Herramientas

Official Black Forest Labs skills: teach agents to write strong FLUX image prompts (typography, exact color values, multi-reference editing) and call the BFL API to generate images, FLUX 3 short videos with sound, and product ads. Prompting needs no API; generation needs a BFL API key.

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.

Skill for naming products, brands, companies and open-source projects: writes a naming brief, explores metaphors, generates candidates while filtering out generic AI-style names, scores them on a rubric, then checks domain, social handle and package name availability. Good for early-stage startups.

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.

Official Google Ads API assistant: ask in plain language, generate and validate GAQL queries, run them to export account data to CSV, and debug offline conversion uploads. Account-changing code is generated, not run. Needs a developer token, credentials file and Python 3.10+.

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.

Turns one idea into a sparse, wordless white-chalk illustration on an even green board. Picks one of six composition families, generates an image, checks it against a gated QA list and repairs it up to twice. Needs image generation and inspection; otherwise returns the prompt and recipe.

Translates a concept into one spatial event, like orbit or convergence, and renders it as a sparse geometric illustration or poster on matte paper, grayscale and text-free by default. Checks the result against quality gates and regenerates once; falls back to prompt-only output.

Connects to GeoServer's REST API so agents can manage workspaces, data stores, layers and styles, run CQL spatial queries, and access features and render maps via WMS/WFS, for publishing and maintaining map services. Needs a running GeoServer with an admin account, Python 3.10+ and uv.

MLflow's official skills plugin: lets coding agents add MLflow Tracing to LLM apps, analyze failed traces, build evaluation datasets and scorers, and query token and latency metrics, closing the instrument, evaluate, iterate loop. Needs MLflow 3.8+.

Builds animations out of text characters: brightness-ramp mapping with cell aspect correction, generative ASCII fields, image, video and Three.js scene to ASCII conversion, and terminal intros or loaders, rendered with <pre>, canvas or ANSI output.

Builds frosted and liquid-glass UI: backdrop-filter blur, translucent fills, bright edge highlights and layered shadows, SVG displacement for refraction, hover, scroll and entrance motion, plus accessible reduced-transparency fallbacks.

Adds functional UI micro-interactions with Framer Motion (motion/react) and modern CSS: hover and press feedback, toggles, toasts, drawers, modals, list reorder and shared-element transitions, with 100-250ms timings, asymmetric enter and exit easing, and reduced-motion support.

Animates SVG with stroke draw-on effects, path morphing via GSAP MorphSVG or Flubber, motion along a path, animated icon state changes, and gradient or filter animation, choosing between CSS, SMIL and GSAP per task.

Integrates Lottie and dotLottie animations from After Effects into web, iOS, Android and React Native: playback and segment control, scroll- or hover-driven interactivity, runtime theming and recoloring, plus an After Effects export checklist.

Twelve Data's official MCP: real-time and historical prices for stocks, ETFs, forex and crypto, 60+ technical indicators, plus financials, dividends, fund holdings, company news and SEC filings. Hosted; sign in with your Twelve Data account in the browser, no API key to copy.

Official agent-first CLI from fal: search and run 1,200+ image, video and speech generation models on fal.ai, check parameters and pricing, upload inputs and download results, with structured JSON output. Good for batch image and promo asset generation. Needs a fal.ai API key, billed per use.

42 official AWS skills for healthcare and life sciences: medical coding and terminology mapping, FHIR/HL7 parsing, claims and prior authorization rules, medical imaging, pharmacoepidemiology and genomics, per US standards. Some need local software. Not for clinical decisions; expert review required.

Runway's official plugin: agents batch-generate videos, images, voiceovers and sound effects from one prompt, for ad variations, product videos and multi-shot shorts; also helps developers integrate Runway into apps. Needs a Runway developer account ($10 minimum top-up), an API key and uv.

Reconnects an existing Figma design to published design-system components. Backs up the frame, classifies each section as already connected, exact swap, compose from primitives or blocked, then replaces detached layers and local wrappers one section at a time. Needs Figma MCP.

Audits a Figma screen or component for design-system drift, read-only: shared primitives rebuilt as plain frames, hard-coded values instead of variables, and variant drift. Each finding cites structural evidence and may suggest a replacement. Outputs Markdown or JSON; needs Figma MCP.

Fixes one design-system finding in a Figma screen, typically from Audit Design System. Checks the fix is feasible, backs up only the affected node, applies the smallest change (swap instance, compose from primitives, bind tokens or align variant) and verifies it locally. Needs Figma MCP.