Skill rating

Specialized skill for building production-ready serverless applications on GCP. Covers Cloud Run services (containerized), Cloud Run Functions (event-driven), cold start optimization, and event-driven

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

智能视频剪辑：用自然语言描述要保留的片段/人物/事件，自动从长视频抽取剪辑（可用参考图做人物/物体匹配）。当用户要按描述找片段、提取高光或做智能剪辑时触发。

Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration

Opinionated toolkit for building, versioning, and publishing high-quality JavaScript/TypeScript packages.

Headless utilities for building range and multi-range sliders in TS/JS, React, Vue, Solid, Svelte & Angular.

Expert skill for building, running, and extending MinecraftConsoles (Minecraft Legacy Console Edition) — a C++ multi-platform reimplementation with dedicated server, LAN multiplayer, and modding suppo

Self-hosted ML coding practice platform with 68 problems covering Transformers, diffusion, RLHF, and more — instant browser feedback, no GPU required.

Write academic conference papers and research submissions

Headless UI for building powerful tables & datagrids for TS/JS, React, Vue, Solid, Svelte, Qwik, Angular, and Lit.

Use when editing photos for Xiaohongshu, comparing editing apps, or improving visual content quality

Create accurate Japanese UI DESIGN.md files for AI agents with proper CJK typography, font stacks, line-height, kinsoku shori, and mixed typesetting rules.

Universal AI context generator that compiles codebase maps, wiki knowledge bases, and MCP tools to save thousands of tokens per AI conversation.

Build and extend Gemma Gem, an on-device AI browser assistant Chrome extension running Google's Gemma 4 model via WebGPU with no cloud dependencies.

标准化文章编辑流程，确保修改范围明确、进度可追踪、变更有记录。当用户说"编辑文章"、"修改文章"、"调整内容"、"改一下这篇"时使用此技能。

Reference HLSL shader implementations for the Slug font rendering algorithm, enabling high-quality GPU-accelerated vector font and glyph rendering.

Open source harness for generating 3D CAD models from text using AI coding agents with build123d/OpenCascade, exporting STEP/STL/URDF, and previewing in a local CAD Explorer viewer.

AI-powered X (Twitter) content strategy skill that distills methodologies from 6 top creators + open-source algorithm data into actionable writing, growth, and monetization guidance.

Experiment with configs by creating and managing variations. Helps you test different models, prompts, and parameters to find what works best through systematic experimentation.

Complete file handling including upload flows, serving files via URL, storing generated files from actions, deletion, and accessing file metadata from system tables

Create or update .groove/index.md config interactively. Run before groove install.

Generate a personal "Now Reading" webpage from your Reader library

Create a new CMS collection in Webflow with specified fields and relationships. Use when setting up blog posts, products, team members, portfolios, or other content types with custom fields.

Core trading insights learned from Agent Arena competition. Use when making any trading decision to apply institutional knowledge.

WildWorld large-scale action-conditioned world modeling dataset with 108M+ frames from a photorealistic ARPG game, featuring per-frame annotations, 450+ actions, and explicit state information for gen

Extract highlights, best moments, and key clips from long videos using each::sense AI. Perfect for gaming highlights, sports clips, podcast moments, webinar summaries, meeting recaps, and auto-trailer

>

>

Fast, lightweight 2D rendering engine for creating interactive graphics, particle effects, and canvas-based applications using WebGL/WebGPU. Use this skill when building 2D games, particle systems, in

Expert guidance for working with Hugging Face Transformers library for NLP, computer vision, and multimodal AI tasks.

Markdown conversion: PDF, Office, HTML, data, OCR, audio, ZIP, YouTube.

Builds, deploys, manages, debugs, configures, and optimizes serverless applications on AWS using Lambda, API Gateway, Step Functions, EventBridge, and SAM/CDK. Covers cold starts, CORS debugging, even

Generate professional poster designs using each::sense AI. Create movie posters, event posters, motivational posters, product launch visuals, vintage designs, travel posters, and more with AI-powered

Generate professional resume and CV designs using each::sense AI. Create modern, creative, minimalist, executive, tech, academic, infographic, two-column, ATS-friendly, and portfolio-style resumes opt

当创建新技能、编辑现有技能或在部署前验证技能是否有效时使用

Create and configure configs in LaunchDarkly. Helps you choose between agent vs completion mode, create the config, add variations with models and prompts, and verify the setup.

Patterns for building reactive apps including subscription management, optimistic updates, cache behavior, and paginated queries with cursor-based loading

[Document Processing] Convert PDF files to Markdown with support for native text PDFs and scanned documents (OCR). Cross-platform.

Build accessible, responsive, and performant frontend components with design system best practices, modern CSS, and framework-agnostic patterns.

**CEX 中心化交易所**(Binance / OKX / Bybit / Bitget 等)的下单交易工具。严格规则:(1) 所有订单必须通过 node scripts/exchange.mjs create_order 执行,禁止写自定义代码下单 (2) create_order 分两步:第一次返回预览,展示给用户等确认,用户说确认后第二次加 confirmed=true 执行 (3) 禁止

Create distinctive, high-converting landing pages that combine proven conversion elements with exceptional design quality. Build beautiful, memorable landing pages using Next.js 14+ and ShadCN UI that

[Document Processing] Use when you need to convert Microsoft Word ( DOCX) files to Markdown with GFM support (tables, images, code blocks).

Generate professional restaurant, cafe, and bar menu designs using each::sense AI. Create print-ready menus, digital displays, QR code menus, and seasonal specials with stunning food photography and e

Building AI agents with the Convex Agent component including thread management, tool integration, streaming responses, RAG patterns, and workflow orchestration

Monitor management - list, search, file-based create, and alerting best practices.

Generate a comprehensive marketing website for a web app — multi-page with real screenshots, animated GIF walkthroughs, feature deep-dives, and workflow demonstrations. Browses the running app, captur

Generates minimal macOS Seatbelt sandbox configurations. Use when sandboxing, isolating, or restricting macOS applications with allowlist-based profiles.

Convert a Jupyter notebook (.ipynb) to a marimo notebook (.py).

Generate 3D models using each::sense AI. Create 3D assets from text or images for games, products, architecture, characters, vehicles, and more with PBR textures.

Generate audio visualization videos using each::sense AI. Create waveforms, spectrum analyzers, particle effects, 3D visualizations, and beat-synced animations from audio files.