Skills
98,873 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Idiomatic Go design patterns: functional options, builder, factory, strategy, middleware chain, pub/sub, and other patterns adapted for Go's type system. Use when: "design pattern", "functional options", "builder pattern", "factory pattern", "strategy pattern", "middleware chain", "option pattern", "how to structure this". Not for: interface design (go-interface-design), package layout (go-architecture-review), concurrency patterns (go-concurrency-review).
Analyze V8 heap snapshots to investigate memory leaks and retention issues. Use when given .heapsnapshot files, asked to compare before/after snapshots, asked to find what retains objects, or investigating why objects survive GC. Provides snapshot parsing, comparison, retainer-path helpers, and scratchpad scripts.
Use hostc when an agent needs to expose a local development server as a temporary public preview URL, share localhost with another device or teammate, test webhooks against a local app, or create a public tunnel for localhost. Trigger on public preview, share local app, expose localhost, tunnel localhost, webhook preview, remote preview, or similar requests.
Manage Linear issues, projects, and workflows via CLI. This skill should be used when the user wants to create, list, update, or search Linear issues, manage projects or milestones, or interact with their Linear workspace. Triggers on "create a task", "add a Linear issue", "list my issues", "update GLE-123", "what's in my backlog", or any Linear-related request.
GPU-based particle systems using instanced rendering, buffer attributes, Points geometry, and custom shaders. Use when rendering thousands to millions of particles efficiently, creating particle effects like snow, rain, stars, or abstract visualizations.
Enforces the path from a green CI run to a shipped build — pubspec `version: x.y.z+N` as the single source of versionName/versionCode (monotonic, never reused), the release artifact verified on real hardware, signing and store API keys that never enter the repo, `--obfuscate --split-debug-info` with symbols archived per build or that release's crash reports are permanently unreadable, a permission set audited from the MERGED manifest and asserted whole, store declarations (Data Safety, nutrition labels, privacy manifests) provable in the repo and read back rather than trusted, size and cold-start budgets, and a staged rollout with a halt plan. Use when cutting or tagging a release, editing `android/app/build.gradle(.kts)`, `key.properties`, `AndroidManifest.xml`, `Info.plist` or `PrivacyInfo.xcprivacy`, bumping a version, uploading to Play or TestFlight, writing store-listing or privacy copy, symbolizing a crash, chasing size, or diagnosing an upload rejection or a blocked submission.
Design, implement, and validate Rust tests, including unit, integration, doctest, compile-fail, property, fuzz, benchmark, coverage, async, concurrency, process, daemon, IPC, terminal, platform, and hardware-facing test strategies. Use when users ask for Rust test architecture, flaky-test diagnosis, coverage gates, benchmarks, trybuild, cargo-nextest, real-process tests, or failure-path verification.
Interactive onboarding wizard to set up Polar payment integration from scratch. Use this skill when: (1) the user wants to “set up Polar” or “integrate Polar” in their project; (2) the user is starting fresh with Polar and needs guided setup; (3) the user asks “how do I get started with Polar”; (4) the user wants to add payments, subscriptions, or checkout to their app using Polar; (5) the user needs help creating their first Polar product and checkout. This skill walks through MCP installation, authentication, product creation, and generates framework-specific integration code
GLSL shader fundamentals—vertex and fragment shaders, uniforms, varyings, attributes, coordinate systems, built-in variables, and data types. Use when writing custom shaders, understanding the graphics pipeline, or debugging shader code. The foundational skill for all shader work.
Model, review, and refactor application state so source state stays minimal, derived state is computed instead of synchronized, impossible states are not representable, and each piece of state lives in the right place. Use this whenever the user mentions state management, reducers, stores, Redux, Zustand, React state, Vue state, Pinia, selectors, derived state, duplicated state, boolean flags, invalid states, async status, useEffect soup, forms, wizards, filters, URL state, server state, or confusing UI logic, even if they do not explicitly ask for a "state model."
Implement Syncfusion React DatePicker component with comprehensive guidance on date selection, formatting, validation, and accessibility. Use this when working with date input fields, date range pickers, custom date formats, locale-specific date handling, or keyboard navigation. This skill covers installation, setup, date formatting, validation, styling, globalization, and accessibility features.
Technical documentation writing and diagram generation. Use when creating docs, syncing documentation with code changes, building Mermaid diagrams, running doc coverage audits, or establishing writing style guides. Use for doc-as-code workflows, ERD generation, sequence diagrams, documentation gap analysis, and AI-assisted drafting.
Use when using Drei helper components with React Three Fiber: controls, environment maps, text rendering, HTML overlays, or performance helpers. Prevents the common mistake of not wrapping useGLTF in Suspense, using wrong Environment preset name, or forgetting makeDefault on controls. Covers 150+ Drei components across controls, environment, text, materials, loaders, performance. Keywords: Drei, @react-three/drei, OrbitControls, Environment, useGLTF, useTexture, Html, Text, Stage, ContactShadows, Instances, helper components, ready-made, quick setup React 3D.
Use when writing custom GLSL shaders, creating ShaderMaterial or RawShaderMaterial, defining uniforms, or patching built-in materials with onBeforeCompile. Prevents the common mistake of wrong uniform format, missing needsUpdate on uniforms, or not including required defines. Covers ShaderMaterial, RawShaderMaterial, GLSL, uniforms, ShaderChunk, onBeforeCompile, defines, GLSL3. Keywords: ShaderMaterial, RawShaderMaterial, GLSL, vertex shader, fragment shader, uniform, varying, ShaderChunk, onBeforeCompile, custom shader, write shader, custom visual effect, GPU programming.
Workflow required before any Mule application upgrade work. Call use_skill as your FIRST action — before reading project files (pom.xml, mule-artifact.json) or editing versions yourself — whenever the user asks to upgrade, migrate, bump, modernize, or move a Mule app to a newer Java version, a newer Mule Runtime version, or both. Covers upgrading Java and/or Mule Runtime, getting latest compatible connector versions, updating connector and plugin versions, and fixing impacts from operation changes in flows, DataWeave scripts, and MUnit tests. Even a targeted single-version bump like 'move this app to Java 17' or 'upgrade the runtime to 4.6' requires this workflow — do not hand-edit pom.xml versions and attempt the change yourself. When you call this skill, it must be the only tool call in that response.
Install and verify WinUI 3 prerequisites — .NET SDK 8.0.100+, WinApp CLI 0.7+, and Developer Mode; identify additional Native AOT and Windows Sandbox requirements. Use when the user asks to set up or repair the toolchain, or when another WinUI skill finds a missing or outdated prerequisite.
Maintain profiler performance cases containing only JSONL under ascend-kernel's csrc/ops/<op>/test. Collect data with torch_npu.profiler (fixed warmup=5, active=5), summarize Total Time(us) from ASCEND_PROFILER_OUTPUT/op_statistic.csv, and output a standardized Markdown comparison report (custom operator vs. benchmark) with a DType column. Do not generate perf_cases.json or *_profiler_results.json. See examples/layer_norm_profiler_reference/ for a reference implementation.
Use when asking about 'purge files', 'storage pressure', 'disk space iOS', 'isExcludedFromBackup', 'URL resource values', 'volumeAvailableCapacity', 'low storage', 'file purging priority', 'cache management' - comprehensive reference for iOS storage management and URL resource value APIs
Expert knowledge for Azure AI Custom Vision development, including best practices, decision-making, limits and quotas, security, integrations, coding patterns, and deployment. Use for exporting Custom Vision models, calling prediction APIs, using ONNX/TensorFlow, managing CMK/RBAC, Smart Labeler, and other Azure AI Custom Vision development tasks. Not for Azure AI Vision (use azure-ai-vision), Azure AI services (use microsoft-foundry-tools), Azure Machine Learning (use azure-machine-learning), or Azure AI Foundry Local (use microsoft-foundry-local).
Expert knowledge for Azure Service Connector development, including troubleshooting, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use when connecting Azure compute to Redis, databases, storage, messaging, AI services, or third-party endpoints, and for other Azure Service Connector development tasks. Not for Azure API Management (use azure-api-management), Azure Connector Namespace (use azure-connector-namespace), Azure Logic Apps (use azure-logic-apps), or Azure Service Bus (use azure-service-bus).
Expert knowledge for Azure Service Fabric development, including troubleshooting, best practices, decision-making, architecture and design patterns, limits and quotas, security, configuration, integrations and coding patterns, and deployment. Use for designing Service Fabric clusters, Reliable Services/Actors, CRP/CRM, reverse proxies, or sfctl/EventStore APIs, and other Azure Service Fabric development tasks. Not for Azure Kubernetes Service (AKS) (use azure-kubernetes-service), Azure Container Apps (use azure-container-apps), Azure App Service (use azure-app-service), or Azure Functions (use azure-functions).
Compose and Compose Multiplatform expert for UI development across Android, Desktop, iOS, and Web. Covers state management, composition, animations, navigation, performance, design-to-code workflows, and production crash patterns, backed by source analysis from androidx/androidx and JetBrains/compose-multiplatform-core. Use whenever the user mentions Compose, @Composable, remember, LaunchedEffect, Scaffold, NavHost, NavDisplay, MaterialTheme, LazyColumn, Modifier, recomposition, Compose Multiplatform/CMP, commonMain, expect/actual, ComposeUIViewController, UIKitView, ComposeViewport, Res.drawable/Res.string, or any Compose API. Also trigger on phrases like "design to compose", "build this UI", "implement this design", or any modern Kotlin UI question — including casual mentions like "my compose screen is slow". Plus focus topics: FocusRequester, focusProperties, onPreviewKeyEvent, D-pad, TV remote, ChromeOS, androidx.tv.material3
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-*.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating user timing marks.
Document undocumented public APIs in PyTorch by removing functions from coverage_ignore_functions and coverage_ignore_classes in docs/source/conf.py, running Sphinx coverage, and adding the appropriate autodoc directives to the correct .md or .rst doc files. Use when a user asks to remove functions from conf.py ignore lists.
Enforces a typed-error spine — a hand-rolled sealed Result<T,F> plus one per-boundary sealed Failure carrying a stable code and typed params (never a localized string), returned instead of thrown; recoverable failures are values, only bugs throw. Convert-at-boundary catches narrowly with an on-clause and logs the original error+stack BEFORE returning a typed Failure; call sites switch exhaustively with no default:; the taxonomy of what the global error net (FlutterError.onError + PlatformDispatcher.onError, installed by app-startup-and-bootstrap) routes into, plus Isolate.run re-wrapping; mechanism selection (Error vs assert vs Exception vs sealed outcome) and @useResult; and a never-lose-data layer (one-transaction-per-mutation, debounced autosave drafts, optimistic soft-delete/Undo). Use when writing result.dart/failures.dart, a try/catch or sealed-switch default:, wiring bootstrap handlers, a repository/service/DAO boundary, or transactions, drafts, or soft-delete/Undo.
Validate and format Israeli identification numbers including Teudat Zehut (personal ID), company numbers, amuta (non-profit) numbers, and partnership numbers. Use when user asks to validate Israeli ID, "teudat zehut", "mispar zehut", company number validation, or needs to implement Israeli ID validation in code. Includes check digit algorithm and test ID generation. Do NOT use for non-Israeli identification systems.
Complete guide for MagicBlock Ephemeral Rollups - high-performance Solana execution with sub-10ms latency, gasless transactions, and Solana Plugins. Use when building real-time games, high-frequency trading, or any application requiring ultra-low latency on Solana.
Turn a request into a SCHEDULABLE task DAG — atomic tasks with real dependencies, not planning prose: challenge scope and pick a planning mode with the user first, explore the real repo so no path is invented, then decompose into atomic TASK-NNN entries — each with a ≤3-file write scope, 2-3 testable acceptance criteria, a slice-scoped validate command, explicit dependencies, and an assigned agent — emitted as one canonical object into matching `.ulpi/plans/<name>.md` and `.json`. Every named path comes from observed repo state, the dependency graph stays acyclic, and JSON is the source of truth the markdown is rendered from — no phantom files, no circular edges, no task that hides side effects it never provisions. Use when the user asks to plan, decompose, or break work into execution-ready tasks.
Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.
Enforces Flutter/Dart project scaffolding where the layout makes defects greppable — a single-package app by default (feature-first under lib/features/, shared foundation split by role in core/ data/ services/ routing/ theme/ l10n/, a thin main.dart that calls bootstrap(), no lib/src in the app), extracting a generically-named pure-Dart package only when a body of logic earns it (public barrel over private lib/src/ for PACKAGES only, meta-only deps as the compile firewall, resolution:workspace member, downward-only dependency DAG), with pubspec treated as the audit artifact and no utils/helpers/common/misc/grab-bag-shared junk-drawer folders. Use when creating any .dart file or directory, deciding where a repository/Notifier/MethodChannel/value-type/token belongs, authoring or fixing a pubspec.yaml, adding a workspace member, writing an import directive, mirroring a test under test/, or reviewing a diff for organisation.
Route RealityKit work on visionOS 27 and handle core entity/component basics, RealityView scene setup, asset loading, input targets, SwiftUI attachments, anchoring, portals, synchronization, and USDStage bridge usage. Use for general RealityKit triage, choosing documented components, loading Reality Composer Pro, USD, USDZ, or .reality content, and deciding whether to hand off to realitykit-rendering-materials, realitykit-animation-physics, realitykit-audio-spatial, realitykit-ecs-systems, spatial-preview-developer, usdkit-runtime-developer, usd-editor, shadergraph-editor, ARKit, SwiftUI, or build-debug skills
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.