Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Create distinctive React and Tailwind interfaces with strong hierarchy and polished implementation. Use when building or redesigning pages, flows, or components, or when another better-react-web-ui skill needs shared design guidance. Pair with add-ui for direct implementation or requested alternatives.
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 (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Multi-framework frontend development. Frameworks: React 18+ (Suspense, hooks, TanStack), Vue 3 (Composition API, Pinia, Nuxt), Svelte 5 (Runes, SvelteKit), Angular (Signals, standalone). Common: TypeScript, state management, routing, data fetching, performance optimization, component patterns. Actions: create, build, implement, style, optimize, refactor components/pages/features. Keywords: React, Vue, Svelte, Angular, component, TypeScript, hooks, Composition API, runes, signals, useSuspenseQuery, Pinia, stores, state management, routing, lazy loading, Suspense, performance, bundle size, code splitting, reactivity, props, events. Use when: creating components in any framework, building pages, fetching data, implementing routing, state management, optimizing performance, organizing frontend code, choosing between frameworks.
Use this skill for any user-facing frontend UI task involving React, TypeScript, Tailwind CSS, shadcn/ui, product pages, dashboards, settings pages, admin tools, app shells, tables, forms, detail views, landing pages, or UI redesigns. This skill is especially important when the user asks for production-quality UI, "not AI demo style", "not template-looking", "Linear/Vercel/Stripe style", "design first then code", "frontend-skill", "shadcn constraints", or asks to polish/rebuild a bad-looking frontend. Do not use it for backend-only work, algorithm-only work, CLI-only work, or throwaway prototypes.
Use when developing, reviewing, debugging, or migrating HarmonyOS NEXT native apps with ArkTS, ArkUI, DevEco Studio, DevEco Code, DevEco CLI, Agent Framework Kit, Stage model, UIAbility, .ets, module.json5, oh-package.json5, HAP/HSP/HAR, API 22-24, API 26 Beta1, HarmonyOS 6.1, HarmonyOS 6.1.1 Release, HarmonyOS 7 preview, HarmonyOS 26.0.0 Beta1, state management decorators, Navigation/NavPathStack, ArkTS concurrency, permissions, persistence, networking, media, Camera Kit, Scan Kit, Map Kit, Push Kit, Payment Kit, App Linking, Share Kit, Weather Service Kit, ArkGuard, APIAVAILABLE, ContainerReader, jsLeakWatcher, Linux CI, testing, performance, or common 鸿蒙开发 workflows.
Guide for creating and maintaining outbox-based eventually consistent operations in Sentry. Most commonly used for cross-silo data replication, but applicable anywhere eventual consistency is needed — including single-silo deferred side effects, audit logging, and event fanout. Use when asked to "add outbox", "add outbox replication", "replicate model to control silo", "replicate model to cell", "add outbox category", "write outbox signal receiver", "debug stuck outboxes", "outbox not processing", "data not replicating", "test outbox", "migrate model to use outboxes", "backfill outbox data", "outbox coalescing", "ReplicatedCellModel", "ReplicatedControlModel", "OutboxCategory", "OutboxScope", or "outbox_runner". Covers model mixins, category registration, signal receivers, testing, backfill, and debugging workflows.
Monitoring, logging, and tracing implementation using OpenTelemetry as the unified standard. Use when building production systems requiring visibility into performance, errors, and behavior. Covers OpenTelemetry (metrics, logs, traces), Prometheus, Grafana, Loki, Jaeger, Tempo, structured logging (structlog, tracing, slog, pino), and alerting.
Run an improve-my-MCP campaign: an autoresearch-style loop that measures the MCP agent experience with the eval harness, picks the highest-impact tool problem from production data, makes one bounded fix, and keeps it only if before/after scores improve. Use when asked to "improve my MCP", run an MCP improvement campaign, fix tool discoverability or descriptions based on evidence, or prepare an eval-backed PR for a tool change. Every shipped change must carry eval evidence; guardrails below are hard rules.
Integrate Arcjet Guard into Python Google ADK — assign guard_tool to LlmAgent(before_tool_callback=), put guard_plugin first on Runner(plugins=) so a deny dict with arcjetDenied skips the tool, and read a caller-owned id via google_adk_context. Use when asked to add Arcjet to google-adk, Google ADK Python, rate limit those tools, screen inbound messages, or block prompt injection / PII. This is Python google-adk 2.x, not JS @google/adk and not @google/genai.
Comprehensive SAP Joule CLI (formerly sapdas CLI) assistant for managing digital assistants from the command line — compiling capabilities, deploying assistants, running BDD tests, linting, and troubleshooting errors. Use this skill whenever the user mentions "joule cli", "sapdas", "joule compile", "joule deploy", "joule test", "joule login", "joule lint", digital assistant deployment, capability compilation, DAAR files, RTA artifacts, or any task involving the Joule command line interface — even if they just say something like "deploy my assistant" or "how do I log in to Joule from the terminal". Also trigger when the user asks about testing Joule capabilities with Cucumber, linking AI assistants, managing deployed assistants, or automating Joule workflows in CI/CD pipelines.
Apache Kafka messaging skill. Covers producer acks=all/1/0 selection, idempotence (enable.idempotence + acks=all) configuration, manual consumer offset commit (enable.auto.commit=false), DLT dead-letter handling (@RetryableTopic/@DltHandler), @KafkaListener + error handler (DefaultErrorHandler), ordered messages (same Key to the same partition), and transactional messages. Corrects LLMs that: get message loss with acks=0, miss messages with auto.commit, ignore duplicate consumption, and skip DLT configuration.
Design and create Busabase-backed App-in-Skill packages with a canonical app project, Busabase-native setup and product onboarding, review/execution workflows, a standardized responsive UI, and AirApp-first delivery. Use when a user wants a Busabase research desk, review queue, planner, action console, operating dashboard, control panel, collaboration workspace, onboarding/readiness flow, or an existing Kelly App-based skill updated. Every generated skill contains a complete app/ project, deploys that source to Busabase AirApp by default, runs pnpm dev only when local preview is explicitly requested, follows the Kelly desktop and phone UI contract, delegates AirApp runtime, SDK, security, scaffolding, and deployment constraints to busabase-app-creator, and delegates repository-level conformance testing to kelly-app-skill-creator-tests.
Multi-language support, resource files, culture formatting, and globalization patterns for ASP.NET Core Razor Pages applications. Use when implementing multi-language support in ASP.NET Core applications, managing resource files for translations, or formatting dates, numbers, and currencies for different cultures.
Manage Git branching strategies, commit conventions, and collaboration workflows. Use when choosing between trunk-based development, GitHub Flow, or GitFlow, implementing conventional commits for automated versioning, setting up Git hooks for quality gates, or organizing monorepos with clear ownership.
Guides the 7-step MATLAB memory optimization workflow: baseline, profile, identify, optimize, measure, verify, report. Use when asked to reduce MATLAB memory usage, find memory bottlenecks, fix out-of-memory errors, or optimize memory-intensive code.
Guidance for dependency injection in .NET MAUI apps — service registration, lifetime selection (Singleton/Transient/Scoped), constructor injection, automatic resolution via Shell navigation, explicit resolution patterns, platform-specific registrations, and testability best practices. USE FOR: "dependency injection", "DI registration", "AddSingleton", "AddTransient", "AddScoped", "service registration", "constructor injection", "IServiceProvider", "MauiProgram DI", "register services". DO NOT USE FOR: data binding (use maui-data-binding), Shell route setup (use maui-shell-navigation), or unit test mocking patterns (use maui-unit-testing).
Provides Needle Engine context for web-based 3D projects built on Three.js with the @needle-tools/engine component system. Use this skill whenever the user is working with Needle Engine components, GLB files exported from Unity or Blender, Vite configs with needlePlugins, TypeScript classes extending Behaviour, or anything involving @needle-tools/engine imports. Also trigger when the user mentions "needle engine", "needle tools", serializable decorators (@serializable, @syncField, @registerType), the <needle-engine> web component, 3D web apps using a component system on Three.js, or 3D scenes loaded from GLB in a web context — even if they don't explicitly name the engine. Trigger even when the user is just reporting a bug or error without mentioning Needle Engine — check if @needle-tools/engine is in package.json or imports. If the project uses Needle Engine, always load this skill.
Comprehensive toolkit for creating, analyzing, and visualizing complex networks and graphs in Python. Use for network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing network topologies. Applicable to social networks, biological networks, transportation systems, citation networks, and any domain involving pairwise relationships.
Node version discipline — before running tsc / eslint / build / test / install in any Node project, align the Node version to the project's declared version (.nvmrc / .node-version / .tool-versions / volta / engines.node) and disclose it in the verification report, preventing false-pass / false-fail when the host default Node mismatches the project-pinned version; when the project declares no Node version at all, ask the user for the version and offer to persist a declaration file so future sessions/CI auto-align. Use this skill whenever the user is about to run a version-sensitive Node command, or mentions Node version mismatch / wrong Node / version conflict. 中文触发词「node 版本对齐」「nvm 对齐」「.nvmrc」「Node 版本纪律」「对齐 Node 版本」「切换 node 版本」「版本不匹配」「初始化 node 版本管理」「为工程增加 node 版本声明」「给工程加 .nvmrc」「无 .nvmrc 时补一个」「工程没有 node 版本管理」, English aliases node version discipline, nvm use, align node version, switch node version, add nvmrc, initialize node version.
Use when a project contains okteto.yaml or okteto.yml, or when the user mentions Okteto, dev environments, or an okteto command. Also use before running kubectl, helm, or docker build in a repo that has an Okteto manifest; when okteto up hangs or seems stuck; when parallel git worktrees collide over the same environment; or when deciding whether okteto destroy or okteto namespace delete is safe to run.
Pi packages — npm/git distribution of extensions, skills, prompts, themes via keywords pi-package and package.json pi manifest; pi install paths and security expectations. Use when shipping or consuming pi-package, adding pi.skills entries, or explaining install vs project-local -l. Use for "publish pi skills on npm", "pi install", "pi-package.json", even without naming this skill.
Answer product, PM, stakeholder, or non-engineer questions about app behavior by inspecting code and returning a share-ready plain-English answer. Trigger on product question, PM question, stakeholder answer, how a feature works, or why the app behaves that way. Do NOT use for code changes.
Use this skill when troubleshooting production or test incidents such as slow endpoints, high latency, OOMKilled pod restarts, pod crashes or throttling, slow queries, Sentry-reported errors and traces, post-deploy watches, before/after deployment metrics, or 503 responses during or after a rollout
Build Progressive Web Apps (PWAs) with offline support, installability, and caching strategies. Trigger whenever the user mentions PWA, service workers, web app manifests, Workbox, 'add to home screen', or wants their web app to work offline, feel native, or be installable.
Facilitate methodical review of proposals (technical designs, product specs, feature requests). Use when asked to "review this proposal", "give feedback on this doc", "help me review this RFC", or when presented with a document that needs structured feedback. Handles markdown files, GitHub gists/issues/PRs, and other text formats. Chunks proposals intelligently, predicts reviewer reactions, and produces feedback adapted to the proposal's format.
Find and read source code for Dart or Flutter packages from project dependencies or pub.dev. Use when asked to inspect package implementation details, trace dependency code, locate package files by resolving `.dart_tool/package_config.json`, or inspect a package that is not currently installed by unpacking it with `dart pub unpack`.
High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Interpret factor/stock-selection logic from strategy descriptions, research report PDFs, or screenshots, and generate a QMT built-in daily-frequency factor backtest script based on the scripts/daily-factors-backtest.py framework. Use when the user mentions QMT built-in backtesting, factor stock-selection backtesting, cross-sectional factors, research report replication, handlebar backtesting, or after_init precomputed signals.
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.