Каталог навыков агентов

Apply lean thinking to UX: hypothesis-driven design, collaborative sketching, and rapid experiments instead of heavy del...

Access CTO system documentation and learn how components work. Use when user asks 'how does X work', 'show me how to', '...

Step-by-step explanation of a concept with progressive depth

确认听众、时长与主题，将内容分为封面、目标、概念/示例、练习、总结。交付完整单文件 HTML，内联 CSS/JS、中文字体回退、16:9 固定舞台等比缩放、键盘上一页/下一页和页码、减少动态支持。读取

Comprehensive guide to Learning Path patterns for the Plataforma B2B de treinamento técnico corporativo educational plat...

simulation-designer for engaging, immersive learning experiences.

Evidence-bound centered evaluation geometry for cinematic shots/sequences, measuring deviation from declared staging, op...

Routes frontend, UI/UX, mobile, motion, React, WebGPU, video, browser verification, typography, component discovery, and...

Film production design capability for sets/locations, architecture, props, dressing, graphics, palette, texture, period/...

Story bible, canon, timeline, character-state, location, object, promise/payoff and continuity tracking across novels, e...

Structured research notebook for sources, quotes within permitted limits, paraphrases, facts, uncertainties, story uses,...

Generate breadboard circuit mockups and visual diagrams using HTML5 Canvas drawing techniques. Use when asked to create...

Required legal pages for UK/HU lead generation websites. Privacy Policy, Cookie Policy. GDPR compliant. Bilingual templa...

Anti-scope-creep. Forces the question: what is the smallest thing that delivers value?

Design and build animations that make a lesson topic genuinely easier to understand — visual, moving explanations of the...

Build compact, standalone multi-lesson course artifacts with lesson navigation, objectives, flashcards, quizzes, and sou...

Guide for designing effective Letta agents. This skill should be used when users need help choosing agent architectures,...

Guide for designing effective memory architectures in Letta agents. Use when users need help structuring memory blocks,...

Runs a 7-step UX pipeline with parallel research plus product planning. Use for features, redesigns, discovery, or agent...

Level design fundamentals, pacing, difficulty progression, environmentalstorytelling, and spatial design for engaging ga...

Conversion-focused design that removes friction and guides users toward action through clarity, trust, and speed.

Pattern of rule lib-layers. Load when moving code or a symbol between libs — where to start, in which order to move doma...

Use when building or reviewing Lightning Web Components — specifically lifecycle management, wire service, memory leak p...

Place a real product into a believable lifestyle or in-use scene (kitchen, bathroom, desk, outdoor, gym, bedroom, festiv...

Comprehensive development support for LI.FI DEX aggregator including SDK, Widget, and API integration for cross-chain sw...

Light/dark theme violation repair for Pattern Patrol P4. Use when you find raw bg-white/text-black classes or a state in...

独特吸睛、审美好、有特色、美观全面的前端设计。当任务涉及前端界面、项目展示页、系统演示、大屏可视化、可视化平台、微信小程序 UI、移动端界面、设计系统、Tailwind v4、shadcn/ui、Next.js、React、Vite、可访问...

Light 按需工程技能·前端设计：把模糊的「做个好看的界面」落成**能跑的 React/Tailwind/shadcn 代码 + 设计决策说明**—— 有**视觉记忆点**(signature element)、**风格自洽**(desi...

Lightweight 3D effects for decorative elements and micro-interactions using Zdog, Vanta.js, and Vanilla-Tilt.js. Use thi...

Efectos 3D ligeros y decorativos con Zdog (pseudo-3D), Vanta.js (fondos animados WebGL) y Vanilla-Tilt (tilt parallax en...

Overlay the branded like/subscribe CTA animation — channel gem avatar + @C0BALT_CUT handle + subscribe/like/bell click c...

Lime design system rules for this project's UI. Use when building or changing any screen, component, form or style, when...

Create and configure a Linear agent app so the assistant can manage issues, projects, and workflows under its own identi...

Playful, minimal design with bright colors, rounded shapes, tactile 3D borders, and friendly illustrations for approacha...

灵枢白箱条件单元域入口：浏览器与网页（104 单元 / 14 子域）。触发词：浏览器、渲染、DOM、事件循环、Web存储、CSP、性能、PWA。 场景：任务命中本域任一子域主题时使用。先查下方路由表定位单元，语义模糊时经 mdcg cg o...

Maintain and debug the link-curator web dashboard (port 8090). Separate process from the official Hermes dashboard.

Use when reviewing rendered HTML, interactive components, or design-system patterns related to Use descriptive link text...

Create LinkedIn posts for lead generation and thought leadership. Use when projecting ideas to LinkedIn, creating post s...

Hilarious LinkedIn profile roasting skill that delivers savage but friendly comedy burns based on someone's profile, act...

Använd INNAN du bygger en länk, för att avgöra om det ska vara en Inline Link (i löptext), Action Link (fristående) elle...

Runs linting, formatting, and type checks for react-basics-ui. Triggers on "lint", "pre-commit", "format", "eslint", "pr...

Audits a Figma design page read-only — frame membership and bounds, section overlap, naming, arrow geometry and entry di...

Complete Linux administration skill covering process management, filesystem, permissions, package management, users, bas...

Lior Code to Figma™ by Lior Eli. Fixed rules for exporting any design, mock, flow or set of states from Claude into Figm...

Build or restyle anything in Liquid Dawn, the calm daylight sibling of Liquid Midnight. The look: warm paper grounds (Da...

iOS 26 Liquid Glass expert. Use when user asks about Liquid Glass implementation, SwiftUI glassEffect, migration from iO...

Build native macOS/iOS apps with Apple's Liquid Glass design language and Human Interface Guidelines. Use when creating...

Use for Apple Liquid Glass work on iOS 26+, iPadOS 26+, and related SwiftUI/UIKit interfaces. Covers native glassEffect...

Apply or adapt a dual-theme liquid glass UI board for premium dashboards, workspace launchers, settings surfaces, design...

iOS 26 Liquid Glass design system — dynamic glass material with blur, reflection, and interactive morphing for SwiftUI,...

iOS 26 Liquid Glass design system — dynamic glass material with blur, reflection, and interactive morphing for SwiftUI,...

Build React, Next.js, Framer, Motion, or MCP app interfaces with a liquid-glass visual system and reusable code library....

Transform any frontend project (HTML/CSS/JS, React, Vue, Next.js, Tailwind, 3D WebGL/Cesium/Three.js workbenches, or das...

Builds a WebGL fragment-shader effect that renders one bold word as flowing polished liquid metal on near-black, by blur...

Build or restyle anything in Liquid Midnight. The look: Apple Midnight blue-black grounds (hue 245-252, never purple), l...

Builds fused UI cards in React and SVG, in which rounded boxes are joined by the smooth union of their signed-distance f...

Use when applies to HTML documents with `<li>` elements. Also applies to custom ARIA lists where `role='listitem'` must...

Rule under the lists law. Load when editing a list screen (libs/admin/*/feature/list), the kit table and pagination. Nam...

Draw an architecture, workflow, data-model or timeline diagram as editable SVG, check it, and export PNG. Use when a pic...

Make a publication-ready figure from measured data: chart form, units, colorblind-safe color, export and visual check.

Use when working with zensical.toml, docs/conf.py, sphinx, shibuya, litestar-sphinx-theme, mkdocstrings, Griffe, objects...

Simulate the LittleGPT persona as a fictional, unfiltered AI for test scenarios, providing sarcastic, slang-heavy respon...

Convierte transcripción de navegación (voz/texto) en beats U-xx, cruza con evidencia MCP chrome-devtools (E-xx), y produ...

将主题或材料经搜索核实制成苹果 Live Photo 信息动效卡。用 Remotion 编排图片、PNG、emoji、场景、时间线和可选图表，适用于知识解释、产品比较、变化过程及数据故事；制作可预览动效与配对实况资源，说明接收端兼容性。

Tworzenie komponentów LiveView w projekcie DriverHub. Użyj dla formularzy, list, tabel z danymi czasu rzeczywistego.

Use when the project's frontend stack is Livewire — dispatched by `directives/ui/{apply,review,polish}.ts`. Covers react...

Build, refactor, secure, optimize, and test Laravel Livewire v2-v4 components, including state, forms, events, uploads,...

Use when building an animated or interactive widget, explainer or dashboard page: how motion feels, where the eye goes,...

Orchestrate conversations between two LLMs via OpenRouter and compare their conversational personalities, behavioral pat...

This skill should be used when Claude needs to "formulate a request for external feedback", "craft a question for ChatGP...

Designs user flows, interaction states and mockups for a defined product scope; does not implement UI code.

Patterns for skeleton loaders, shimmer effects, and loading states that match design system aesthetics. Covers skeleton...

Design effective loading states, skeleton screens, and empty states that maintain user confidence. Use when content take...

Manage user expectations during wait times with appropriate loading states — from simple spinners to complex skeleton sc...

Complete system design reference for the Loadout VSCode extension — a GUI panel for managing Claude Code agents, skills,...

See a local page in the browser while editing files in Cursor: run the right dev server (Vite HMR or static live-reload)...

本地化扫描、提取与验证，扫描源码中的硬编码字符串，提取到 i18n 资源文件，验证完整性并生成本地化检查报告。

Controlla o imposta il layout di un progetto perché regga testi tradotti più lunghi, l'orientamento RTL, l'ordine di let...

This skill should be used when the user says "lock it", "go with that", "approved", "that's the standard", or explicitly...

Node.jsアプリケーションのログローテーション戦略設計・実装スキル。PM2、logrotate、Winston、集中ログシステムを活用した効率的ログ管理を提供。Anchors:• 『Site Reliability Engineerin...

Structured logging conventions for DraftForge backend (Django/Celery/Daphne) and frontend (React). This skill should be...

Build a single-file HTML demo that answers whether a state model, business logic, or data shape feels right — a pure lif...

Generate logo directions — "give me logo concepts for", "logo ideas for", "design a logo for". Emits 3 to 5 distinct dir...

This skill should be used when the user asks to "animate our logo", "make a logo intro/stinger", "build a brand reveal",...

Generates deep visual prompts for Midjourney/DALL-E to create logo vectors.

Create logos using AI image generation. Discuss style/ratio, generate variations, iterate with user feedback, crop, remo...

Create brand logos with proper typography and visual identity alignment

设计与评审 Logo，提供本地风格检索和位图/矢量交付。

Logo design intelligence with 55 styles, 30 color palettes, 25 industries. Generate logos with Gemini Nano Banana model,...

Generate logo variants for a brand or organization, producing multiple production-grade marks across different architect...

当用户需要用设计师人格蒸馏、品牌策略、概念方向、视觉提示词和质量评分来设计、评审或迭代 Logo 与品牌标识时使用。

Generate logos using Replicate AI and make them transparent with background removal.

When the user wants to optimize logo placement, linking, or branding on a website. Also use when the user mentions "logo...

Human-in-the-loop web studio to tune AI-generated visual output by eye — live sliders/pickers/drag-handles for visual pa...

Human-in-the-loop web studio to tune AI-generated output by eye. Stand up a local interactive studio (sliders, pickers,...

Automated visual tuning: render labeled variants into one artifact, a vision/video model rates them and suggests better...