Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Use this skill whenever the user is working with Drizzle ORM on PostgreSQL. This covers any mention of Drizzle, drizzle-orm, drizzle-kit, drizzle-zod, `pgTable`, `defineRelations`, `relations()`, `db.select()`, `db.query`, or insert/update/delete against Postgres. Typical intents to trigger on: - Designing or debugging Postgres table schemas, columns, identity PKs, enums, JSONB, arrays - Modeling one-to-many or many-to-many relations and join tables in Drizzle - Writing, optimizing, or preparing Drizzle queries (placeholders, `.prepare()`) - Generating Zod validators from Drizzle tables - Setting up TypeScript + Postgres projects (Neon, Supabase, postgres.js, node-postgres) with Drizzle - Migrating from Prisma, TypeORM, or Sequelize **to Drizzle** - Resolving Drizzle type errors; choosing between v1 RC and 0.45.x APIs Do NOT trigger for Drizzle with MySQL/SQLite, raw SQL without an ORM, or other ORMs when Drizzle is not the target.
Plan and execute large refactor or rewrite efforts efficiently with parallel multi-agent analysis and implementation. Use when a user asks to refactor many files, split workstreams, analyze a target code area, and coordinate sub-agents with clear ownership and dependency-aware execution.
Creates and deploys Node.js HTTP web applications on AWS Lambda Web Functions. Guides users through building web apps and APIs with Express, Fastify, or Hono, packaging, deploying via the aws lambda-web CLI, and iterating. Triggers when user wants to deploy a website or web app to AWS as serverless, deploy a Node.js HTTP server to AWS, build a serverless website or API with Node.js, deploy Express/Hono/Fastify apps, set up multi-region HTTP endpoints, connect a Node.js web app to private VPC resources, or explicitly mentions Lambda Web Functions. Does NOT trigger for non-Node.js runtimes or frameworks such as Flask or Django, event-driven patterns (SQS, Kinesis, S3 events), or container deployments.
Automate Pulumi provider repo upgrades with the `upgrade-provider` tool. Use when upgrading a pulumi provider repository to a new upstream version, running `upgrade-provider`, and addressing its common failure modes like patch conflicts or missing module mappings.
Create and edit React Native Storybook stories using Component Story Format (CSF). Use when writing .stories.tsx files, adding stories to React Native components, configuring Storybook addons (controls, actions, backgrounds, notes), setting up argTypes, decorators, parameters, or working with portable stories for testing. Applies to any task involving @storybook/react-native story authoring.
Migrates Capacitor apps off Ionic Enterprise SDK plugins - @ionic-enterprise/auth (Auth Connect), @ionic-enterprise/identity-vault (Identity Vault), and @ionic-enterprise/secure-storage (Secure Storage) - to @capgo/capacitor-social-login (OAuth2/OIDC for Azure AD, Auth0, Okta, Cognito, plus Google/Apple), @capgo/capacitor-native-biometric (biometric-protected Keychain/Keystore credential vault), and @capgo/capacitor-fast-sql or @capgo/capacitor-data-storage-sqlite (encrypted storage). Use when package.json has @ionic-enterprise/* packages, code imports AuthConnect, BrowserVault/Vault/DeviceSecurityType, or SQLite from secure-storage, or the user needs to move stored tokens without logging users out. Do not use for Ionic Appflow live updates or builds (ionic-appflow-migration), generic SQLite plugin swaps (sqlite-to-fast-sql), Capacitor version upgrades (capacitor-app-upgrades), or Capgo live updates (capgo-live-updates).
A comprehensive Flutter UI library inspired by shadcn/ui. Provides high-quality, customizable, and accessible components including Buttons, Cards, Forms, and more. Use this skill when building Flutter UIs, implementing design systems, or needing specific component usage examples.
Look up Wix API/SDK documentation to confirm an exact endpoint, HTTP method, request/response shape, field, enum, or error before writing Wix code—never guess a Wix API from memory. A lookup is a short flow: find the right page, then read it. Two ways: (1) plain `curl` (zero dependencies)—find a page by semantic search (`POST /mcp-docs-search/v1/docs/search`, natural-language `{ search_term, document_type(s) }`, including the SKILLS recipe corpus for multi-step workflows) or by browsing a docs portal as a menu—a structured, typed, counted browse of the REST, SDK, CLI, Build Apps, and Headless portals (`POST /mcp-docs-search/v1/docs/menu/browse`), or the `.md` menu tree from the `llms.txt` root for any surface—then read the page by appending `.md` to its URL; (2) Wix MCP doc tools when present. Triggers: look up a Wix API, find the Wix endpoint/method, confirm a Wix request body or field, verify a Wix API shape, explore Wix docs, which Wix API do I call, read a Wix method schema.
Expert Godot shader patterns for batch-safe hitflash, alpha-scissor foliage/dissolve, screenspace postFX, depth reconstruction, triplanar, and instance uniforms — not first-shader tutorials. Trigger on draw-call batching breaks, discard vs depth-prepass, foliage shadows, post-process quads, or world-position FX. Keywords: instance uniform, ALPHA_SCISSOR, hint_screen_texture, hint_depth_texture, global uniform, sampler2DArray, canvas_item, spatial, post-processing.
Essential native macOS development patterns that web developers don't know about. Use this skill whenever the user is building a macOS app and needs guidance on native patterns, or when they ask about menu bar apps, floating panels, window levels, keyboard shortcuts, file pickers, clipboard, drag and drop, screen capture, activation policy, Quick Look, launch at login, or any macOS-specific API. Also trigger when the user seems to be applying web development patterns to macOS (e.g., using z-index thinking for windows, expecting simple clipboard APIs, or not understanding focus/activation). This is the "how things actually work on macOS" reference that prevents the AI from generating confident but wrong code. Use this skill proactively whenever building any native macOS app.
Guide for implementing, configuring, and debugging React Joyride v3 guided tours. Use this skill whenever the user mentions joyride, guided tour, onboarding tour, walkthrough, tooltip tour, step-by-step guide, product tour, or wants to highlight UI elements sequentially. Also use when debugging tour issues like tooltips not appearing, targets not found, or controlled mode problems. This skill covers the useJoyride hook, Joyride component, step configuration, events, controls, custom components, and styling.
x86-64 assembly skill for reading, writing and debugging assembly code. Use when reading GCC/Clang assembly output, writing inline asm in C/C++, understanding the System V AMD64 ABI calling convention, or debugging register and stack state. Activates on queries about x86-64 assembly, AT&T vs Intel syntax, inline asm, calling conventions, SIMD intrinsics, or reading disassembly output from objdump or GDB.
Guided entry point for using Sentry through your agent. Orients you to your current setup and, for a new project, sets up Sentry end to end with sane defaults — provision a project, install the SDK (errors, tracing, and whatever it enables by default), and confirm real telemetry reaches Sentry. Routes other intents (adding more signals, fixing issues) to the right skill.
Generic Python coding guidelines covering style, typing, OOP design, testing, and tooling. Use when writing Python code outside of a Django context — scripts, CLIs, microservices, data pipelines, tooling. Do NOT use for Django-specific patterns (use ac-django instead).
Use this skill whenever the user wants to create, customize, or troubleshoot X6 v3 graph editor diagrams. Triggers include: any mention of 'X6', 'antv x6', '@antv/x6', 'X6 editor', 'X6 图编辑', '流程图', 'DAG', 'ER图', '实体关系图', '血缘图', '组织架构图', 'UML类图', 'flowchart', 'DAG diagram', 'ER diagram', 'lineage graph', 'org chart', 'network topology', 'stencil', 'drag-and-drop editor', 'port connection', 'node port edge', 'graph editor', 'diagram editor', or requests about X6 node/edge styling, plugins (Selection, History, Clipboard, Keyboard, MiniMap, Scroller, Snapline, Stencil, Dnd, Transform, Export), interactions (panning, mousewheel, connecting, embedding), HTML shape nodes, custom shapes, serialization, or layout. Also use when debugging X6 rendering errors, v2→v3 migration, or editor interaction issues. Do NOT use for G2 statistical charts, G6 network graphs, or S2 pivot tables.
Implement an approved spec or focused task through stale-safe source edits. Use this skill when the user says "implement this", "cook this spec", or "fix this bug". Use it for `/cook .cheese/specs/<slug>.md`. Also use it when the user says "go" with clear acceptance criteria. Run it alone for an unambiguous task. Use `--prototype` when the user says "prototype this", "go prototype it", or "spike this out" and wants to refine the result round by round. A spec helps but is not required. Do not use it for fuzzy planning (`/mold`). Do not use it for no-write discussion (`/culture`) or review-only work (`/age`).
J-Link download and online debugging tool for probing devices, flashing firmware, reading and writing memory, viewing registers, resetting targets, reading RTT/SWO logs, and online debugging (pause/resume/step/breakpoint run/call stack/variable inspection). Automatically triggers when the user mentions J-Link, JLink, RTT, flashing firmware, writing memory, reading memory, register inspection, target reset, probe connectivity check, online debugging, single step, breakpoint, or call stack, and also supports explicit /jlink invocation. Even if the user only says "flash it", "show me the RTT output", or "debug it", this skill should trigger as long as the context involves a J-Link probe.
Laravel AI SDK for building AI-powered features. Use when creating agents, generating images or audio, working with embeddings, vector search, or testing AI features. Triggers on tasks involving laravel/ai, AI agents, tool-calling, structured output, streaming, embeddings, reranking, or AI faking in tests
Build, refactor, or review macOS menubar apps that use Tuist and SwiftUI. Use when creating or maintaining LSUIElement menubar utilities, defining Tuist targets/manifests, implementing model-client-store-view architecture, adding script-based launch flows, or validating reliable local build/run behavior without Xcode-first workflows.
Build, configure, and debug apps with the Quasar framework (`quasar` npm package, v2.33.1). Use when writing, reviewing, or debugging code that imports "quasar" or "quasar/wrappers", configuring Quasar with Vite, Vitest, Storybook, UMD, or Quasar CLI, styling with Quasar Sass variables, or upgrading between Quasar v2 releases.
Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).
Generate pragmatic CI/CD pipelines from detected project stack signals — fast baseline generation, repeatable checks, environment-aware deployment stages. Use when setting up CI for a new project, refactoring existing pipelines, or standardizing deployment workflows across multiple repos.
This skill provides comprehensive guidance for SAP BTP Job Scheduling Service development, configuration, and operations. It should be used when creating, managing, or troubleshooting scheduled jobs on SAP Business Technology Platform. The skill covers service setup, REST API usage, schedule types and formats, OAuth 2.0 authentication, multitenancy, Cloud Foundry tasks, Kyma runtime integration, and monitoring with SAP Cloud ALM and Alert Notification Service. Keywords: SAP BTP, Job Scheduling, jobscheduler, cron, schedule, recurring jobs, one-time jobs, Cloud Foundry tasks, CF tasks, Kyma, OAuth 2.0, XSUAA, @sap/jobs-client, REST API, asynchronous jobs, action endpoint, run logs, SAP Cloud ALM, Alert Notification Service, multitenancy, tenant-aware, BC-CP-CF-JBS
Unified codebase review — audits skill quality, code health, infrastructure alignment, and cross-consistency across a portfolio of repos. Runs deterministic metrics (ruff, coverage, complexity, TODOs, dependency staleness) and LLM-driven architectural judgment. Also handles delivery status, commit squashing, infrastructure harmonization, and boilerplate backporting. Use when user says "review skills", "audit skills", "audit codebase", "code quality", "repo status", "what needs pushing", "align repos", "backport", "upgrade deps", "assess codebase", "health check", or wants a thorough quality pass on skills and/or code.
Dodo Payments license keys for software products, covering activation, validation, and deactivation via client.licenses, activation limits, expiry, entitlement grants, revocation, and license webhooks. Use when gating a desktop app, CLI, plugin, or SaaS feature behind a license key, enforcing per-seat or per-device limits, or building a license dashboard.
Generates Postman collection JSON files from Express, Next.js, Fastify, Hono, or other API routes. Scans route definitions, extracts endpoints, methods, params, and creates importable collections. Use when users request "generate postman collection", "export to postman", "create postman file", or "postman import".
Django bible for Django 6.1 with a trailing Django 5.2 LTS section and optional DRF. Fat Models doctrine with migrations, transactions, security, testing, and tooling. Use when writing Django models, views, forms, serializers, migrations, tests, or reviewing Django code. Do NOT use for project-specific Django patterns (load the project overlay skill instead).
Comprehensive Blazor development expertise covering Blazor Server, WebAssembly, and hybrid apps. Use when building Blazor components, implementing state management, handling routing, JavaScript interop, forms and validation, authentication, or optimizing Blazor applications. Includes best practices, architecture patterns, and troubleshooting guidance.
Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, PHP, Python, Django, Go, C#/.NET, Kotlin, NestJS, C/C++, and more. Helps catch bugs, improve code quality, and give constructive feedback. Use when: reviewing pull requests, conducting PR reviews, code review, reviewing code changes, establishing review standards, mentoring developers, architecture reviews, security audits, checking code quality, finding bugs, giving feedback on code.
Investigates network, streaming and protocol failures with falsification-first layered experiments, the general fallback for unknown root causes. Use for ECONNRESET / RST_STREAM / SSE stalls, CDN/CGNAT timeouts or certificate errors, throughput collapse where everything returns 200 but transfers crawl, or LAN identity/topology mysteries. Not for known Tailscale/TUN/DNS/proxy-path conflicts (use tunnel-doctor).
Guidelines for building SwiftUI applications with MVVM/Clean Architecture, Swift 6 strict concurrency, and modern state management. Use when building SwiftUI views, structuring view models, managing state with @State/@Observable, handling async data flow, or optimizing SwiftUI view performance.
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.