Herramientas

Official skills from US broker Alpaca: teach agents to backtest, place and check paper trades, plus developer guides for Broker API account opening, funding and reconciliation. Needs an Alpaca API key (paper trading uses no real money) and the Alpaca CLI; results need professional review.

Applies a Swiss International Style design system with Tailwind CSS: a 12-column grid on an 8px base, IBM Plex Sans with light headings, a stone palette, hierarchy through opacity rather than hue, a single accent color, body text capped at 60ch, mobile-first layouts and dark mode.

Microsoft Translator's translation quality tool: GPT scores each sentence using MQM error categories or a direct score; --list_mqm_errors shows error types and severity. Needs line-aligned source and target files, Python and an OpenAI or Azure OpenAI key (paid); a translator should still review.

Searches ZIM-format knowledge bases such as Wikipedia, Wiktionary and Stack Exchange offline: full-text search, read articles by section and follow links, even with no internet. Download .zim files from Kiwix first (hundreds of MB to tens of GB) into ~/zim-files, and install uv.

Official ChatPPT MCP from YOO-AI: generates slide decks from a topic, text or document, lets you change templates, colors, fonts and animations, writes speaker notes and downloads pptx. Closed-source cloud service; needs a yoo-ai.com API key; personal tokens are test-only with limited calls.

Styles elevated surfaces such as cards, dialogs, popovers and toasts with smooth-shadow-ring utilities instead of pairing a border or ring with a shadow, avoiding the double-edge look. Covers ring and shadow tinting, dark mode and overrides. Requires the shadow-plugin Tailwind plugin.

Official BibiGPT skill: hand agents YouTube, Bilibili, podcast or local audio and video to get summaries, timestamped transcripts, chapter notes and mind maps. Needs a BibiGPT account (free tier has daily limits) plus its desktop app (with the bibi CLI) or an API key.

Webflow's official MCP: manage your site's pages, CMS content and blog posts by chat, and with the MCP Bridge App in the Designer, edit page elements and styles directly. Needs a Webflow account and Node.js 22.3+; first connection asks you to authorize sites.

Connects any FHIR-compliant EHR server (e.g. the Epic sandbox or HAPI) to agents to search, read, create and update patient clinical data in plain language, with SMART on FHIR auth. By WSO2. Needs a FHIR server URL, access token and uv; clinicians must review results.

Connects to the St. Louis Fed's FRED database: search and pull 800,000+ macroeconomic time series (GDP, unemployment, inflation, interest rates) with built-in year-over-year and period-over-period changes. For macro research, investing and teaching. Needs a free FRED API key and Node.js.

Lokalise's official CLI (lokalise2) covering the Lokalise API v2: upload and download language files and manage keys, translations, screenshots, translation tasks and contributors. Needs a Lokalise account (paid, 14-day free trial) and an API token passed via --token.

Diffs a live page's accessibility violations against a baseline, stashing uncommitted changes by default or comparing with a branch, and reports new, fixed and pre-existing WCAG issues with selectors and fixes. Locates only, no edits. Runs AccessLint's Chrome and CLI tools via npx.

Runs the AccessLint rule engine against a live page and returns a worklist of WCAG 2.2 violations, each with its DOM selector, source file and line when mapped, evidence and a suggested fix. Locates without editing; sets up a debuggable Chrome and runs the CLI via npx.

Guides building small always-on WebGL visuals (avatars, ambient orbs, glass and iridescent surfaces) inside product UI: one shared context, a single capped frame loop, cheap fragment shaders, context-loss handling, a mandatory non-WebGL fallback, and React SSR and Server Components pitfalls.

Makes the agent use Tailwind container queries instead of viewport breakpoints for responsive components, migrating sm:/md:/lg: classes to @container variants. Explains when page-level layout should keep viewport breakpoints and lists common review mistakes. Tailwind v3 needs a plugin.

Sonar's official plugin bringing SonarQube checks into the agent coding loop: secrets-scanning hook, issue fixing, quality gates, coverage and dependency risk; with Vortex analysis on, every edit is checked. Needs SonarQube (free Community Build works), the sonar CLI and Docker.

From Twilio Labs: exposes Twilio's public APIs (SMS, voice, phone numbers, Serverless and more) as MCP tools generated from its OpenAPI specs, with filtering by service or tag. Needs a Twilio API key; marked as a proof of concept.

Shapes the agent's own replies rather than your documents: separates what changed from what was verified, cuts invented confidence, leads with the action and keeps load-bearing caveats. Manually invoked and stays on until you say stop; a script can enable it in CLAUDE.md or AGENTS.md.

Neon's official plugin combining the Neon MCP and skills to manage serverless Postgres: projects and branches, object storage, Functions and the AI Gateway. Signs in to Neon via OAuth the first time you use the MCP.

Analyzes your codebase and generates a render.yaml Blueprint, or creates services directly through the Render MCP, to deploy apps to Render. Maintained by Render and included in OpenAI's curated skills. Needs a Render account and code pushed to GitHub, GitLab or Bitbucket.

Third-party MCP for Canvas LMS (not by Instructure): teachers can review courses and assignments, grade, comment, and create quizzes and discussions; students can check due dates and grades; admins can create courses and export reports. Needs a Canvas API token, your school domain and Node.js.

Wolfram's official agent tools: use the Wolfram Language and Wolfram|Alpha for symbolic and numeric math and scientific and statistical data, for teaching and research. The command runs the official Docker image with a free developer license; Wolfram 15+ users can install it in the app.

When the user describes a concept in their own words that matches an established term of art, the agent appends that single term after its answer, linked to a Google Images search, so the user learns the proper name and can see examples.

PostHog's official plugin with a built-in MCP and 30+ skills: query product analytics, feature flags, A/B experiments, dashboards and error tracking from chat, and optionally send Claude Code sessions to LLM Analytics. Needs OAuth sign-in with a PostHog account.