Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use when building, animating, or debugging Roblox GUI elements including HUDs, menus, world-space UI, and player labels. Triggers on: ScreenGui setup, SurfaceGui or BillboardGui placement, UDim2 sizing questions, TweenService UI animations, responsive scaling, LocalScript GUI logic, ResetOnSpawn issues, or any Frame/TextLabel/ImageButton layout work.
Use when writing multiplayer C++: replicating a property, choosing an RPC type, tuning relevancy or dormancy, registering replicated subobjects, or turning on push model or Iris. Also use when the user mentions 'replicate a variable', 'OnRep', 'DOREPLIFETIME', 'GetLifetimeReplicatedProps', 'Server RPC', 'NetMulticast', 'WithValidation', 'COND_OwnerOnly', 'HasAuthority', 'ENetRole', 'FFastArraySerializer', 'MARK_PROPERTY_DIRTY_FROM_NAME', 'net dormancy', 'replication graph', 'dedicated server' or 'listen server'. For GAS prediction and attribute replication, see ue-gameplay-abilities; for movement replication and CMC prediction, see ue-character-movement.
Builds full-stack Frappe Framework applications end-to-end. Use this skill any time the user mentions: creating or modifying a DocType, writing a controller or lifecycle hook, adding a whitelisted API, setting up a new Frappe app or bench site, building a desk form or list view, creating portal pages, writing background jobs or scheduled tasks, managing permissions or roles, writing Frappe tests, or working with frappe.db / frappe.qb. Also applies when the user says things like "how do I hook into save", "add a field to a DocType", "create a REST endpoint in Frappe", "run bench migrate", or "install an app on a site" — even if they don't explicitly say "Frappe"
Comprehensive fullstack development skill for building complete web applications with React, Next.js, Node.js, GraphQL, and PostgreSQL. Includes project scaffolding, code quality analysis, architecture patterns, and complete tech stack guidance. Use when building new projects, analyzing code quality, implementing design patterns, or setting up development workflows
Apply when building VTEX IO storefront components under react/ for Store Framework experiences. Covers storefront component structure, css-handles, storefront context hooks, browser-safe data fetching, and how components should behave when used as theme blocks. Use for custom storefront UI, product widgets, banners, forms, or reviewing shopper-facing React code in VTEX IO apps.
Audit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown delivery, ai-catalog.json, /.well-known discovery files, and WebMCP tools. Exclude AI citability and brand signals (seo-geo) and commerce protocol depth (seo-ecommerce).
Interact with the DX (getdx.com) APIs to get and manage information about the Software Catalog, manage Scorecards to track system health, analyze Snapshot survey results, and perform data analysis on Engineering productivity. Also answers questions about DX itself — product concepts, setup/admin procedures (SSO, connectors, backfills), and troubleshooting — by fetching DX's own documentation.
Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when the user says “make a plan”, “create a plan”, “plan this out”, “plan the implementation”, “help me plan”, “design a plan”, “draft a plan”, “write a plan”, “outline the steps”, “break this down into tasks”, “what's the plan for”, or makes a similar planning request. Also triggers on explicit “/planner” or “/plan” commands.
Static analysis skill for C/C++ codebases. Use when hardening code quality, triaging noisy builds, running clang-tidy, cppcheck, or scan-build, interpreting check categories, suppressing false positives, or integrating static analysis into CI. Activates on queries about clang-tidy checks, cppcheck, scan-build, compile_commands.json, code hardening, or static analysis warnings.
Decide which Sentry signal to reach for when instrumenting code — error, span, span attribute, log, or metric. Use when adding instrumentation and unsure whether something should be a log vs a span vs a metric, when deciding "what to instrument where", when reviewing instrumentation for gaps, or when a coding agent needs a rule for choosing between errors, traces, logs, and metrics. This skill decides WHAT to emit; the sentry-*-sdk skills handle HOW to set each pillar up.
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the author.
Read and search GitHub repository documentation via gitmcp.io MCP service. **When to use:** The user provides a GitHub URL, mentions a specific repo in owner/repo format, asks “what does this repo do?”, “read the docs for X repo”, or similar, or wants to search code or docs within a repo.
Creates structured change proposals with specification deltas for new features, breaking changes, or architecture updates. Use when planning features, creating proposals, speccing changes, introducing new capabilities, or starting development workflows. Triggers include "openspec proposal", "create proposal", "plan change", "spec feature", "new capability", "add feature planning", "design spec".
Develops SAP Fiori applications using SAP Fiori tools extensions for VS Code and SAP Business Application Studio. Use when: generating Fiori Elements or Freestyle SAPUI5 applications, configuring Page Editor for List Report or Object Page, working with annotations and Service Modeler, setting up deployment to ABAP or Cloud Foundry, creating adaptation projects, using Guided Development, previewing with mock data or live data, configuring SAP Fiori launchpad, or using AI-powered generation with Project Accelerator/Joule. Technologies: SAP Fiori Elements, SAPUI5, OData V2/V4, CAP, SAP BTP, ABAP, Cloud Foundry, fiori-mcp-server (MCP tools for AI-assisted generation)
Govern stable domain context with a narrowly scoped CONTEXT.md when needed, and route hard-to-reverse decisions to ECC's existing architecture-decision-records skill. Use when domain terms require repeated explanation, one term has multiple meanings, unclear language causes module-boundary mistakes, or domain semantics must remain separate from architecture decisions.
Software Mansion's guide for migrating Expo SDK apps to Meta Quest using expo-horizon packages. Use when adding Meta Quest or Meta Horizon OS support to an existing Expo or React Native project. Trigger on: Meta Quest, Horizon OS, Quest 2, Quest 3, Quest 3S, VR app, expo-horizon-core, expo-horizon-location, expo-horizon-notifications, build flavors for Quest, panel sizing, VR headtracking, Horizon App ID, quest build variant, isHorizonDevice, isHorizonBuild, migrate expo-location to Quest, migrate expo-notifications to Quest, Meta Horizon Store publishing, or any task involving running an Expo app on Meta Quest hardware.
Use when implementing middleware for next-safe-action -- authentication, authorization, logging, rate limiting, error interception, context extension, or creating standalone reusable middleware with createMiddleware() or createValidatedMiddleware(). Covers both use() (pre-validation) and useValidated() (post-validation) middleware.
Creates task-oriented technical documentation with progressive disclosure. Use when writing READMEs, API docs, architecture docs, or markdown documentation. Also use this skill at the END of any completed reverse engineering, penetration testing, CTF, or security analysis task to generate a formal report in the user's project directory. Trigger keywords: 写报告, 写文档, 出报告, writeup, 技术文档, report, documentation.
Deep research and discovery before building something new. Explores local projects for reusable code, researches competitors, reads forums and reviews, analyses plugin ecosystems, investigates technical options, and produces a comprehensive research brief. Three depths: focused (30 min), wide (1-2 hours), deep (3-6 hours). Triggers: 'research this', 'discovery', 'explore the space', 'what should I build', 'competitive analysis', 'before I start building', 'research before coding'. Not for cited fact-checking research reports (a separate harness does those); this is pre-build product discovery.
Use when writing Unreal Engine C++ AI — AI controllers, behavior tree nodes, blackboards, AI perception, navmesh pathfinding, EQS queries, or Smart Objects. Also use when the user mentions 'AAIController', 'UBTTaskNode', 'ExecuteTask', 'FinishLatentTask', 'UBlackboardComponent', 'FBlackboardKeySelector', 'UAIPerceptionComponent', 'FAIStimulus', 'UAISenseConfig_Sight', 'MoveTo', 'UNavigationSystemV1', 'ProjectPointToNavigation', 'UNavArea', 'ANavLinkProxy', 'UEnvQueryManager', 'FEnvQueryRequest', 'EQS', 'navmesh', 'USmartObjectSubsystem', or 'ZoneGraph'. For State Tree authoring, see ue-state-trees; for Mass crowds, see ue-mass-entity; for the movement component that executes paths, see ue-character-movement
Build AI agents with structured access to Sanity content via Sanity Context. Use when setting up a Sanity-powered chatbot, connecting an AI assistant to Sanity content, or adding client-side tools to an agent. Covers MCP endpoint setup in the Context app (GROQ mode over a dataset, or Knowledge Base mode), agent implementation, Insights, and advanced patterns. Always use this skill when users mention building a chatbot with Sanity, creating an AI assistant for their content, setting up the Sanity Context MCP server, integrating Sanity with Claude/GPT/any LLM, making content searchable by AI, implementing semantic search over Sanity data, or connecting their CMS to an AI agent.
Best practices for Next.js 16 App Router performance, caching, server components, server actions, routing, and codebase hygiene — plus a category-major review/refactor algorithm that finds codebase-level removal, deduplication, and reuse opportunities. Use when writing Next.js 16 App Router code, configuring caching with 'use cache', building Server Components, setting up parallel/intercepting routes, configuring next.config.js or proxy.ts, or auditing/refactoring a Next.js codebase (a single file or the whole repo). This skill does not cover generic React 19 patterns (use the react skill) or non-Next.js server rendering.
Profile a model running on MAX to find where it spends time and whether the GPU is saturated. Use when the user asks to "profile my model," "where is my model spending time," "why is inference slow," "is my GPU being utilized," "how much GPU am I using," "get a kernel breakdown," "capture an nsys/rocprof/ncu trace of max serve," or wants to measure MAX inference performance. Works for any model MAX can run — built-in architectures and custom ones loaded with --custom-architectures — from a pip or pixi install (max generate, max serve, or a Python script) on NVIDIA or AMD GPUs. Decide cheapest-first: a GPU utilization check, then a kernel breakdown, then a single-kernel deep dive only when one kernel dominates
Best practices for Apache Kafka event streaming and distributed messaging. Use when building event-driven architectures, implementing producer/consumer patterns, designing topic partitioning strategies, setting up Kafka Streams, configuring schema registries, or integrating change data capture pipelines.
Use when working on multiple branches simultaneously, switching context without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches. Provides git worktree commands and workflow patterns for parallel development with multiple working directories.
Use this skill when the user asks to “add an app to my MCP server”, “add UI to my MCP server”, “add a view to my MCP tool”, “enrich MCP tools with UI”, “add interactive UI to existing server”, “add MCP Apps to my server”, or needs to add interactive UI capabilities to an existing MCP server that already has tools. Provides guidance for analyzing existing tools and adding MCP Apps UI resources.
Product requirements and planning specialist. Creates PRDs and tech specs with functional/non-functional requirements, prioritizes features using MoSCoW/RICE frameworks, breaks down epics into user stories, and ensures requirements are testable and traceable. Use for PRD creation, requirements definition, feature prioritization, tech specs, epics, user stories, and acceptance criteria.
World-class computer vision skill for image/video processing, object detection, segmentation, and visual AI systems. Expertise in PyTorch, OpenCV, YOLO, SAM, diffusion models, and vision transformers. Includes 3D vision, video analysis, real-time processing, and production deployment. Use when building vision AI systems, implementing object detection, training custom vision models, or optimizing inference pipelines.
Ships a Capacitor app to the Apple App Store and Google Play. Use for release prep and submission - version/build numbers (CFBundleVersion, versionCode), signing, archiving and uploading the IPA/AAB, TestFlight, Play tracks and closed testing, icons and screenshots, listing metadata, App Privacy and Data safety forms, age ratings, export compliance, phased rollout, and current platform deadlines (iOS 26 SDK since April 28 2026, iOS 27 SDK from April 2027, UIScene lifecycle for Xcode 27, Play target API 36 from Aug 31 2026, 16 KB page size). Also for upload errors like ITMS-90725, ITMS-91053, ITMS-91061, ITMS-4238 redundant binary, or "Version code has already been used". Do not use for a guideline-by-guideline Apple rejection audit (capacitor-apple-review-preflight), CI pipeline authoring (capacitor-ci-cd), Capgo Cloud Build setup (capgo-native-builds), or converting a website into an app (webapp-to-capacitor).
Write, review, or improve Swift APIs using Swift API Design Guidelines for naming, argument labels, documentation comments, terminology, and general conventions. Use when designing new APIs, refactoring existing interfaces, or reviewing API clarity and fluency
Apply when defining, validating, or consuming VTEX IO app settings. Covers settingsSchema, app-level configuration boundaries, and how backend or frontend code should depend on settings safely. Use for merchant-configurable behavior, settings forms, or reviewing whether settings belong in app configuration rather than hardcoded logic or custom data entities.
Use when streaming levels in and out, setting up World Partition, or moving between maps. Also use when the user mentions 'level streaming', 'World Partition', 'data layer', 'UDataLayerManager', 'SetDataLayerRuntimeState', 'LoadStreamLevel', 'UnloadStreamLevel', 'ULevelStreamingDynamic', 'LoadLevelInstance', 'ALevelInstance', 'streaming source', 'streaming volume', 'HLOD', 'OpenLevel', 'ServerTravel', 'seamless travel', 'sub-level', 'open world', or 'UWorldSubsystem'. For replication and net relevancy, see ue-networking-replication; for GameMode travel callbacks, see ue-gameplay-framework; for saving world state to disk, see ue-serialization-savegames
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.