Herramientas

Expo's official skills: Expo Router navigation, native-feeling UI, animations, native modules and SDK upgrades, plus EAS build and submit, OTA updates and CI workflows. EAS skills use Expo's paid services.

Fast async link checker written in Rust that scans websites and Markdown, HTML and other files for broken links and email addresses, with JSON output, config files and an official GitHub Action, often wired into docs CI.

Hugging Face's official hf CLI: search, download and upload models and datasets, manage repos and storage buckets, and run jobs on Hugging Face's cloud. Output adapts automatically for agents, and hf skills add installs companion skills. Uploads and similar actions need a login.

Extracts any website's logo, colors, fonts, spacing, shadows and motion in one command, exporting W3C design tokens, a Tailwind theme, DESIGN.md or a brand guide PDF, plus WCAG contrast checks. Good for competitor and brand audits. Needs Node.js 18+; run dembrandt install-browser first.

Design engineer Jakub Krehel's UI polish skill covering animation, typography, icons, hover states, optical alignment, concentric radii, shadows and hit areas, with quick and full review modes, so agents get the details right when building or reviewing UI. Works on web code; needs Node.js.

NVIDIA's official plugin that finds and installs the right skills from NVIDIA's catalog for your task, spanning CUDA acceleration, NIM inference, NeMo training, RAG blueprints, Omniverse simulation and robotics. Listed in both the Claude and Codex official marketplaces.

NVIDIA's official, verified catalog of hundreds of skills covering CUDA-X libraries, NeMo training, NIM and Dynamo inference, RAG blueprints, Jetson, Omniverse and robotics simulation. The install adds only nvidia-skill-finder, which recommends other skills and installs them once you confirm.

Fast Rust toolkit for tabular data with nearly 80 subcommands for querying, stats, cleaning, validation, joins and format conversion on CSV and Excel. Also offers an MCP server and a Claude Cowork plugin.

Marketing and sales workflows open-sourced by Single Brain: expert-panel content scoring, cold email optimization, turning podcasts and long videos into shorts and social posts, YouTube competitor analysis, decks and financial scenarios, mostly with Python scripts. Some need Gemini or YouTube keys.

Community plugin marketplace bundling hundreds of subagents, slash commands, hooks and skills by category, installable individually or all at once, with the buildwithclaude.com site for browsing community plugins and MCP servers.

Works with Gmail, Calendar, Drive, Docs, Sheets, Slides, Tasks, Chat and other Google Workspace services, with multi-user OAuth and read-only mode. You create your own Google OAuth client and run it in HTTP mode.

Searches Google Flights for flights and the cheapest travel dates, filtering by route, date, cabin, stops, airline and alliance, good for trip planning. Open-source Python, no API key needed; built on reverse-engineered Google endpoints, so changes at Google may break it.

AWS's generally available agent toolkit and plugin marketplace: plugins such as aws-core, aws-agents and aws-data-analytics bundle the AWS MCP Server with evaluated skills for IaC, serverless, containers and billing. Calling AWS APIs requires configured credentials.

PostgreSQL MCP server with database health checks, index tuning, EXPLAIN plan analysis and hypothetical index simulation, plus safe read-only SQL execution in restricted mode.

Teaches agents to build, debug and review stateful AI agents with the Cloudflare Agents SDK: state sync, scheduled tasks, RPC, MCP servers, email and streaming chat, checking the latest official docs first. Maintained by Cloudflare.

Framework for writing data transformation models in SQL or Python, with a Terraform-like plan/apply flow, virtual data environments, unit tests and table diffs, and transpilation across 10+ SQL dialects. A Linux Foundation project and an alternative to dbt.

Default workflow for Vue work: standardizes on Vue 3, the Composition API and script setup with TypeScript, reads core references on reactivity, SFCs, data flow and composables, plans component boundaries first, loads topics like slots, transitions and performance only when needed, then self-checks.

Debugging index for Vue 3: maps common symptoms in reactivity, computed, watchers, components, props and emits, templates, forms and v-model, lifecycle, slots, TypeScript and SSR hydration to reference notes that explain the cause and the fix.

Vue Router 4 best practices and gotchas: guards and lifecycle hooks not firing when only params change, no this in beforeRouteEnter, async calls and infinite redirect loops in guards, the deprecated next() callback, and cleaning up listeners after unmount.

Guides the agent in writing library-grade Vue composables whose inputs accept a plain value, ref or getter: choose MaybeRefOrGetter or MaybeRef depending on whether the input is read-only or writable, and normalize with toValue() and toRef() inside watchers. Requires Vue 3 or Nuxt 3+.

Covers how JSX in Vue differs from React JSX, such as class instead of className and JSX plugin config, for migrating React JSX to Vue or fixing attribute type errors. A brief skill that points to a single reference note.

For Vue 3 projects on the Options API (data(), methods, this): how to get TypeScript inference with defineComponent and type props, event handlers and computed values, plus gotchas like avoiding arrow functions in methods and lifecycle hooks and not sharing debounced state across instances.

Pinia best practices and gotchas for Vue apps: fixing the getActivePinia error, returning all state from setup stores, keeping reactivity when destructuring stores, calling store methods from templates, keeping ephemeral filters in the URL, and using Pinia in large apps.

Testing practices for Vue apps: Vitest and Vue Test Utils, black-box component tests, flushPromises for async code, helpers for testing composables, Pinia stores, async components and Teleport, avoiding snapshot-only tests, and Playwright for end-to-end testing.