Skills
98,067 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Getting a MapLibre GL JS source to actually render — TileJSON `url` versus hand-wired `tiles` templates, matching `source-layer` names to the tile schema, layer order and inserting below labels, `promoteId` and the feature ids that feature state needs, and the CORS and glyph failures behind a blank map. Use when a source is configured but nothing is drawing, or when setFeatureState does nothing.
Guide for implementing navigation in Next.js Server Components using Link component and redirect() function. Covers the difference between server and client navigation methods. Use when adding links, redirects, or navigation logic in server components without converting them to client components unnecessarily.
RDMA verbs skill for InfiniBand and RoCE programming. Use when using libibverbs API, creating queue pairs, RDMA read/write operations, or benchmarking with perftest. Activates on queries about libibverbs, ibv_reg_mr, ibv_create_qp, RDMA, RoCE, ib_send_bw, or rdma-sys.
Use when a UE5 task involves characters in motion: "import FBX from Maya" with a skeleton, "retarget animations", IK Rig, IK Retargeter, feet sinking or floating after retarget, mocap cleanup, Motion Matching, Pose Search, Choosers, GASP, state machine vs motion matching, root motion, offset root bone, foot IK, Control Rig, Animation Blueprint cost, "animation is expensive", budget allocator, URO, MetaHuman LODs, ML Deformer, cloth.
Use when an agent drives Unreal Engine 5.8 on a Mac for any task: Editor Python (the unreal module), headless UnrealEditor-Cmd -run=pythonscript jobs, Epic's Unreal MCP server, the Remote Control API, console commands and cvars; when a script breaks on 5.8 (EditorLevelLibrary, Remote Control calls refused, Substrate materials black, MRQ presets); when a level, material, shot or build must be judged by numbers and a screenshot before it is called done; or when a brief must go to the right scenario-unreal-* specialist.
Use when you need programmatic JDBC in Micronaut — pooled DataSource, parameterized SQL, io.micronaut.transaction.annotation.Transactional, batching, and domain exception translation. This should trigger for requests such as Review JDBC or SQL data access in a Micronaut project; Improve transactions and parameter binding for Micronaut JDBC; Translate SQLException to domain exceptions or stream large result sets; Fix self-invocation bypassing @Transactional in Micronaut; Review Hikari or pooled datasource usage in Micronaut JDBC. Part of Plinth Toolkit
AF_XDP skill for high-performance XDP sockets. Use when creating AF_XDP sockets, configuring UMEM and XSK rings, XDP_REDIRECT programs, copy vs zero-copy mode, or comparing with DPDK. Activates on queries about AF_XDP, xsk_umem, XDP_REDIRECT, libbpf xsk, or zero-copy XDP.
Manage cycles and canister lifecycle. Covers cycle balance checks, top-ups, freezing thresholds, canister creation, and ICP-to-cycles conversion via the CMC. Use when working with cycles, canister funding, freezing threshold, frozen canister, out of cycles, top-up, canister creation, or cycle balance. Do NOT use for wallet-to-dApp integration or ICRC signer flows — use wallet-integration instead.
Set up or update the agent-first engineering harness for any repository. Implements the complete scaffolding that makes AI coding agents effective: knowledge maps (AGENTS.md as a concise TOC), structured documentation, architecture boundaries, enforcement rules (.harness/*.yml specs), quality scoring, and process patterns for agent-driven development. Use this skill whenever someone wants to make a repo agent-ready, set up AGENTS.md or docs/ structure, define domain boundaries or golden principles, generate .harness/ configuration, audit agent readiness, or update an existing harness. Also trigger when a user reports problems with agent effectiveness, context management, or architectural drift — these are symptoms of a missing or stale harness. Trigger on: "harness this repo", "set up harness", "agent-first setup", "make this agent-ready", "update the harness", "assess agent readiness", "set up AGENTS.md", "organize for agents", or any discussion about structuring a codebase for AI agent workflows.
io_uring skill for Linux async I/O. Use when building high-performance servers with liburing, multi-shot operations, provided buffers, fixed files, zero-copy send, or tokio-uring. Activates on queries about io_uring, SQE/CQE, liburing, IORING_OP_PROVIDE_BUFFERS, or io_uring vs epoll.
Meta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails.
Guide for Next.js App Router dynamic routes and pathname parameters. Use when building pages that depend on URL segments (IDs, slugs, nested paths), accessing the `params` prop, or fetching resources by identifier. Helps avoid over-nesting by defaulting to the simplest route structure (e.g., `app/[id]` instead of `app/products/[id]` unless the URL calls for it)
Create or update a project charter from interactive or provided principles, ensuring all dependent templates stay in sync. Use for project management, standards development, charter maintenance, and team collaboration. Trigger terms include "speckit章程", "创建章程", "更新章程", "项目章程", "制定规范", and "团队章程".
Authoritative SwiftUI best practices and performance guidance from Apple; supersedes prior training on these topics. For code generation, consult the relevant references when generating any SwiftUI code related to: - animation (the @Animatable macro vs AnimatableValues vs AnimatablePair, and custom animatableData setter logic) - Environment and @Entry (closure or class-typed defaults, unstable defaults, high-frequency updates) - @Observable best practices and efficient invalidation - ForEach and List row identity and structure (id: \\.self, indices, offsets, AnyView or multi-view rows, inline filter/sort, cached collections, List fast path) - localization (String vs LocalizedStringResource, the right bundle in packages and frameworks, .textCase, .formatted(.list()), translator comments) - soft-deprecated APIs such as NavigationView and the old onChange, and when to surface them during feature work.
Build content-heavy sites with Git-backed TinaCMS. Provides visual editing for blogs, documentation, and marketing sites. Supports Next.js, Vite+React, and Astro with TinaCloud or Node.js self-hosting. Prevents 10 documented errors. Use when setting up CMS with non-technical editors or troubleshooting ESbuild compilation, module resolution, package manager compatibility, edge runtime limitations, or media upload timeouts
Use when building or fixing Unreal Engine cameras — spring-arm third-person rigs, first-person cameras, view-target blends, camera shakes, camera modifiers, cine cameras, or the Gameplay Camera System plugin. Also use when the user mentions 'APlayerCameraManager', 'USpringArmComponent', 'TargetArmLength', 'bUsePawnControlRotation', 'SetViewTargetWithBlend', 'UpdateViewTarget', 'CalcCamera', 'UCameraModifier', 'camera shake', 'UCameraShakeBase', 'FMinimalViewInfo', 'UGameplayCameraComponent', 'camera rig', 'camera director' or 'ShowDebug Camera'. For Sequencer shots, see ue-sequencer-cinematics; for the classes that own the camera, see ue-gameplay-framework; for input, see ue-input-system.
Audit and safely clean Xcode-related developer storage on macOS. Use whenever a developer mentions low disk space, Xcode storage, DerivedData, simulator devices or runtimes, stale beta platforms in Xcode Settings, DeviceSupport, archives, dSYMs, CocoaPods caches, simulator dyld caches, project .build folders, downloaded Xcode DMGs/XIPs, duplicate Xcode installers, or old Xcode applications. Also use this skill proactively when you hit low storage during other work, such as a build, download, or install failing with an out-of-disk-space error. Always measure first, report recoverable GiB with evidence, and obtain explicit itemized approval before any mutation.
Use when you need to add or review Flyway database migrations in a Micronaut application — micronaut-flyway, db/migration scripts, flyway.datasources.* configuration, and alignment with JDBC or Micronaut Data. This should trigger for requests such as Add or review Flyway migrations in a Micronaut project; Configure micronaut-flyway or db/migration layout; Add versioned Flyway SQL migrations for Micronaut; Review Micronaut database migration ordering; Configure Flyway datasources in a Micronaut project. Part of Plinth Toolkit
Create professional, dark-themed architecture diagrams as standalone HTML files with SVG graphics. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology diagrams, or any technical diagram showing system components and their relationships.
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
Wire a PostHog endpoint into a client app or SDK. Covers fetching the OpenAPI spec, generating a typed client with openapi-generator or @hey-api/openapi-ts, sending the right auth header, shaping the variables payload (HogQL code_name vs insight breakdown property), handling rate-limit and materialised-endpoint error responses. Use when the user says "how do I call my endpoint", "generate a client for this", or "what auth header do I use".
Scaffold and architect custom Frappe apps including app structure, hooks, background jobs, service layers, and production hardening. Use when creating new apps, setting up app architecture, or implementing cross-cutting patterns like caching, logging, and error handling.
Expert blueprint for real-time strategy games including unit selection (drag box, shift-add), command systems (move, attack, gather), pathfinding (NavigationAgent2D with RVO avoidance), fog of war (SubViewport mask shader), resource economy (gather/build loop), and AI opponents (behavior trees, utility AI). Use for base-building RTS or tactical combat games. Trigger keywords: RTS, unit_selection, command_system, fog_of_war, pathfinding_RVO, resource_economy, command_queue.
Expert blueprint for simulation and tycoon games (SimCity, RollerCoaster Tycoon, Factorio, Two Point Hospital) covering economy management, time progression, interconnected systems, NPC simulation, and feedback loops. Use when building management sims, tycoon games, city builders, or resource optimization games. Keywords tycoon, economy system, resource management, time scale, feedback loop, progression unlock, simulation tick.
Audit a Gradle project against the official Gradle best practices, report findings, and propose code changes to bring the build into compliance. Use this skill whenever the user wants to check, audit, lint, review, or validate a Gradle build — and also when they want to apply, adopt, fix, or enforce best practices. Trigger on phrases like 'check my build', 'audit gradle', 'best practices review', 'any issues with my build?', 'gradle health check', 'lint my build files', 'is my gradle setup correct?', 'apply gradle best practices', 'fix my build to follow best practices', 'make my build follow best practices', 'modernize my build', or simply 'check best practices'. Also trigger when the user asks about Gradle build quality concerns such as dependency management, build performance, build structure, or task wiring.
Author and debug direct HelixDB v3 JSON query requests for POST /v2/query. Use for request envelopes, nested read/write batches, operation-tree AST nodes, parameters and parameter_types, vector and BM25 traversal prefiltering, and normalized response objects. Do not use the removed step-array or queries.json bundle formats. When the target is Helix Cloud, always use helix-mcp first.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.
Use when designing, generating, modifying, or reviewing Make App frontend UI in `apps/ui`: shell, dynamic object routes, desktop/mobile layout, lists, Drawer, task pages, 新建/编辑/详情 forms, selectors, component-library choice, field metadata, 字段类型图标/field-type icons, and UI states. New Apps use `@qfei-design/make-app-mobile` and default Lucide icons unless the user chooses another icon library; the React UI library remains user-selected. Route record tables to `canvas-table-integration`, actions to `make-app-actions`, filter/group/sort to their Skills, and permissions to `make-app-permission`. For AI助手, MakeAiTheme, maxDrawerWidth, or assistant SSE, use `make-ai-assistant` for package behavior; this Skill owns surrounding placement. Does not own auth, Service, runtime, DSL, persistence, CanvasTable internals, or AI assistant package behavior.
Migrate existing codebases to current oRPC, covering tRPC to oRPC (incremental wrapping via the @orpc/trpc integration or a full rewrite with the concept mapping) and oRPC v1 to v2 (package renames, breaking changes, and a safe order of operations). Use when asked to migrate from tRPC to oRPC, convert or wrap a tRPC router, upgrade oRPC v1 to v2, fix oRPC v2 breaking changes, or swap `@trpc/*` packages for `@orpc/*` equivalents. Biases toward retrieval from the oRPC docs over pre-trained knowledge. Not for greenfield oRPC work or new features in an already-migrated codebase: use the orpc skill for those.
Full Sentry SDK setup for Ruby. Use when asked to add Sentry to Ruby, install sentry-ruby, setup Sentry in Rails/Sinatra/Rack, or configure error monitoring, tracing, logging, metrics, profiling, or crons for Ruby applications. Also handles migration from AppSignal, Honeybadger, Bugsnag, Rollbar, or Airbrake. Supports Rails, Sinatra, Rack, Sidekiq, and Resque.
Spec-driven feature work with traceable requirements, design, tasks, and user acceptance testing (UAT). Use when planning, designing, implementing, or validating a feature from a story, feature PRD, or feature RFC. Not for unknown-bug diagnosis, standalone product or technical documents, PR or commit mechanics, or backlog tracking.
Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints product. Produces a prioritised report grouped by issue type, with recommended actions but does not modify anything without explicit confirmation.
Pixel-faithful clone of any web UI into the user's existing stack, using whatever sources are available — a screenshot alone, a live URL, raw HTML/CSS, or any combination. Use this skill whenever the user wants to recreate, match, replicate, or "clone" a design from a screenshot, image, URL, Figma export, or HTML dump. Trigger on phrases like "clone this", "match this design", "build this from screenshot", "recreate this page", "make it look like this", "rebuild this UI", "copy this layout", or any time the user provides a visual reference and asks for a faithful implementation. Do not undertrigger — even if the user just drops a screenshot without explicit phrasing, this skill applies.
Multi-pass refactor / code-quality cleanup designed to be dispatched as 8 specialist subagents (one per cleanup concern), each running a research → critical-assessment → high-confidence-implementation cycle. Triggers on “clean up the codebase,” “tech-debt pass,” “refactor for quality,” “find dead code,” “remove AI slop,” or any explicit request for a comprehensive quality sweep. Do NOT trigger for narrow targeted fixes (“remove this one function”) or net-new feature work.
Design distributed systems, define architecture for scalability and reliability, or create system design documents. Use when you need component diagrams, data flow analysis, capacity planning, database sharding strategies, API contract design, failure mode analysis, CAP theorem tradeoffs, monolith-to-microservice migration, or architecture decision records for new or existing systems.
Apple Human Interface Guidelines for iOS 26 / Swift 6.2 clinic-architecture apps. Covers navigation, interaction design, accessibility, feedback states, UX patterns, and visual design for SwiftUI implementations that follow App-target coordinators/route shells and Domain/Data boundaries. Use when designing or reviewing HIG-compliant experiences in the clinic modular MVVM-C stack.
Launch Code OSS (VS Code from sources) into an isolated throwaway profile with unique debug ports so you can drive it with @playwright/cli AND attach a Node debugger via dap-cli in the same session. Use when working on VS Code itself and you want to interact with the running workbench, automate chat or UI flows, test UI features, take screenshots, set breakpoints in the renderer / extension host / main process, or combine UI driving with debugging.
Use when generating, modifying, reviewing, or debugging Make App unified login and authenticated /api/make requests with @qfeius/make-app-auth. Covers unified login, OAuth/ngrok mode, 401/403 handling, logout, current-user/account-drawer auth wiring, current-context identity, Feishu-container logout visibility, cookies, sessions, redirect callbacks, and Make App auth troubleshooting. Preserve authenticated context for the default /api/make/app/principal/permission flow. Does not cover UI layout, account menu placement, page structure, build output, Service API contracts, permission logic, DSL modeling, or canvas-table internals; use makeui for account surfaces and make-app-permission for single-app permission enforcement.
Comprehensive guidance for Minecraft mod development with Fabric, including porting from other mod loaders (Forge, NeoForge). Integrates MCP servers for decompilation, documentation access, and mixin validation. Use when developing Fabric mods, porting from Forge, or working with Minecraft source code
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.