Skills
97,905 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Route Node package-delivery ambiguity into one install packet: temporary Git bridge, SHA-pinned shared bridge, private-auth Git path, tarball / `npm pack` artifact, workspace / `file:` inner-loop, or publish-first registry handoff. Use when the user wants to install an npm / pnpm / Yarn / Bun package from a branch, tag, commit, fork, private repo, monorepo package, or unreleased fix, and the real question is which delivery path is safest rather than how Git or package registries work in general. Triggers on: npm install from GitHub, git dependency, github:owner/repo, git+ssh, git+https, private package from repo, install branch vs commit, monorepo package install, npm pack vs git, and should we publish this instead.
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
This skill should be used when the user asks to design, create, choose, modernize, or review a terminal UI, text user interface, curses app, dashboard, wizard, REPL shell, prompt flow, or CLI with interactive screens. PROACTIVELY activate for: TUI architecture, terminal-ui design, framework selection, curses vs modern framework, full-screen vs inline UI, app state modeling, widget composition, command palette, keyboard-first workflow, terminal dashboard, interactive CLI UX, and cross-platform terminal product planning. Provides: architecture patterns, framework decision rules, UX guardrails, scope boundaries, and production readiness checklists
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Set up or repair codecontext adoption in a project. Use this whenever the user wants to add @context annotations to a repo, install the codecontext toolchain, update AGENTS.md guidance, improve agent workflows around decision capture, or audit whether an existing codecontext setup is coherent. Prefer this skill over vague "document the tool" work: it is specifically for making a repo actually usable with codecontext.
Add and configure Contentful in an existing Next.js project. Covers installing the JavaScript SDK, configuring environment variables, creating production and preview-aware clients, fetching content in App Router or Pages Router, and wiring Draft Mode preview flows. Use when users ask to integrate Contentful with Next.js, fetch entries, set up preview or draft content, or configure the Contentful client. Also triggers on "Contentful SDK Next.js", "contentful.js", "fetch Contentful entries", "get content from Contentful", "Contentful preview", "preview mode", "Contentful environment variables", "Contentful client setup", "create Contentful client", "Pages Router Contentful", "getStaticProps Contentful", "Server Components Contentful", "revalidate Contentful", "ISR Contentful". Not for personalization or Experiences SDK setup (contentful-personalization). Not for non-Next.js frameworks (contentful-guide can route to platform docs).
Comprehensive blueprint for Action RPGs including real-time combat (hitbox/hurtbox, stat-based damage), character progression (RPG stats, leveling, skill trees), loot systems (procedural item generation, affixes, rarity tiers), equipment systems (gear slots, stat modifiers), and ability systems (cooldowns, mana cost, AOE). Based on expert ARPG design from Diablo, Path of Exile, Souls-like developers. Trigger keywords: action_rpg, loot_generator, rpg_stats, skill_tree, hitbox_combat, item_affixes, equipment_slots, ability_cooldown, stat_scaling.
SwiftUI animation patterns: implicit and explicit animations, transitions, phase and keyframe animations, the Animatable protocol, and the @Animatable macro. Use when implementing animations, transitions, or motion in SwiftUI views.
Memory hierarchy skill for caches, coherence, and locality. Use when explaining cache levels, associativity, false sharing, prefetching, or MESI coherence. Activates on queries about cache hierarchy, L1 L2 L3, false sharing, cache line, prefetch, or cache coherence.
Use when writing or reviewing n8n expressions (`{{...}}` syntax), `$json` / `$node` references, Luxon date code, or expression errors. Triggers on `{{}}`, `$json`, `$node`, `$input`, `DateTime`, `Luxon`, "expression error", "evaluating", "format date", "transform field", or any node-parameter assignment.
Implements Syncfusion Angular Grid component for feature-rich data tables and grids. Use this when working with data display, sorting, filtering, grouping, aggregates, editing, or exporting. This skill covers grid configuration, CRUD operations, virtual scrolling or infinite scrolling, hierarchy grids, state persistence, and advanced data management features for data-intensive applications.
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
Use when working with n8n workflows in any capacity. The always-on protocol for the n8n-skills plugin, loaded by the SessionStart hook every session. Routes to the right skill, summarizes every n8n MCP tool (closing the deferred-description gap), and lists the cross-cutting rules.
Install and configure a Claude Code status line that displays real-time ZenMux account information: subscription tier, 5-hour and 7-day quota usage with color-coded progress bars, and PAYG wallet balance, alongside standard session info (model, git, context usage, prompt cache). Trigger on: "status line", "statusline", "set up status bar", "show ZenMux in status bar", "install ZenMux statusline", "configure status line with ZenMux", "状态栏", "配置状态栏", "安装状态栏", "在状态栏显示ZenMux信息". Activate when user wants to SET UP, INSTALL, CONFIGURE, or CUSTOMIZE a Claude Code status line that includes ZenMux account data. Do NOT trigger for querying usage interactively (use zenmux-usage), docs (use zenmux-context), or general setup (use zenmux-setup).
Add bot protection with Turnstile (CAPTCHA alternative). Use when protecting forms, securing login/signup, preventing spam, migrating from reCAPTCHA, integrating with React/Next.js/Hono, implementing E2E tests, or debugging CSP errors, token validation failures, Chrome/Edge first-load issues, multiple widget rendering bugs, timeout-or-duplicate errors, or error codes 100*/106010/300*/600*
Apply Fastify best practices when creating servers, plugins, routes, schemas, hooks, configuration, decorators, authentication, logging, performance tuning, database integration, migrations, testing, clean architecture, and TypeScript integration. Use when writing or reviewing Fastify code, setting up a new Fastify project, or asking "How should I structure my Fastify app?"
Reverse-engineers Apple firmware and binaries with the ipsw CLI. Inspects IPSWs and OTAs remotely or locally; extracts kernelcaches, dyld_shared_cache, exclave, SEP, and coprocessor firmware; disassembles and cross-references DSC dylibs, KEXTs, and Mach-Os; dumps and diffs ObjC/Swift headers; decompiles and queries sandbox profiles; searches entitlements; symbolicates crashes and panics; and diffs releases. Use for iOS/macOS internals, private frameworks, kernel or firmware research, and Apple security research, even when ipsw is not named.
Use when the user reaches for a Code node, mentions writing JavaScript or Python in n8n, or any custom logic comes up in workflow design. Triggers on "Code node", "Code", "JavaScript", "Python", "custom logic", "transform data", "$input", "$json transformation", "loop in code", "write a function", or any time the obvious answer seems to be "just put it in code."
Manages Starwind UI v3 in Astro and React projects—initializing, migrating, adding, updating, searching, debugging, styling, theming, and composing styled components, Primitive adapters, or Runtime integrations. Use for Starwind components, starwind.config.json, Tailwind CSS v4 themes, V2-to-V3 migration, or Starwind CLI/MCP work.
Comprehensive guide for implementing Syncfusion Blazor MultiColumn ComboBox component. Use this when displaying structured data in a dropdown with multiple columns, filtering, selection, paging, virtualization, grouping, and customization options. Perfect for complex data structures and advanced filtering scenarios in Blazor applications. Covers all MultiColumn ComboBox features from Syncfusion.Blazor.MultiColumnComboBox package.
Comprehensive vitest testing guidance for TypeScript projects. Use when (1) writing new tests with the AAA pattern, parameterized tests, or async/await, (2) reviewing test code for anti-patterns like loose assertions (toBeTruthy), over-mocking, or nested describe blocks, (3) optimizing slow test suites, or (4) implementing property-based testing with fast-check — especially for encode/decode pairs, roundtrip properties, validators, normalizers, and idempotence checks. Covers test organization, assertions, test double hierarchy (fakes/stubs/mocks), async testing, performance patterns, and property-based testing patterns. Trigger keywords include vitest, *.test.ts, describe, it, expect, vi.mock, fast-check, fc.property, roundtrip, and idempotence.
Create OpenCode plugins using the @opencode-ai/plugin SDK. Use for building custom tools, event hooks, auth providers, or tool execution interception. Use proactively when developing new plugins in .opencode/plugin/ or ~/.config/opencode/plugin/. Examples: - user: "Create a plugin to block dangerous commands" → implement tool execution before hook with blocking logic - user: "Add a custom tool for jira" → design tool schema and implementation using SDK context - user: "Show toast on file edit" → react to file edit events and display status message - user: "Build a custom auth provider" → implement auth flow for new model provider - user: "Intercept git commits" → add hook to validate commit messages before execution
Use when writing, running, configuring, reviewing, or debugging code in a Deno project, or when scaffolding a new one. Covers dependency management with deno install and deno add, package.json and node_modules support, npm and JSR packages, permissions, where configuration belongs across package.json, tsconfig.json and deno.json, workspaces, the built-in toolchain (fmt, lint, test, check, bench, compile), and publishing.
Email has the highest ROI of any marketing channel. $36 for every $1 spent. Yet most startups treat it as an afterthought - bulk blasts, no personalization, landing in spam folders. This skill covers transactional email that works, marketing automation that converts, deliverability that reaches inboxes, and the infrastructure decisions that scale. Use when: keywords, file_patterns, code_patterns.
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
Route Firebase AI feature work into either direct app/client Firebase AI Logic SDK integration or a server-owned Genkit workflow. Use when a web, mobile, backend, or full-stack feature needs model calls, typed outputs, reusable flows, tools, retrieval, prompt files, evals, observability, or deployment. Choose client-ai-logic, flow-foundation, tool-and-agent, retrieval-and-prompt, evaluation-and-observability, deployment-runtime, or comparison-or-fallback; route Firebase platform/operator work to `firebase-cli` and broad framework comparisons to `survey`.
Use when querying or extending GitNexus's PDG control/data-dependence surface (the `pdg_query` MCP tool, CDG/REACHING_DEF edges), or reasoning about "what controls X" / "where does Y flow" / guard clauses. Examples: "what guards this statement?", "trace this variable within the function", "why is the pdg_query result empty?", "add a CDG query".
Investigates a single PostHog error tracking issue end-to-end. Use when the user provides an issue ID or pastes an issue URL (`/error-tracking/<id>`) and wants to understand the error — who it affects, what triggers it, when it started, whether it correlates with a release, browser, OS, or feature flag, and what the next step should be. Pulls aggregated metrics, sample exception events, segment breakdowns, linked replays, and synthesizes a hypothesis-grade summary in one pass
Use when building or debugging Unity gameplay systems: enemy AI that patrols, chases and attacks, NavMesh baking and agents (AI Navigation 2), feet sliding on agents, state machines or behavior trees, physics projectiles that tunnel, the physics spiral, layers and the collision matrix, CharacterController vs Rigidbody characters, object pooling, 'hundreds of enemies', DOTS, Burst or Jobs decisions, Netcode for GameObjects multiplayer, audio mixers, snapshots, volume sliders and 3D combat sounds.
Use when a Unity 6.3 game is slow or stutters: low FPS, frame spikes, hitches when entering areas or during first-time effects, GC spikes, too many draw calls or SetPass calls, CPU vs. GPU bottleneck questions, work with Profiler, Profile Analyzer, Memory Profiler, Frame Debugger, or Project Auditor, GPU Resident Drawer or SRP Batcher setup, LOD and Mesh LOD, shader warm-up and variants, memory or VRAM budgets, IL2CPP and build size, or proving a fix with player data
Use when setting up URP (or choosing URP vs HDRP), configuring URP assets and quality tiers for PC and phones, lighting a stylized or realistic Unity scene (sun, sky, baked or mixed lightmaps, Shadowmask, Adaptive Probe Volumes, reflection probes), or fixing blurry shadows, light leaks, gray bakes, washed-out images, tonemapping and grading, bloom too expensive on mobile, TAA, STP or MSAA choices, GPU Resident Drawer setup, shader warm-up hitches, or a custom shader that vanished or lost its baked light.
Implement Syncfusion Blazor Toolbar (SfToolbar) component for creating interactive command bars and toolbars. Use this when working with toolbars, command bars, or action bars with buttons and icons. This skill covers responsive toolbars with overflow handling, item configuration and alignment, keyboard navigation, accessibility features, and dynamic item management.
Uniwind best practices for React Native styling with Tailwind CSS. This skill should be used when writing, reviewing, or refactoring React Native code using Uniwind. Triggers on tasks involving Uniwind, className styling, Tailwind in React Native, NativeWind migration, or theming.
Voice agents represent the frontier of AI interaction - humans speaking naturally with AI systems. The challenge isn't just speech recognition and synthesis, it's achieving natural conversation flow with sub-800ms latency while handling interruptions, background noise, and emotional nuance. This skill covers two architectures: speech-to-speech (OpenAI Realtime API, lowest latency, most natural) and pipeline (STT→LLM→TTS, more control, easier to debug). Key insight: latency is the constraint. Hu
Guides the creation of agile user stories. Use when the user wants to create a user story. This should trigger for requests such as Create a user story; Write a user story; I need to write a user story; Split feature requirements into user stories. Part of Plinth Toolkit
Integrate, fix, review, migrate, test, or debug Duit / flutter_duit backend-driven UI in Flutter applications. Use when a task mentions DUIT, flutter_duit, backend-driven UI, BDUI, server-driven UI, XDriver, DuitViewHost, DuitRegistry, HTTP or WebSocket transports, custom Duit widgets, components, capability delegates, compile-time DUIT flags, or rendering JSON layouts from a backend.
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.