Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Audit and enforce the core/client boundary in multi-client projects. Detects where shared platform code is tangled with client-specific code, finds hardcoded client checks, config files that replace instead of merge, scattered client code, migration conflicts, and missing extension points. Produces a boundary map, violation report, and refactoring plan. Optionally generates FORK.md documentation and restructuring scripts. Triggers: 'fork discipline', 'check the boundary', 'is this core or client', 'platform audit', 'client separation', 'fork test', 'refactor for multi-client', 'clean up the fork'.
Setup Sentry AI Agent Monitoring in any project. Use when asked to monitor LLM calls, track AI agents, or instrument OpenAI/Anthropic/Vercel AI/LangChain/Google GenAI/Pydantic AI. Detects installed AI SDKs and configures appropriate integrations.
Documents edge cases, error states, boundary conditions, race conditions, and recovery paths for a feature - the systematic catalog of what can go wrong and the failure modes to design for. Use during specification to map the failure surface and ensure comprehensive coverage, or during QA planning to identify boundary and limit scenarios to test. Distinct from deliver-acceptance-criteria, which writes story-level Given/When/Then checks; this skill produces the whole-feature edge-case catalog.
Activate when the user asks about any repository listed in the system prompt under 'OpenViking — Indexed Code Repositories', or when they ask about an external library, framework, or project that may have been indexed. Also activate when the user wants to add, remove, or manage repos. Always search the local codebase first before using this skill
Use this skill when using Arcade Physics in Phaser 4. Covers enabling physics, velocity, acceleration, gravity, collisions, overlap, world bounds, physics groups, static bodies, and collision categories. Triggers on: physics, arcade, velocity, gravity, collide, overlap, bounce, physics body.
Extracts files from repomix-packed repositories, restoring original directory structures from XML/Markdown/JSON formats. Activates when users need to unmix repomix files, extract packed repositories, restore file structures from repomix output, or reverse the repomix packing process.
Initialize an Adobe App Builder project end-to-end and prepare the machine to build one. Creates the Console project and workspace, subscribes APIs (including those needing a product profile), maps intent to the right template, runs non-interactive `aio app init`, and guides post-init customization. Use whenever the user mentions creating an App Builder app, scaffolding a project, `aio app init`, an Experience Cloud extension, adding actions or web assets, or creating a Console project/workspace — even without saying "App Builder". Also for SPA templates, AEM extensions, API Mesh, Asset Compute workers, and MCP servers. Also covers first-time machine/CLI setup (Node 20, aio CLI install, `aio login`, IMS org, stage vs prod) and debugging setup/init failures — `ERR_REQUIRE_ESM`, empty `aio console org list`, `451 accept developer terms`, template not found, init hangs, or Node/npm and post-init build errors.
Babysits an open GitHub PR until merge-ready, first judging whether an old PR still belongs. Use when asked to watch a PR over time or update an old one — not for one-shot comment resolution or one CI failure. GitHub (incl. Enterprise) only
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
Autonomously optimizes end-to-end LLM inference throughput on AMD Instinct GPUs and reports a validated gain, using the Hyperloom multi-agent optimizer. Given a model, framework, workload (TP/EP, concurrency, ISL/OSL, precision), an objective and a time budget, it explores per-workload which levers to pull (serving/config parameters and env, framework enablement and source patches, and hot GPU-kernel rewrites), benchmarks each candidate, and returns the optimization stack that produced the gain. Use when the user wants to make a model serve faster, raise tokens/sec or throughput, optimize or tune vLLM or SGLang on MI300X/MI325X/MI355X, run Hyperloom, run the kernel-agent, quantize-then-optimize with Quark, set up Hyperloom from scratch, or resume a Hyperloom session. Do not use to stand up a server for plain serving, diagnose a broken ROCm install, or run a one-off kernel/benchmark or trace analysis without the optimization loop.
Create, read, update, and delete ManagedEventSubscription metadata in Salesforce. Use this skill for any work involving managed event subscriptions, platform event subscriptions, event channel subscribers, or .managedEventSubscription-meta.xml files. TRIGGER when: user asks to subscribe to a platform event, create a managed subscription, set up event replay, configure an event channel subscriber, update replay preset, activate or deactivate a subscription, delete a subscription, or manage ManagedEventSubscription metadata. SKIP when: user needs to create the platform event channel itself (use generating-platform-event skill) or needs Flow-based event subscriptions (use generating-flow skill).
Configures a web framework build so Capacitor can ship it as an iOS/Android app. Use for Next.js static export (output 'export', out/), Nuxt 4 (ssr false, nuxt generate, .output/public), Angular (dist/<project>/browser), SvelteKit adapter-static (SvelteKit 2 svelte.config.js or SvelteKit 3 vite.config), React/Vue/Svelte/Solid on Vite, and React Router framework SPA mode. Covers webDir mismatch, blank white screen after cap sync, missing index.html, SSR/API routes/middleware/server actions that cannot run in the app, next/image errors, deep-link reloads landing on the home page, router base paths, and env variables. Do not use for whole-app store readiness (webapp-to-capacitor), Cordova projects (cordova-to-capacitor), Capacitor major upgrades (capacitor-app-upgrades), or UI kits (ionic-design, konsta-ui, tailwind-capacitor).
Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues
Rapidly scaffold and implement a playable game — no assets, design, audio, deploy, or monetize. Get something on screen fast. Use when the user says "quick game", "fast prototype", "just get something playable", or wants a game without the full pipeline. For the complete one-shot pipeline (deploy + monetize), use /viral-game instead. For a milestone-driven project, use /make-game. Do NOT use for production games.
Apex code quality guardrails for Salesforce development. Enforces bulk-safety rules (no SOQL/DML in loops), sharing model requirements, CRUD/FLS security, SOQL injection prevention, PNB test coverage (Positive / Negative / Bulk), and modern Apex idioms. Use this skill when reviewing or generating Apex classes, trigger handlers, batch jobs, or test classes to catch governor limit risks, security gaps, and quality issues before deployment.
A basic WeChat Pay payment solution covering payments, refund statements, profit sharing, merchant onboarding, and confirmation of account-opening intent. Provides five capabilities: solution selection, code examples, business quick reference, quality assessment, and troubleshooting. Use when the user mentions “JSAPI payment,” “APP payment,” “H5 payment,” “Native payment,” “mini program payment,” “payment code payment,” “combined payment,” “special-merchant onboarding,” “confirmation of account-opening intent,” or asks to “recommend a payment method,” “provide payment API code examples,” or “troubleshoot payment or refund issues.”
Searches the official PIG documentation and summarizes the answer. Triggered when the user asks technical questions about PIG CLOUD, PIG AI or pigx, how to configure or implement something, or explicitly says "check the docs" or "look it up". For specific questions about the PIG framework, search the documentation first before answering instead of relying on potentially outdated training data.
Check whether a RevenueCat user currently has access to a paid feature via entitlements. Use when the user asks to gate a feature behind premium, check if the user has a pro subscription, read customerInfo active entitlements, show or hide a feature based on subscription status, react to entitlement changes, or 'is the user subscribed' on iOS, Android, Kotlin Multiplatform, Flutter, or React Native.
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.