Skills
98,284 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Implement comprehensive Hebrew internationalization (i18n) patterns for web and mobile applications. Use when user asks about Hebrew localization, "beinle'umiyut", i18n for Israeli apps, Hebrew plural forms, Hebrew date formatting, RTL CSS logical properties, bidirectional text handling, React/Vue/Angular/Next.js RTL integration, Tailwind CSS RTL, or next-intl setup. Covers Hebrew pluralization rules, date and number formatting for Israel, RTL-first CSS, Tailwind RTL utilities, and bidi text algorithms. Do NOT use for NLP or content writing (use hebrew-nlp-toolkit or hebrew-content-writer instead).
Prevents, detects, and remediates files that should never be committed — secrets (.env, API tokens, hardcoded credentials) and dev artifacts (build output, scratch databases, editor/OS files). Covers .gitignore (and why it does not untrack), git rm --cached, auditing tracked files, history scrubbing, and credential rotation. Use when a repo has committed secrets or junk, when setting up a new repo's ignore rules, or when reviewing what a repo actually tracks.
ALWAYS START HERE for any LangChain, Deep Agents, or LangGraph agent building project. Required starting point before choosing other skills or writing any code. Covers framework selection (LangChain vs LangGraph vs Deep Agents), agent archetypes, dependency setup, and which skills to load next based on your decisions.
Run code in Lightning AI Sandboxes - fast, isolated ephemeral VMs with optional persistence, snapshots, custom images, Docker-in-sandbox (docker / docker compose), network egress policies, file I/O, public port URLs, and interactive PTY sessions. Use when the user wants to execute untrusted or experimental code safely, needs a throwaway cloud VM, wants to build/run containers or preview a containerized app, or asks about lightning.ai sandboxes or snapshots.
Help Litium partner developers build, configure, and deploy e-commerce sites and backoffice UI extensions. Use for React Accelerator (Next.js, GraphQL, blocks, cart, checkout, wishlist), MVC Accelerator (.NET Razor views, controllers, view models, client builds), local setup, Litium Cloud deployment, data modelling and product fields, Litium Admin, Storefront GraphQL, Connect, and Extension Management APIs, or forum.litium.com solutions. Covers @litiumab/platform-extension-sdk extensions in React, Vue, Angular, or Vanilla: scaffolding, extension.manifest.json, window.litiumExtension, sub-path routing, IIFE/Vite builds, testing, installation, and deployment. Triggers: build Litium site, create Litium project, product field, block, accelerator, Litium API, wishlist, cart, placeOrder, custom field, backoffice extension, platform-extension-sdk, UI extension, panel, or settings page extension.
Consult other LLMs (GPT-4.1, o4-mini, Gemini 2.5 Pro, Claude Opus) for second opinions on complex bugs, hard problems, planning, and architecture decisions. Use proactively when stuck for 15+ minutes or facing complex debugging. Use when user says 'ask Gemini/GPT/Claude about X' or 'get a second opinion'.
Build a stunning new website for a local business prospect. Adapted from the full website-rebuild skill but optimized for speculative local business pitches. 10-phase process: brand extraction, SEO audit, design audit, rebuild plan, full build with design system, copy optimization, combined QA, pre-deploy checklist, and output to monorepo. Uses scraped content from prospect-scrape as input. No tools/calculator research phase. Single combined QA round. Triggers on: "rebuild prospect", "local business rebuild", "build prospect site", "rebuild their site", "prospect rebuild", or any request to build a new website for a qualified prospect.
Clean, compact, and reconcile durable project context and any configured issue-tracker mirror without changing established meaning. Always use this skill whenever a request cleans, audits, or checks consistency across two or more durable context sources, even when they are called product docs, glossary, decisions, specs, or agent instructions instead of PRODUCT.md, GLOSSARY.md, docs/decisions, docs/specs, AGENTS.md, or CLAUDE.md. Also use for confirmed shipped-spec retirement or a full consistency sweep between default-branch spec folders and their tracker issues. Do not use to define new product intent, record one newly settled term or decision, look up context, shape a feature, implement work, or revise an active spec's behavior against work that has shipped, which belongs to `babysit-specs`.
Set up, authenticate, and manage MakeThisBetter feedback from Claude Code. Use when the user runs /makethisbetter followed by setup, update, setup-auth, login, signup, list, pick, respond, archive, restore, ready, release, decline, duplicate, reopen, or any feedback management command. Also triggers on MakeThisBetter setup, updating the widget, listing pending or archived feedback, choosing feedback to fix, responding to a Reporter, preparing a committed fix for release, or releasing deployed feedback.
Call Python libraries from MATLAB using the py. interface, pyrun, pyrunfile, or pyenv. Use when writing or executing MATLAB code that calls Python functions or passes data between MATLAB and Python. REQUIRED when triaging Python errors from MATLAB (ModuleNotFoundError, ImportError, "Unable to resolve the name 'py.*'"). REQUIRED when setting up Python environments for MATLAB, creating virtual environments, or installing Python packages for use with MATLAB.
Generate or improve MATLAB help text (documentation comments) for a function, class, or script file following MathWorks standards (H1 line, syntax paragraphs, See Also, 75-char lines). Read BEFORE writing MATLAB help — default patterns (Inputs:/Outputs: lists, block comments, uppercase See Also) produce non-conforming output. Use when writing, rewriting, fixing, or reviewing MATLAB help comments or function documentation.
Always-on guardrail for .NET MAUI API currency. Prevents AI coding agents from using deprecated, obsolete, or removed APIs across XAML/C#, Blazor Hybrid, and MauiReactor. Includes a reasoning framework for detecting project target framework and library versions, plus a curated table of the most common deprecated API traps in .NET MAUI 10. USE FOR: "deprecated API", "obsolete API", "API migration", "MAUI breaking changes", "check API currency", "review MAUI code", "generate MAUI code", "edit MAUI code". DO NOT USE FOR: learning new MAUI features (use feature-specific skills), performance optimization (use maui-performance), or testing guidance (use maui-unit-testing).
WeChat Mini Program Iconfont icon integration skill. Pick and download icons from iconfont.cn, automatically replace font files, update CSS, and scan and replace emoji in WXML/JS with iconfont class names. Trigger words: "更新图标", "添加图标", "替换 emoji", "iconfont", "图标集成", "小程序图标".
Build websites and web applications using Telefonica's Mistica design system React components. Use this skill when writing React UI code with @telefonica/mistica, creating pages, layouts, forms, or any user interface that should follow Telefonica's design guidelines. Triggers on tasks involving Mistica components, Telefonica branding, or when the user mentions Mistica.
Design and build motion-first creative websites — page design (structure, type scale, palette, spacing) plus interaction choreography: scroll animation, Framer Motion, GSAP, and light 3D via Three.js/R3F. Use for animated landing pages, creative portfolios, product showcases, WebGL-lite scenes, and motion audits. Also use when tuning interaction handfeel (手感差/太生硬/不跟手), replicating motion from a video or URL reference (复刻), building 3D depth from flat image assets (伪3D/抠图), diagnosing dead scroll-timeline stretches, mixing scene audio, auditing discoverability (点不开/没人会发现), building headless verification probes, or fixing a page that moves well but looks generated (不好看/像AI做的/没设计感). Equally for building a whole site from nothing (从0到1做个网页/落地页/官网/作品集): stack choice, sections and copy, components (导航/hero/表单/卡片/定价表), and production polish (favicon/OG/404/空状态/暗色模式). Not for dashboards, admin UI, or full 3D scene generation.
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.
Writes and reviews Swift observability code on Apple platforms - unified logging (Logger, OSLog, privacy redaction, log levels and persistence), signposts and Instruments, activity tracing, MetricKit metrics and diagnostics (launch, hangs, crashes, OOM, disk writes), crash reports and symbolication, OSLogStore log export, Xcode Organizer, and shipping telemetry to your own backend or third-party SDKs. Use when adding logging, instrumenting performance, wiring MetricKit, diagnosing production crashes or hangs, exporting logs for support, or choosing between print, Logger, signposts, and analytics SDKs.
Apply Odoo 18-20 best practices for module architecture, ORM patterns, XML views, OWL components, security, testing, and performance, plus dev environment setup and an official documentation index. Use when developing, reviewing, or debugging Odoo custom modules or setting up an Odoo development environment.
Rank open PRs for the automerge queue using eligibility tiers and AI judgment of meaningful fixes close to merge, including older PRs with screenshots and bounded requested changes. Exclude untrusted authors and apply the queue label only after human confirmation. Feeds om-auto-merge-buddy.
Automated Python-to-Rust migration via iterative convergence loops. Treats the Python codebase as the living specification and produces a fully-tested Rust equivalent with zero-tolerance parity validation. Use when migrating Python modules, libraries, or CLIs to Rust. Activates for: migration, oxidize, python to rust, port to rust, rewrite in rust.
Generate YAML code pasteable into Power Apps Studio using the pa.yaml v3 schema. Includes modern controls, caching patterns, Gallery with collections, and all lessons learned to vibe code without errors. Trigger: when the user asks to create screens, controls or code for Power Apps in YAML format.
Integrate a client app with the 1Shot public relayer JSON-RPC API to submit gas-abstracted EIP-7710 delegated transactions on EVM chains. Use when the host or backend calls relayer_* methods directly, redeems a delegation context from wallet_requestExecutionPermissions (embedded 1Shot Wallet or MetaMask), verifies relayer webhooks, or builds MetaMask/local-signer delegation flows. Do NOT use for embedding wallet.1shotapi.com alone (OWSProxy, configure, eth_requestAccounts, eth_sendTransaction) — the wallet calls the relayer internally; use the 1shot-wallet skill instead. Trigger on relayer_send7710Transaction, relayer_estimate7710Transaction, relayer_getCapabilities, relayer_getFeeData, relayer_getStatus, EIP-7710/7715 delegations, requestExecutionPermissions, decodeDelegations, or gas-abstracted txs via a third-party relay.
React Router v7 (Framework Mode, formerly Remix) reference. loader, action, middleware, hooks (useLoaderData / useNavigate / useFetcher / useNavigation, etc.), components (Link, NavLink, Form, Outlet), routes.ts, SSR / SPA / Static, ErrorBoundary, session, redirect, defer, type-safe routing.
Build UIs with React Spectrum S2 (Spectrum 2), Adobe's component library for React. Use when developers are using `@react-spectrum/s2` or need Adobe design system components. Includes React Aria Components docs as a reference for building custom components on top of unstyled primitives.
Use when the user asks for safe refactoring suggestions, refactor opportunities, or cleanup ideas. Analyzes codebase patterns (duplicate blocks, long functions, magic values, unused code, simple type improvements) and proposes low-risk refactors grouped by safety level. Does not execute changes—suggests only.
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.
