Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Design & UI
Data visualization with chart selection, color theory, and annotation best practices. Covers chart types (bar, line, scatter, heatmap), axes rules, and storytelling with data. Use for: charts, graphs, dashboards, reports, presentations, infographics, data stories. Triggers: data visualization, chart, graph, data chart, bar chart, line chart, scatter plot, data viz, visualization, dashboard chart, infographic data, data presentation, chart design, plot, heatmap, pie chart alternative
Data visualization with chart selection, color theory, and annotation best practices. Covers chart types (bar, line, scatter, heatmap), axes rules, and storytelling with data. Use for: charts, graphs, dashboards, reports, presentations, infographics, data stories. Triggers: data visualization, chart, graph, data chart, bar chart, line chart, scatter plot, data viz, visualization, dashboard chart, infographic data, data presentation, chart design, plot, heatmap, pie chart alternative
Design new Datadog dashboards, redesign existing ones, or audit dashboards for operational readiness. Covers widget selection, layout organization, template variables, group structure, tab organization, alert threshold validation, and zero-knowledge readability. Uses pup CLI for inspecting dashboards and validating designs. Use when designing new dashboards, redesigning existing ones, auditing before on-call handoff, or reviewing after dashboard changes. Do not use for: (1) Datadog agent installation or configuration, (2) monitor/alert rule design, (3) APM instrumentation or tracing setup, (4) log pipeline configuration.
Use when building React "Bring Your Own Screen" (BYOS) custom UI on top of a Descope flow — takes exported flow JSONs, extracts the real interaction IDs and outputs, generates BYOS components that match hosted parity, and avoids the rediscovery-the-hard-way failure modes (silent form rejection, shared screen-name collisions, anonymous-session stickiness, nested-form hydration errors, wrong form keys, dead-end buttons, missing OAuth provider field).
Specialized skill for reverse-engineering Design Systems from websites. Uses Python pre-processing to extract design tokens without hitting token limits, and generates complete HTML documentation using real fragments and images from the original site.
Email marketing design with layout patterns, subject line formulas, and deliverability rules. Covers welcome sequences, promotional emails, transactional templates, and mobile optimization. Use for: email marketing, newsletter design, drip campaigns, email templates, transactional emails. Triggers: email design, email template, email marketing, newsletter design, email layout, email campaign, drip campaign, welcome email, promotional email, transactional email, email subject line, email header image, email banner
Expert guide for using the Figma Context MCP (Framelink) efficiently while avoiding 429 rate-limit errors. Activate when: (1) using Framelink Figma MCP tools (get_figma_data, download_figma_images), (2) fetching Figma designs for code generation, (3) user hits 429 rate limits from Figma API, (4) extracting design tokens or component data from Figma, (5) downloading Figma assets/images, (6) any design-to-code workflow involving Figma URLs. Covers metadata-first fetching, depth-limited node trees, batch image downloads, rate-limit diagnostics, and plan-tier awareness.
Calculate and debug Flexbox layout math for flex base size, flex-basis, flex-grow, flex-shrink, the flex shorthand, fractional grow values, and min/max constraints. Use when flex items resize unexpectedly, when distributing free space along one axis, when comparing flexbox with grid, or when deriving predictable card, nav, toolbar, and row layouts.
Implement or review advanced Flutter visual rendering such as frosted or liquid glass, backdrop blur, refraction, shaders, custom painting, glow, masks, and effect fallbacks. Use when the request explicitly needs a nontrivial visual effect; route art direction, ordinary styling, animation timing, and evidence-based performance diagnosis to their dedicated skills.
A specialist team for the coding agent you already use: 12 roles, 21 workflows and 33 skills that plan, build in parallel, review and debug, leaving plans, ADRs and results as files. Gates wait for your own tests. Also research, slides and video. One .agents/ folder for Claude Code, Codex, Cursor and 11 more.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics
Explain and apply foundational math for front-end development, including arithmetic, algebra, ratios, exponents, roots, linear equations, inequalities, geometry, trigonometry, coordinates, and choosing CSS versus JavaScript math. Use when a web design calculation needs first-principles explanation before applying CSS, JavaScript, Grid, Flexbox, responsive, or color-specific skills.
Remote-control a running GIMP (the open-source image editor) by Python script through its built-in Script-Fu server — build documents and layer stacks, fill, gradient and brush-stroke drawables, add text layers, attach non-destructive GEGL filters, cut out with masks and selections, retouch photos, and export PNG/JPEG/TIFF/GIF/.xcf or batch-convert whole folders in the session the user is looking at. Use whenever the user wants to create or edit a GIMP document (.xcf), composite, retouch or resize a raster image, batch-process a folder of images, script or automate GIMP, export layers separately, or says "GIMP", "xcf", "gimp script", "batch resize these photos", "open this in GIMP" — even if they do not mention scripting. Also covers Hungarian: "csinálj egy képet GIMP-ben", "vezéreld a GIMP-et", "rétegek", "exportáld PNG-be", "kötegelt átméretezés". Not for natural-media painting (use krita or rebelle), vector and layout design (use affinity), or keyframed motion graphics (use cavalry).
Build a complete, production-ready full-stack web application from PRD documents, prototype images, and resource files. Handles the entire pipeline: system design, database schema, seed data, backend API, frontend UI, visual verification against prototypes, and deployment script generation. Use this skill whenever the user: - Provides a PRD (product requirement document) and wants a working app built - Says things like "根据PRD开发", "build from PRD", "implement this product", "把需求文档做成应用", "develop this app from requirements" - Has prototype images + requirements and wants full-stack implementation - Wants to turn product specifications into a running web application - Mentions building an app from wireframes/mockups combined with a requirements doc Trigger this skill even if the user just says "帮我开发" or "build this" with PRD materials present in the working directory
Clarify and record user-confirmed UI design requirements through focused question sets, optionally after grill-workflow and before prototype or specification. Use when the user wants custom visual direction, design preferences, or resolution of a design conflict; do not use for product scope or implementation.
Computer vision expert specializing in real-time hand tracking and gesture interface design. Use when "hand tracking, gesture recognition, mediapipe, hand gestures, touchless interface, sign language, hand pose, finger tracking, mediapipe, hand-tracking, gesture-recognition, computer-vision, hci, touchless, ml" mentioned.
HeroUI v3 component library expertise for React (web) and React Native (mobile). Use when code imports @heroui/react, @heroui/styles, or heroui-native, user asks to build UI with HeroUI, or references HeroUI components, theming, or migration from NextUI/HeroUI v2.
Turn an uploaded photo into a HEYTEA-inspired text or no-text object-and-doodle poster, a static flavor monster, a poster pairing the unchanged photographed product with an approved monster, or an approved runnable desktop pet. Use for 喜茶简笔画海报, 歪扭儿童字, 实物加小人涂鸦, 风味小怪兽, 小怪兽融合海报, 桌宠, 照片变桌面宠物, 食物桌宠, or 饮料桌宠.
Same pixels, fewer tokens — for user-facing deliverables where visual polish is the spec. Use when building or editing a landing page, marketing site, hero, pricing/feature section, dashboard, or any HTML/CSS UI component. Keeps the full rendered design (layout depth, hierarchy, motion, responsive richness, a11y) and cuts tokens by expressing that design densely — CSS custom properties, shared classes, shorthand, fluid units — instead of by cutting the design. The honey core trims code and prose; this trims how the design is *written*, never how it looks. Reach for it whenever output is user-facing markup, even if the user never says "minimal".
Use when asked to "build habit-forming products", "Hooked model", "trigger action reward investment", "create sticky behavior loops", or "design habit loops". Helps design products that form unprompted user habits. The Hooked Model (created by Nir Eyal) explains how products create habits through Trigger, Action, Variable Reward, and Investment.
Generate world-class medical infographics using carousel-level visual language. Templates include hero stats, multi-section layouts, comparisons, myth-busters, process flows, and patient checklists. Default 1080x1350 for Instagram.
Use JavaScript number math safely for front-end UI behavior, including expressions, precedence, coercion, NaN, Infinity, floating-point precision, BigInt limits, modulo wrapping, rounding, random values, and repeatable UI randomness. Use when building sliders, carousels, counters, animation values, randomized UI, financial-ish display values, or debugging numeric edge cases in browser JavaScript.
Design effective KPI dashboards with metrics selection, visualization best practices, and real-time monitoring patterns. Use this skill when building an executive SaaS metrics dashboard tracking MRR, churn, and LTV/CAC ratios; designing an operations center with live service health and request throughput; creating a cohort retention analysis view for a product team; or debugging a dashboard where metrics contradict each other due to inconsistent calculation methodology.
Light research mainline, step 9 — figures: make each figure serve an argument (which claim it supports and what would be missing if removed); set publication-grade specifications (column width, font size, colorblind safety, error bars, n, significance); ensure visual honesty (no secretly truncated y-axes, no false correlations from dual y-axes, no jet-rainbow); multimodally “take a real look” after rendering; research data figures must be generated programmatically, never with AI image generation. When to use: after results analysis, to draw paper figures; plan a figure set (figure list, budget, redundancy control); choose chart types; create publication-grade figures (column width, font size, dpi, colorblind-safe palette); address concerns that a figure is misleading or presents a nonsignificant result as the main figure; inspect rendered output for overlapping labels or legends obscuring data; create framework or schematic diagrams (programmatic, not AI-generated). Triggers: draw / figures / figure / illustration / render / paper figure / main figure / caption / error bar / colorblind / viridis / truncated y-axis / dual y-axis / heatmap / framework diagram / panel / display item / column width / publication-grade / chart recommendation / review render / plot / chart / matplotlib / seaborn. Core rules: **visual dishonesty (truncated y-axis / false correlation from dual y-axes) = critical gate** (spec §4.2, STAGE_GATES[9]=[visual_honesty]); missing error bars / jet-rainbow / over-budget figure set / redundancy = warn; **presenting a nonsignificant result as the main figure / mismatch between figure and text = critical → initiate 9→7 rework**; **research data figures must be generated programmatically (matplotlib/seaborn/R), never with AI image generation** (permanent rule); static lint only flags suspicious forms—whether something is truly misleading requires final judgment based on the caption and a person/reviewer. This skill initiates **9→7 rework (nonsignificant result as main figure / figure-text mismatch → result-analysis)**.
Applies Material Design 3 Expressive typography principles including variable fonts, type scales, and hierarchy. Use this when working on text styling, type hierarchy, readable interfaces, or when the user asks to apply Material Design 3 typography guidelines.
Transform text content into professional Mermaid diagrams for presentations and documentation. This skill MUST be used when the user names Mermaid, and SHOULD be used when they ask to visualize concepts, create flowcharts, or make diagrams from text (流程圖、架構圖、關係圖、時序圖、心智圖). For diagrams inside HTML Artifacts, MUST prefer the artifact’s existing HTML/CSS/SVG or diagram approach; select Mermaid when it fits, not merely because a flowchart was requested. Explicit Excalidraw requests MUST use excalidraw-diagram, and explicit Obsidian Canvas requests MUST use obsidian-canvas-creator.
Migrate a React Native project from NativeWind to Uniwind. Use when the user wants to replace NativeWind with Uniwind, upgrade from NativeWind, switch to Uniwind, or mentions NativeWind-to-Uniwind migration. Handles package removal, config migration, Tailwind 4 upgrade, cssInterop removal, theme conversion, and all breaking changes.
Enforces Mobbin MCP for real shipped-app design inspiration before UI/UX work. Use when designing, redesigning, or reviewing screens, flows, paywalls, onboarding, checkout, settings, empty states, marketing sections, or microcopy patterns; when the user says Mobbin, design inspiration, UI reference, pattern research, or benchmark against real apps. Requires Mobbin MCP search_screens, search_flows, and search_sections — do not invent UI from memory or substitute Dribbble/generic AI layouts.
Molten OS Core — create or audit high-converting landing pages (build → index.html + styles.css, or 22-point audit). Use for landing page, waitlist, sales page, or conversion review. Reads `molten-docs/brand/brand.md` and `molten-docs/design/design.md` when present. Routes to build or audit workflow by intent.
Build a throwaway prototype to flesh out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
Design and audit SDK, API, CLI, webhook, and developer-platform onboarding across quickstarts, auth keys, sandbox data, examples, docs IA, install friction, versioning, errors, observability, migration guides, sample apps, telemetry, and time-to-first-success. Use when developers need to integrate quickly and reliably.
Design and audit product search, marketplace discovery, recommendation surfaces, filters, facets, relevance signals, zero-results, query understanding, ranking drift, result quality evals, fairness, sponsored placement boundaries, and feedback loops. Use when users need to find content, products, creators, docs, apps, skills, or inventory quickly and trust the results.
Expert web designer for responsive, mobile-first websites. Specializes in landing pages using Astro, Tailwind CSS, and Cloudflare Pages. Enforces design consistency through style guides, semantic HTML, and accessibility. Prioritizes data-driven content patterns to minimize hardcoding. Trigger when working on website projects, landing pages, web components, or design system implementation.
Multi-slide carousel design for Instagram, LinkedIn, and Twitter/X with layout rules and hooks. Covers slide structure, text hierarchy, swipe psychology, and platform-specific specs. Use for: carousel posts, Instagram carousels, LinkedIn carousels, slide posts, educational content. Triggers: carousel, instagram carousel, linkedin carousel, slide post, carousel design, swipe post, multi-image post, carousel template, educational carousel, carousel content, instagram slides, linkedin slides
Create or update a Phat feature specification using an accepted UI prototype as a faithful UI contract with a reproducible visual baseline while preserving requirements, domain rules, and ADRs as authoritative sources. Use after to-prototype or edit-prototype when the prototype has been reviewed and should inform the implementation-ready behavioral contract before to-tasks, or as support within change-scope when a task plan already exists.
Design every state a screen can be in, not just the happy one. Loading with skeletons that match the layout, spinner timing, empty states that teach one action, partial and stale data, errors that say what to do, optimistic updates and rollback, streaming, offline, unsaved changes, and success that does not interrupt. Use when building any screen that fetches, submits or can be empty, or when a screen “flashes”, “jumps”, or shows a spinner over everything.
Make finished App Store screenshot sets from raw screenshots — brand-colour gradient and white (or a dark-dominant dark theme) flowing as one panorama across the images, big centred heavy headlines, a device at a fixed spot with its screen dimmed while a cropped part pops out past it, and glossy puffy 3D objects from the app's own context (a crescent and stars for a prayer app, speech bubbles for a subtitle app) on the seams, with a phone-less hero where the app's symbol is a giant 3D object holding its own UI cards. Covers every required iPhone size (6.9" and 6.3") and the iPhone Duo outer and inner displays, in light and dark (from light- and dark-mode screenshots if given), rendered with an HTML template and headless Chrome; the UI stays pixel-exact. Use when the user asks for App Store / store screenshots, iPhone Duo screenshots, or a dark-theme screenshot set from raw screenshot folders, or names this skill. Produces the sets directly, with no plan files or approval stops.
Build node-based editors, interactive diagrams, and flow visualizations using Svelte Flow. Use when creating workflow editors, data flow diagrams, organizational charts, mindmaps, process visualizations, DAG editors, or any interactive node-graph UI. Supports custom nodes/edges, layouts (dagre, hierarchical), animations, and advanced features like proximity connect, floating edges, and contextual zoom.
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.