Docker
容器化与 Docker
lark-conversation-governor
cklxx
Lark 对话治理技能 — 主动消息节奏控制、静默窗、停用信号检测。
k8s-debug
eveld
Launch ephemeral debug container in running pod for interactive debugging. Use when you need to debug a pod without restarting it.
cnn-vision
levy-n
Implements CNN architectures for computer vision tasks. Covers convolution operations, pooling, CNN design patterns (LeNet, ResNet, VGG), transfer learning, fine-tuning pretrained models, data augmentation, and image preprocessing. Use when building image classifiers, doing object detection, or when user mentions 'CNN', 'convolution', 'pooling', 'ResNet', 'VGG', 'transfer learning', 'fine-tuning', 'image augmentation', 'ImageNet', 'feature maps', 'MNIST', 'image classification', 'multi-modal', 'image captioning', or 'multimodal network'.
start-dev-server
kenny-stacks
Start Clarinet devnet and frontend development servers. Use when the user wants to run their Stacks project locally for testing and development.
deckset-presentation-expert
doudou1337
Expert assistant for creating Deckset presentations with markdown. Helps with slide formatting, headings, lists, images, videos, presenter notes, build steps, themes, and configuration. Use when working with .md presentation files, or when user mentions Deckset, creating slides, presentations, or decks.
asset-generation
phrazzld
Programmatic visual asset pipeline for proposal-context logos and images. Uses Recraft, OpenAI Image, and Nano Banana Pro together with phase-aware breadth vs convergence.
cuda-kernel-dev
TrevorS
Target: reduce ~700 kernel launches/frame to ~545
dependency-injection
Kaakati
"Expert DI decisions for iOS/tvOS: when DI containers add value vs overkill, choosing between injection patterns, protocol design for testability, and SwiftUI-specific injection strategies. Use when designing service layers, setting up testing infrastructure, or deciding how to wire dependencies. Trigger keywords: dependency injection, DI, constructor injection, protocol, mock, testability, container, factory, @EnvironmentObject, service locator"
video-agent
founderjourney
AI content generation suite with 35+ models. Image generation, video creation, audio processing via FAL AI, Google Vertex AI, ElevenLabs. Pipeline orchestration and cost management.
baoyu-image-gen
Jst-Well-Dan
Generates images using official OpenAI and Google APIs via AI SDK. Supports text-to-image, reference images, aspect ratios, and quality presets. Use when user asks to "generate image with API", "use official API for images", "create image with OpenAI/Google", or needs API-based generation instead of browser-based.
performance-optimization
Kaakati
"Expert performance decisions for iOS/tvOS: when to optimize vs premature optimization, profiling tool selection, SwiftUI view identity trade-offs, and memory management strategies. Use when debugging performance issues, optimizing slow screens, or reducing memory usage. Trigger keywords: performance, Instruments, Time Profiler, Allocations, memory leak, view identity, lazy loading, @StateObject, retain cycle, image caching, faulting, batch operations"
Performance Optimization
Kaakati
Performance optimization patterns for Flutter applications including widget optimization, memory management, profiling, and 60 FPS best practices
accessibility-patterns
Kaakati
"Expert accessibility decisions for iOS/tvOS: when to combine vs separate elements, label vs hint selection, Dynamic Type layout strategies, and WCAG AA compliance trade-offs. Use when implementing VoiceOver support, handling Dynamic Type, or ensuring accessibility compliance. Trigger keywords: accessibility, VoiceOver, Dynamic Type, WCAG, a11y, accessibilityLabel, accessibilityElement, accessibilityTraits, isAccessibilityElement, reduceMotion, contrast, focus"
querying-yaml
iota9star
Extracts specific fields from YAML files efficiently using yq instead of reading entire files, saving 80-95% context. Use this skill when querying YAML files, filtering/transforming configuration data, or getting specific field(s) from large YAML files like docker-compose.yml or GitHub Actions workflows
qwen3-tts-profile
TrevorS
Profile and benchmark qwen3-tts-rs inference. Runs e2e_bench with chrome tracing, flamegraph, or Nsight Systems inside a CUDA Docker container. Triggers on: "profile", "benchmark", "run profiling", "chrome trace", "flamegraph", "nsys", "perf trace", "how fast", "what's slow", "performance", "bottleneck"
claude-code-web-docker
TrevorS
Set up and use Docker in Claude Code for Web environments. Use when Docker builds fail with bridge/iptables errors, SSL certificate errors through proxy, or when working in containerized web environments.
baoyu-danger-gemini-web
Jst-Well-Dan
Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.
model-patterns
Kaakati
"Expert model design decisions for iOS/tvOS: when DTO separation adds value vs overkill, validation strategy selection, immutability trade-offs, and custom Codable decoder design. Use when designing data models, implementing API contracts, or debugging decoding failures. Trigger keywords: Codable, DTO, domain model, CodingKeys, custom decoder, validation, immutable, struct, mapping, JSON decoding"
baoyu-post-to-wechat
Jst-Well-Dan
Posts content to WeChat Official Account (微信公众号) via Chrome CDP automation. Supports article posting (文章) with full markdown formatting and image-text posting (图文) with multiple images. Use when user mentions "发布公众号", "post to wechat", "微信公众号", or "图文/文章".
coordinator-pattern
Kaakati
"Expert Coordinator pattern decisions for iOS/tvOS: when coordinators add value vs overkill, parent-child coordinator hierarchy design, SwiftUI vs UIKit coordinator differences, and flow completion handling. Use when designing navigation architecture, implementing multi-step flows, or decoupling views from navigation. Trigger keywords: Coordinator, navigation, flow, parent coordinator, child coordinator, deep link, routing, navigation hierarchy, flow completion"
devops-pathfinders
founderjourney
Advanced DevOps skill for managing Debian 12 VPS servers on Contabo with Docker, Nginx, and MySQL infrastructure. Use when working with server setup, Docker deployments, SSL configuration, security hardening, backup strategies, troubleshooting access issues, container management, Nginx reverse proxy configuration, or any DevOps task on the Pathfinders Labs infrastructure. Specialized in KISS (Keep It Simple, Stupid) approach with single Docker network, shared MySQL, native Nginx, and centralized credentials management.
generative-models
levy-n
Generative AI models: GANs, VAEs, Diffusion Models, and image generation. Covers GAN architecture (Generator/Discriminator), DCGAN, Wasserstein GAN, Variational Autoencoders, latent space interpolation, Diffusion models (DDPM), Stable Diffusion, conditional generation, and text-to-image. Use when user asks about 'GAN', 'generative adversarial', 'VAE', 'variational autoencoder', 'diffusion model', 'image generation', 'Stable Diffusion', 'DCGAN', 'Wasserstein', 'WGAN', 'latent space', 'generate images', 'text-to-image', 'DDPM', 'denoising diffusion', 'style transfer', or 'deepfake'.
deployment-docker
CsHeng
Docker and containerization guidelines. Use when deployment docker guidance is required.
web-asset-generator
founderjourney
Generate production-ready web assets through conversation. Favicons, PWA icons, and social media images from logos, emojis, or text.