Skills
100,344 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Interview-driven assistant for customers with Kubernetes-based production setups who are getting started with Antithesis. Helps the customer (and the Antithesis engagement team) figure out what their k8s setup contains, what to keep, drop, or stub for testing, and produces structured questions for ops plus an escalation packet when stuck.
AI image generation skill using ChatGPT's latest image model gpt-image-2-all; use when the user needs to generate images, visual infographics, create images, or edit/modify/adjust existing images. Image generation service based on the ChatGPT latest image model gpt-image-2-all on the API 易 platform (https://api.apiyi.com/), with no need for external network access. The model is billed per call at $0.03/image and supports text-to-image, single-image editing, multi-image fusion, and natural-language image editing, with high text fidelity and friendly Chinese prompts. Key differences from NanoBanana2 in controlling size via prompt description (no explicit size parameter): no size parameter, so the size must be described at the start of the prompt; a flat $0.03/image with no resolution tiers; the conversational endpoint /v1/chat/completions is the primary recommendation.
Reference for APM (Agent Package Manager) — apm.yml syntax, install / uninstall / update commands, target detection, lockfile workflow. Read when you need exact field names, but do NOT auto-invoke on every apm-related task; user prompts about projects with installed skills can be handled with general APM knowledge. Invoke explicitly when the user mentions APM by name, asks to author or audit an apm.yml, or runs into an unfamiliar APM command / error.
Use when designing app UI for Apple operating systems—iOS/iPadOS surfaces (sheets, detents, tab bars, large titles, widgets, lock screen, Dynamic Island), macOS (windows, traffic lights, sidebars, menus, vibrancy), visionOS spatial design, watchOS (complications, Digital Crown), or standard UIKit/SwiftUI component anatomy (nav bars, lists, forms, buttons, alerts, search, empty states). Part of the apple-design family. Keywords: iOS design, iPadOS, macOS Tahoe, visionOS, watchOS, spatial, ornament, sheet, presentationDetents, tab bar, navigation bar, large title, sidebar, traffic lights, widget, dynamic island, stage manager, components, SwiftUI, List, Form, button hierarchy, ContentUnavailableView, alert, searchable.
Implement right-to-left (RTL) layouts for Arabic web and mobile applications. Use when user asks about RTL layout, Arabic text direction, bidirectional (bidi) text, Arabic CSS, "right to left", or needs to build Arabic UI. Covers CSS logical properties, Tailwind RTL, React/Next.js RTL setup, Arabic typography, and font selection. Do NOT use for Arabic RTL (similar but different typography) unless user explicitly asks for shared RTL patterns.
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.
Use when a founder wants to document or design a whole company as version-controlled markdown (company as code, a company wiki agents can read, an OKF bundle). Runs a 12-phase interview, scaffolds with scaffold_bundle.py and checks it with okf_linter.py.
Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.
MySQL and MariaDB specifics for Atlas: dev database and URL scope (schema vs server), character sets and collations, users, roles and grants, enum and set columns, generated columns, foreign-key indexes, functional and prefix indexes, triggers and stored programs, table copies and MY lint checks, partial migration failures (no transactional DDL), GET_LOCK, managed services (RDS, Aurora, Cloud SQL, Azure), schema and migration tests, and custom lint rules. Use with the atlas skill whenever Atlas manages a MySQL or MariaDB database
Guided onboarding of a repository onto Atlas, one verified stage at a time: plan the units and the workflow, define the schema as code, set up the migration workflow, add CI with the Atlas Registry, deploy to staging, and promote to production. Each stage ends on a check the agent runs itself, such as a dry run with no changes or a deployment recorded in Atlas Cloud. Use when the user asks to onboard, adopt, or set up Atlas for a project or a team, or to resume an onboarding
Generates Atuntun-style Xiaohongshu cover prompts. For viral vertical cover design for content about AI tools, productivity methods, product reviews, tutorials and deployment, personal experience, podcast recommendations, and workplace insights. Features a real person on camera, oversized soft pale yellow (#FDFFA7) / white Chinese titles, thick black outlines, cutout outlines of people, green checklists, emoji stickers, arrow annotations, and high-contrast, high-density composition. Keywords: Xiaohongshu cover, viral cover, Atuntun style, AI tutorial cover, product review cover, cover prompt.
Find what a change could break beyond its diff, name the one fact it is safe because of, and prove that fact by running real code instead of writing it up. Use for blast radius, what could this break, is this change safe, what else does this touch, reviewing a small diff you do not trust, or /augur.
This skill helps an LLM generate correct core AxAgent code using @ax-llm/ax. Use when the user asks about agent(), child agents, namespaced functions, discovery mode, clarification, bubbleErrors, host-side final/clarification protocol, or ordinary agent runtime behavior. For MCP clients, native runtime modules, subscriptions, tasks, or authentication use ax-mcp alongside this skill. For RLM/code-runtime work use ax-agent-rlm; for callbacks and telemetry use ax-agent-observability; for recall/memory/skill loading use ax-agent-memory-skills; for agent.optimize(...) use ax-agent-optimize.
This skill helps an LLM generate correct AxAgent observability code using @ax-llm/ax. Use when the user asks about axGlobals.onUsage, usageContext, centralized or multi-tenant usage accounting, actorTurnCallback, onContextEvent, agentStatusCallback, onFunctionCall, reportSuccess, reportFailure, getChatLog(), getUsage(), resetUsage(), debug traces, progress updates, or telemetry for AxAgent runs.
This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions, or long-running agent runtime behavior.
This skill helps an LLM generate correct AI provider setup and configuration code using @ax-llm/ax. Use when the user asks about ai(), providers, models, routing, adaptive balancing, presets, embeddings, batch audio with ai.transcribe() or ai.speak(), extended thinking, context caching, or mentions OpenAI/Anthropic/Google/Azure/DeepSeek/Meta/Mistral/Cohere/Reka/Grok/Typesafe/Jev with @ax-llm/ax.
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
Comprehensive Azure cloud expertise covering all major services (App Service, Functions, Container Apps, AKS, databases, storage, monitoring). Use when working with Azure infrastructure, deployments, troubleshooting, cost optimization, IaC (Bicep/ARM), CI/CD pipelines, or any Azure-related development tasks. Provides scripts, templates, and best practices for production-ready Azure solutions.
Connects an app to the Azure SQL Database container securely, with a least-privilege database user instead of the sa login, the right auth method per environment, and safe handling of the connection secret. Use when a user asks "don't use sa in my app", "create a least-privilege database user", "app login for SQL", "which authentication should my app use", "secure the connection string", "Encrypt / TrustServerCertificate", "store the connection string in Key Vault", "dotnet user-secrets", "managed identity for Azure SQL", or "grant only the roles my app needs". SQL auth locally, Microsoft Entra or managed identity in the cloud, changing only the connection string. Reach for this before wiring an app to connect as sa, or before committing a connection string to source.
Backtest crypto and traditional trading strategies against historical data. Calculates performance metrics (Sharpe, Sortino, max drawdown), generates equity curves, and optimizes strategy parameters. Use when user wants to test a trading strategy, validate signals, or compare approaches. Trigger with phrases like "backtest strategy", "test trading strategy", "historical performance", "simulate trades", "optimize parameters", or "validate signals".
AI image generation with OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream and Replicate APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images.
Turn one minimoths crawl session into a dated prices table appended to a product note in the Obsidian vault. Use when asked to update a product note with today's prices, add a prices section, or find the best price for a product after running a search.
Decide whether a system needs a backend-for-frontend, how many, and what each one may own: adoption signals and honest costs, one-experience-one-BFF granularity with frontend-team ownership, the shape-don't-decide rule, upstream aggregation with partial-failure and resilience budgets, identity-keyed BFF caching, mediating user identity toward upstream services (token exchange, confused-deputy prevention), and the alternatives (shared gateway, GraphQL federation, token-mediating backend, direct SPA→API, meta-framework server as BFF). Use when adopting or splitting BFFs, aggregating upstream services, handling upstream failures, forwarding user identity downstream, weighing GraphQL against per-client BFFs, or auditing a BFF that has drifted into a public API or a business-logic layer. For protecting the BFF's own entry points use bff-entry-points; for physical route layout use structure-codebase; for externally consumed API contracts use api-design; for OAuth/OIDC protocol flows use secure-oauth-oidc.
Blade template conventions for any Bagisto package or module (Admin, Shop, or any custom Webkul-style package). Activates when creating or editing Blade views, building Blade components (anonymous @props components or Vue-backed x-template components), wiring forms, datagrids, modals, layouts, or slots, or matching the project's markup, attribute-binding, indentation, and formatting style. The conventions are framework-wide; only the per-package namespace tokens differ.
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
Set up a new app repository for the Boring Factory end to end — create it from the app template (hachej/boring-app), set its secrets and settings, invite the expert, verify the first runs, and hand the expert their next steps. Use when the maintainer asks to create, bootstrap or set up a new app or repository for the Factory, or to connect an existing repository to it.
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.