Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
This skill should be used when the user asks to "optimize a prompt", "improve prompt performance", "design a prompt template", "write better prompts", "debug prompt issues", "use chain-of-thought", "structured prompting", "few-shot prompting", or wants to apply advanced prompt engineering patterns for production LLM applications.
Complete Python 3.13+ fundamentals system. PROACTIVELY activate for: (1) Python 3.13 free-threading (no-GIL), (2) JIT compiler usage, (3) Pattern matching syntax, (4) Walrus operator, (5) F-string features 3.12+, (6) Type parameter syntax 3.12+, (7) Exception groups, (8) Dataclasses and enums, (9) Context managers. Provides: Modern syntax, performance features, best practices, naming conventions. Ensures correct Python 3.13+ patterns with optimal performance.
Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.
High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.
Use PyTRIO to write, debug, or explain remote large language model training and inference code. Use when the user mentions pytrio, TRIO, PyTRIO SDK, ServiceClient, TrainingClient, SamplingClient, LoRA training, SFT, asynchronous SFT, PyTRIO-Jev, PyTRIO Decision Model, multimodal inference, multimodal training, Vision GRPO, visual RLVR, ImageChunk, RL, GRPO, OPD, Search-R1, ReTool, DAPO, GSPO, ALFWorld, TextWorld, Agentic RL, OPSD, On-Policy Self-Distillation, DPO, custom loss functions, forward_backward_custom, forward_backward_custom_async, tool-calling reinforcement learning, HuggingFace datasets, the PyTRIO OpenAI-compatible API, SwanLab training records, saving weights, checkpoints, or remote LLM post-training.
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.
Complete React forms system. PROACTIVELY activate for: (1) Controlled form patterns, (2) React Hook Form setup and validation, (3) Zod schema validation, (4) Dynamic fields with useFieldArray, (5) Server Actions with forms, (6) useOptimistic for optimistic updates, (7) File upload handling, (8) Multi-step form wizards. Provides: Form validation, error handling, field arrays, file drag-drop, form state management. Ensures robust form handling with proper validation and UX.
Complete React component patterns system. PROACTIVELY activate for: (1) Compound components with context, (2) Render props pattern, (3) Higher-Order Components (HOC), (4) Custom hooks as patterns, (5) Provider pattern with reducer, (6) Controlled vs uncontrolled components, (7) Prop getter pattern, (8) State reducer pattern. Provides: Pattern implementations, composition strategies, reusable component APIs, flexible state control. Ensures clean, maintainable component architecture.
Eagerly initialize Riverpod providers at app startup by watching them in a root Consumer; handle loading/error in the initializer, AsyncValue.requireValue. Use when a provider must be ready before the rest of the app is used. Use this skill when the user asks about eager initialization or preloading providers.
Use ProviderObserver to log or debug Riverpod provider lifecycle; didUpdateProvider, ProviderScope observers, naming providers. Use when adding logging, analytics, or debugging for provider state changes. Use this skill when the user asks about ProviderObserver, logging Riverpod, or debugging provider updates.
Guidance for scaffolding new Rust projects. Use when: (1) starting a new Rust project or workspace, (2) configuring Cargo.toml best practices, (3) setting up CI pipelines for Rust, (4) organizing a multi-crate workspace, (5) configuring clippy, rustfmt, and linting.
Sa-Token integration extension skill. Covers JWT integration (comparison table of Simple/Mixin/Stateless modes), Redis persistence (JDK serialization/JSON serialization), Alone-Redis standalone Redis (isolating auth cache from business cache), AOP annotation-based authorization (using annotations in the Service layer), SpEL expression annotations (@SaCheckEL), Quick-Login quick login (zero-code login page), JSON serialization extensions (Jackson/Fastjson/Fastjson2/Snack3), template engine integration (Thymeleaf/Freemarker tag dialects), and RPC integration (Dubbo/Dubbo3/gRPC context propagation). Use when users need to integrate JWT for stateless authentication, configure Redis distributed sessions, isolate caches, use annotation-based authorization in the Service layer, or quickly build a login page. For basic login authentication, use the sa-token skill first.
Sa-Token microservice authentication skill. Covers the Same-Token mechanism for isolating internal services from the public network, unified authentication at the SpringCloud Gateway (Reactor reactive), authentication for internal RPC calls via Feign/Dubbo/gRPC, distributed Session schemes (Redis Session center / stateless JWT), Reactor/WebFlux framework integration, and SpringBoot3/4 dependency adaptation. Use when the user needs service-to-service authentication in a microservice architecture, gateway Token forwarding and validation, isolation of internal services from the public network, or distributed session sharing. For basic login authentication, use the sa-token skill first.
Sa-Token OAuth2.0 server-side skill. Covers the four grant types: Authorization Code, Implicit, Password, and Client Credentials. Includes complete OAuth2-Server setup, the SaOAuth2DataLoader data loader, custom and tiered Scope permissions, the OIDC protocol, OpenId/UnionId, custom grant_type, custom login authorization pages, annotation-based Access-Token validation, interoperability with login sessions, Scope level control, and custom API routes. Use when the user needs to build an OAuth2.0 authentication server, develop an open platform, or implement third-party application authorization. For basic login authentication, use the sa-token skill first.
The Figma↔Storybook bridge, both directions, via the native Figma MCP. design→code: map foundation tokens (color/spacing/type) from Figma variables with design↔code parity + drift, and deliver approved Figma components (extract → build → embed), authoring stories via sb-stories' rules. code→design: build Code Connect mappings from components + stories + token parity + usage so Figma Dev Mode shows the real code. Use for 'sync my Figma tokens', 'map Figma variables to my design system', 'deliver this approved Figma design', 'check design↔code token parity', 'connect my components to Figma / code connect'. NOT for prototyping/iterating an undecided design (that's sb-explore).
Security headers configuration and best practices for ASP.NET Core Razor Pages applications. Covers CSP, HSTS, X-Frame-Options, and comprehensive security middleware setup. Use when configuring security headers in ASP.NET Core applications, implementing Content Security Policy (CSP), or setting up HSTS and other security-related HTTP headers.
Expert at securing web applications against OWASP Top 10 vulnerabilities. Covers authentication, authorization, input validation, XSS prevention, CSRF protection, secure headers, and security testing. Treats security as a first-class requirement, not an afterthought. Use when "security, OWASP, XSS, CSRF, SQL injection, authentication security, authorization, input validation, secure headers, vulnerability, penetration testing, security, owasp, authentication, authorization, xss, csrf, injection, headers" mentioned.
Use this skill to set up semantic-release and conventional commits in a repo whenever the user wants releases automated from commit messages. Triggers include "set up semantic release", "add conventional commits", "configure automated versioning", "set up commitlint", "add husky hooks", or "automate our changelog and GitHub releases" — even if they never name semantic-release and only ask for version bumps, tags, or a changelog to be generated for them. Do NOT use this skill for a hand-maintained CHANGELOG plus manual `git tag` flow (that stays manual by design), or for general CI pipeline work unrelated to releasing.
Professional sub-skill for scikit-learn focused on robust pipeline architecture, custom estimator development, advanced feature engineering, and rigorous model validation. Covers Target Encoding, Nested Cross-Validation, and Production Deployment.
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
Generate the v2 -> v3 sync mapping for a Stream Activity Feeds app by sampling its live v2 activities and reactions and, when the app's v2 integration code is available, reading its write paths; use that code to plan how the app moves from v2 to v3. Use when setting up a Feeds v2 to v3 migration, building, reviewing, or debugging a v3 sync mapping, asking "what mapping do we need for our app?", asking how to port an app's v2 Feeds code to v3, or when a migrated activity in v3 has missing text or attachments, comments that are not comments, or missing bookmarks. Triggers on v3sync, v2 to v3, feeds migration, activity feeds migration, sync mapping, extra_context, reaction kinds, comments and bookmarks mapping, porting plan. The same mapping drives both the live syncer and the bulk exporter
Build, integrate, and answer how-to questions for Stream Chat in Unreal Engine games and apps. Use for Unreal Engine / UE5 / C++ / Blueprint / UMG project work - plugin install per engine version, StreamChatClientComponent wiring on the HUD, ConnectUser and tokens, channels and messages, the shipped WBP_* chat widgets, theming, cooking, and iOS / Android / desktop packaging. Triggers on unreal, unreal engine, ue5, ue 5.7, ue 5.8, .uproject, .uplugin, Build.cs, umg, blueprint, widget blueprint, StreamChat plugin, UStreamChatClientComponent, UChatChannel, FChannelProperties, WBP_TeamChat, in-game chat, game chat. Chat only - there is no Stream Video or Feeds SDK for Unreal.
Implement Stripe payment processing for robust, PCI-compliant payment flows including checkout, subscriptions, and webhooks. Use when integrating Stripe payments, building subscription systems, or implementing secure checkout flows.
Router and mental model for STRK20, the Starknet privacy pool. Use when choosing an integration route, answering questions about how STRK20 works (notes, nullifiers, viewing keys, channels, actions, proofs, deposit screening), stating what is hidden vs public, handling compliance and auditing questions, or mapping the ecosystem (shadow accounts, formerly private sub-accounts, the EVM Privacy Bridge, starter kit, RFPs, incubator, brand kit). Implementation work fires the sibling skills directly, strk20-wallet-api for private dapps in TS/React, strk20-anonymizer-contracts for Cairo helpers, strk20-privacy-sdk for wallets and key-holding backends.
Set up real-time event streams with async generator subscriptions using .subscription(async function*() { yield }). SSE via httpSubscriptionLink is recommended over WebSocket. Use tracked(id, data) from @trpc/server for reconnection recovery with lastEventId. WebSocket via wsLink and createWSClient from @trpc/client, applyWSSHandler from @trpc/server/adapters/ws. Configure SSE ping with initTRPC.create({ sse: { ping: { enabled, intervalMs } } }). AbortSignal via opts.signal for cleanup. splitLink to route subscriptions.
Design, implement, review, or repair database schemas, queries, indexes, transactions, migrations, and backfills with explicit integrity and rollout constraints. Use when datastore behavior or the data lifecycle is a primary part of the task. Do not use for routine persistence calls whose schema and consistency contracts are unchanged.
Diagnose and repair reproducible, intermittent, environment-specific, or production-observed software failures by tracing evidence to a root cause. Use when a symptom exists but its cause is uncertain or when a proposed fix needs causal validation. Do not use for feature implementation, speculative cleanup, or a general review without a concrete failure.
Comprehensive guide for implementing Syncfusion TypeScript dropdown components including AutoComplete, ComboBox, Mention, Dropdownlist, Multiselect, ListBox, and MultiColumn ComboBox. Use this when building selection interfaces, data binding, filtering, cascading dropdowns, dual list transfer, custom templates, and accessible dropdown experiences.
Use this skill when the user asks about Syncfusion JavaScript licensing, license keys, license registration, license validation errors, trial licenses, or license troubleshooting. This skill provides comprehensive guidance on generating, registering, and managing Syncfusion license keys for JavaScript applications, including edition-based and platform-based licensing models, registration methods, CI/CD integration, and resolving common licensing errors.
Comprehensive guide for implementing Syncfusion EJ2 JavaScript Popup components including Dialog, Predefined Dialog (DialogUtility), and Tooltip. Use this when building modal/modeless dialogs, alert/confirm windows, draggable dialogs, resizable windows, popovers, tooltips, and overlaid content with custom positioning, animations, WCAG 2.2 accessibility, forms integration, and event handling in TypeScript/JavaScript applications.
Typed chart grammar guidance for marks, scales, layouts, interaction, accessibility, rendering, and framework adapters. Use when a project uses TanStack Charts or when the task needs its setup, implementation, debugging, testing, migration, or integration guidance.
Type-safe form guidance for fields, validation, composition, submission, SSR, devtools, and framework adapters. Use when a project uses TanStack Form or when the task needs its setup, implementation, debugging, testing, migration, or integration guidance.
Expert guidance for building cross-platform desktop applications with Tauri 2.0 and Rust. Use when developing Tauri apps including commands and IPC, file system operations, window management, state management, system tray, menus, plugin development, security configuration (capabilities/permissions), bundling/distribution, and auto-updates. Covers patterns for editor applications requiring file dialogs, native menus, and frontend-backend communication.
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.