发现 Skills

Create professional SVG logos from descriptions and design specifications. Generates multiple logo variations with different layouts, styles, and concepts. Produces scalable vector graphics that can be used directly or exported to PNG. Use this skill when users ask to create logos, brand identities, icons, or visual marks for their designs.

Apple Intelligence skills for on-device AI features including Foundation Models, Visual Intelligence, App Intents, and intelligent assistants. Use when implementing AI-powered features.

Deep competitive analysis for iOS/macOS apps including feature comparison, pricing analysis, strengths/weaknesses, market positioning, and differentiation opportunities. Use when user asks for competitive analysis, competitor research, feature comparison, market positioning, or wants to understand competition in detail.

Nuxt 4 server-side development with Nitro: API routes, server middleware, database integration, and backend patterns. Use when: creating server API routes, implementing server middleware, integrating databases (D1, PostgreSQL, Drizzle), handling file uploads, implementing WebSockets, or building backend logic with Nitro. Keywords: server routes, API routes, Nitro, defineEventHandler, getRouterParam, getQuery, readBody, setCookie, createError, server middleware, D1, Drizzle, PostgreSQL, WebSocket, file upload

Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.

Organize 8-bit CSS with custom properties, pixel fonts, and responsive pixel art. Apply when creating or modifying retro-styled components and their CSS.

News tracking and update tool. Retrieve the latest news on a specific topic and support intelligent Q&A based on up-to-date information. Triggered when the user needs to: (1) check the latest news in a field (e.g., AI, technology, finance); (2) learn about a company’s developments (e.g., OpenAI, Google, Tesla); (3) track a person’s recent status (e.g., Elon Musk, Sam Altman); (4) get news in a region (e.g., China tech news); (5) learn the latest about a product (e.g., ChatGPT, Claude); (6) follow the progress of an event (e.g., CES); (7) ask questions that require the latest information to answer (e.g., "Which is the strongest AI model right now?"). Trigger keywords include: news, updates, latest, recent, status, progress, information, etc.

Expert knowledge synthesizer specializing in extracting insights from multi-agent interactions, identifying patterns, and building collective intelligence. Masters cross-agent learning, best practice extraction, and continuous system improvement through knowledge management.

Life Cycle Assessment skill for environmental impact evaluation and sustainability analysis

Scenario narrative generation skill for creating vivid, consistent future scenario descriptions

Design settings, locations, props, costumes, and production elements for film/TV with visual consistency

name: returns-reverse-logistics description: 用于退货授权、接收与检验、处置决策、退款处理、欺诈检测以及保修索赔管理的标准化专业知识。基于拥有15年以上经验的退货运营经理的见解。包括分级框架、处置经济学、欺诈模式识别和供应商回收流程。适用于处理产品退货、逆向物流、退款决策、退货欺诈检测或保修索赔时使用。license: Apache-2.0 ver...

Automatically captures, crops, and beautifies screenshots from URLs for your portfolio or docs.

Transform raw data into analytical assets using ETL/ELT patterns, SQL (dbt), Python (pandas/polars/PySpark), and orchestration (Airflow). Use when building data pipelines, implementing incremental models, migrating from pandas to polars, or orchestrating multi-step transformations with testing and quality checks.

Claude Code skill for Four Pillars (Si Zhu / BaZi) Chinese astrology chart generation and destiny analysis referencing nine classical texts

Transform AI-generated content into authentic, human-sounding writing. Covers AI pattern detection, natural writing rhythm restoration, voice injection, brand personality application, and authenticity scoring. Use when content sounds robotic, uses AI cliches, lacks personality, reads like committee writing, or when user mentions AI content, make it human, add personality, sounds robotic, fix AI writing, content authenticity, AI detection, or humanize content.

Creates simple Three.js web apps with scene setup, lighting, geometries, materials, animations, and responsive rendering. Use for: "Create a threejs scene/app/showcase" or when user wants 3D web content. Supports ES modules, modern Three.js r150+ APIs.

Build high-converting cross-border ecommerce PDP, hero image, product image stack, and AI image prompt strategy by resolving minimum inputs in priority order from user input, attachments, context, web research, logic inference, and explicit assumptions/defaults; then diagnose the conversion driver, produce an English (US) baseline, optionally localize while preserving intent, and generate executable image prompts or images through the bundled OpenAI-compatible image script.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

PDF manipulation toolkit. Extract text and tables, create PDFs, merge and split documents, and fill forms for programmatic document processing and analysis.

Build a production-quality chat UI with keyboard handling, recycling lists, gestures, and platform-specific implementations

生成符合中国专利申请标准的技术交底书。此 Skill 应由 generate-docs-agent 编排调用，不建议直接使用。强制进行技术深度分析，确保技术描述深入、逻辑连贯、避免词语堆积。

Provides implementation patterns for Clean Architecture, Domain-Driven Design (DDD), and Hexagonal Architecture (Ports & Adapters) in NestJS/TypeScript applications. Use when structuring complex backend systems, designing domain layers with entities, value objects, and aggregates, implementing ports and adapters, creating use cases, or refactoring anemic models into rich domain models using dependency inversion.