting performance issues caused by schema problems. Triggers on "design schema", "embed vs reference", "MongoDB data model", "schema review", "unbounded arrays", "one-to-many", "tree structure", "16MB limit", "schema validation", "JSON Schema", "time series", "schema migration", "polymorphic", "TTL", "data lifecycle", "archive", "index explosion", "unnecessary indexes", "approximation pattern", "document versioning".
Write MoonBit bindings to JavaScript with `extern "js"`. Use for FFI declarations against browser/Node/Deno APIs or npm packages, wrapping JS objects in opaque types, bridging Promises (`async fn` / `Promise::wait()`), `moon.pkg` exports (esm/cjs/iife), and null/undefined at the JS boundary.
Build, review, debug, migrate, or plan UI animation with Motion for React (motion/react, motion@13). Use for React/Next/Vite: motion.div, AnimatePresence, variants, gestures, drag, layout/layoutId, LazyMotion, useScroll, useAnimate, MotionValues, animateView, AnimateView (motion/react-animate-view, React 19.3), arc(), spring bounce, Reorder grids, reducedMotion, framer-motion→motion, Motion 13 isValidProp, CSS/WAAPI/View Transitions, microinteractions, page transitions, accessibility, and performance-safe animation. Do not use for Vue, vanilla-only Motion, React Native, or non-interactive film/video unless adapting it to product UI.
Plan, direct, and produce code-drawn 2D/3D motion graphics and edited videos (reels, hooks, SaaS/product explainers, talking-head edits) on the user's local machine through any coding agent that has terminal + file access (Claude Code, Codex, Cursor, Claude Desktop, VS Code agents, etc.). Workflow: explain the process → user gives references + story → write a paste-ready ElevenLabs voiceover script → user generates and returns the MP3 → build, preview, render. Uses Canvas/SVG/p5.brush/Three.js/GSAP rendered in headless Chrome, Motion Canvas/Revideo, ffmpeg, small local AI models (cutout, transcription), plus LottieFiles, Freesound, Pexels/Pixabay, Firecrawl and ElevenLabs MCPs, and the Playwright MCP to browse any website visually (Pinterest, Behance, Dribbble, brand sites) and grab image/video assets by itself. Use when the user asks to make, edit, animate, caption, voice, or sound-design a video
Use Mowgli to create and iterate on beautiful designs for your projects with high taste and without the usual AI slop design aesthetic. This skill allows you to push existing designs and product flows to a Mowgli project, or read pixel-perfect React + Tailwind designs from one. Mowgli displays all the product's screens and states on an infinite canvas and allows rapid, natural-language iteration. Due to its unique approach of spec-driven design, Mowgli can help redesign, tweak, visualize and experiment on designs with deep product understanding and context. Combined with this skill, it allows full interoperation with existing codebases and GitHub repos, as well as an easy path from beautiful designs to real implementation.
Use narova whenever the user names Narova or reel.config, or wants a deterministic scene-scripted video: narrated/captioned explainers, multi-host dialogue, prompt/script/README-to-video, product walkthroughs with real browser actions, or source-grounded videos from sites, articles, docs, and repositories. Supports optional local neural TTS, word-synced captions and reveals, music/SFX, platform export presets, SRT/VTT, 2D HTML/CSS/SVG, Three.js/WebGL 3D, mixed compositing, AI clips, and silent marker-driven work. It turns a scene script into MP4 through HyperFrames or the browserless Skia/FFmpeg provider; scene.threeModule is the raw 3D escape hatch. Use plain HyperFrames for unrelated silent motion graphics.
NetBox server administration: configuration, authentication backends (local/LDAP/SAML/OIDC), object permissions, API tokens, performance tuning, backups, upgrades, and housekeeping. Use when managing a NetBox instance rather than consuming its API.
Methodology for migrating data into NetBox from spreadsheets, legacy IPAM/DCIM systems, CMDBs, and unstructured sources. Use when planning or executing a data migration — covers assessment, cleaning, dependency ordering, import strategy selection, validation, and post-migration verification with Discovery and Assurance.
React and Next.js performance optimization from Vercel Engineering. Use when building React components, optimizing performance, eliminating waterfalls, reducing bundle size, reviewing code for performance issues, or implementing server/client-side optimizations.
A skill for writing server-side APIs with the Nitro v3 framework and H3. Use for initialising backend-only Nitro projects, adding full-stack capabilities to Vite projects, writing spec-compliant CRUD endpoints, and database interaction with Drizzle ORM. Use this skill when developing new Nitro endpoints, initialising Nitro configuration, or consulting Nitro development conventions.
Kaggle notebook/kernel lifecycle operations. PROACTIVELY activate for: (1) creating Kaggle notebooks or kernels, (2) `kaggle kernels init`, (3) pushing or running notebooks with `kaggle kernels push`, (4) pulling notebooks with metadata, (5) checking kernel status, files, logs, or outputs, (6) downloading output artifacts with file patterns, (7) deleting kernels, (8) Python API kernel operations, (9) auth for notebook CLI workflows. Provides: safe CLI/Python lifecycle commands, run monitoring, output retrieval, destructive-action guardrails.
Manage Notion notes, pages, and data sources with a JSON-first CLI for search, read/export, write/import, append, and move operations. Use when working with Notion, organising notes, moving pages, triaging an inbox, or reading/writing page content.
(NS) GraphRAG process. Use for GraphRAG, knowledge graph over documents, multi-hop retrieval, entity/relationship extractors, indirect-link analytics, or grounded structured extraction — even if they only say RAG, NER, knowledge graph, or cited Q&A. Do NOT use for Postgres schema/mode alone (`ns-postgres-rag` first). Do NOT use for competing vector stores, free graph QL, or co-occurrence-as-edge.
Open Graph and social sharing image design with platform specs, text placement, and branding. Covers OG meta tags, Twitter cards, LinkedIn previews, and dynamic generation. Use for: social sharing images, blog thumbnails, link previews, social cards. Triggers: og image, open graph, social sharing image, twitter card, social card, link preview image, og meta, sharing preview, social thumbnail, meta image, og:image, twitter:image, linkedin preview
Use when asked to "set OKRs", "objectives and key results", "quarterly OKR planning", "align objectives", "measure OKR progress", or "focus priorities with OKRs". Helps teams focus on what matters most and create a cadence of progress. The OKR framework (originated by Andy Grove at Intel, popularized by John Doerr at Google) creates alignment, focus, and learning cycles. Christina Wodtke's Radical Focus approach emphasizes simplicity and avoiding common pitfalls.
Olares models via olares-cli router — Router (the AI gateway) and the Model Console inside a locally installed model application. Configure cloud vendors and their models, manage local LLM / embedding / audio / OCR model applications, edit a local model's card, name models with aliases, groups and default categories, issue API keys and quotas, read usage and audit, and call a model: chat, embed, rerank, search, scrape, translate, images, video, music, 3D, transcribe, speak, diarize, OCR. Requires Olares 1.12.7+. Use for Router, llm-gateway, AI gateway, 模型, 模型网关, 本地模型, add an OpenAI/Anthropic/DeepSeek key, install a Qwen or Gemma model, sk- key, model quota, token spend, model alias, default-chat, engine_args, which model answers by default, why a model call fails.
When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value. Also use when the user mentions "onboarding flow," "activation rate," "user activation," "first-run experience," "empty states," "onboarding checklist," "aha moment," or "new user experience." For signup/registration optimization, see signup-flow-cro. For ongoing email sequences, see email-sequence.
Create stunning, animation-rich HTML presentations from scratch or convert PowerPoint files (.ppt/.pptx) to beautiful web slides. Use when the user wants to build a pitch deck, presentation, slideshow, or slide deck — or convert an existing PPT to a web presentation. Generates zero-dependency single HTML files with keyboard/touch navigation and scroll-triggered animations. Style options include Neon Cyber, Bold Signal, Swiss Modern, Paper & Ink, and 8 more curated presets.
Create parametric OpenSCAD 3D models of workshop tools (drill presses, vacuums, saws, etc.) for workshop layout planning. Use when asked to "model a tool", "create OpenSCAD for [tool]", "add [tool] to workshop", or when planning workshop layouts that need tool representations. Supports brand-accurate colors (Bosch, Festool, Makita, DeWalt, Milwaukee) and standardized code structure with customizer parameters.
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.