Loading...
Loading...
Found 9,262 Skills
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
Use when securing Spring Boot API endpoints with JWT Bearer token validation, scope-based authorization, or DPoP proof-of-possession - integrates com.auth0:auth0-springboot-api SDK for REST APIs receiving access tokens from frontends or mobile apps. Triggers on Auth0AuthenticationFilter, Spring Boot API auth, JWT validation, SecurityFilterChain, hasAuthority SCOPE.
Use this skill when a vanilla static SPA scaffold exists and needs to feel like a polished product — progress persistence, sidebar + scrollspy navigation, dark/light theme, content zoom, responsive (mobile sidebar overlay), keyboard nav, fade-in entrances, toast notifications, iframe modal viewers, quiz scoring with section back-links. Triggers on phrases like "加進度勾選", "響應式", "暗色模式", "縮放", "scrollspy", "sidebar 收合", "手機版", "RWD", "dark mode", "progress tracking", "quiz UX", "interactive polish". Always invoke AFTER `static-spa-conversion` (renders working), as a standalone enhancement layer.
Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores.
Use this skill when developing WeChat Mini Programs (小程序, 企业微信小程序, wx.cloud-based apps) that need AI capabilities. Features text generation (generateText) and streaming (streamText) with callback support (onText, onEvent, onFinish) via wx.cloud.extend.AI. Built-in models include Hunyuan (hunyuan-2.0-instruct-20251111 recommended) and DeepSeek (deepseek-v3.2 recommended). API differs from JS/Node SDK - streamText requires data wrapper, generateText returns raw response. NOT for browser/Web apps (use ai-model-web), Node.js backend (use ai-model-nodejs), or image generation (not supported).
Perform comprehensive code reviews with best practices, security checks, and constructive feedback. Use when reviewing pull requests, analyzing code quality, checking for security vulnerabilities, or providing code improvement suggestions.
Expert skill for integrating local Large Language Models using llama.cpp and Ollama. Covers secure model loading, inference optimization, prompt handling, and protection against LLM-specific vulnerabilities including prompt injection, model theft, and denial of service attacks.
Production-grade AI agent patterns with MCP integration, agentic RAG, handoff orchestration, multi-layer guardrails, observability, token economics, ROI frameworks, and build-vs-not decision guidance (modern best practices)
Use when building 3D scenes with TresJS (Vue Three.js) - provides TresCanvas, composables (useTres, useLoop), Cientos helpers (OrbitControls, useGLTF, Environment), and post-processing effects
Parse ebooks, extract concepts and entities with citation traceability, classify by type/layer, and synthesize across book collections.
Implements security headers and Content Security Policy with safe rollout strategy (report-only → enforce), testing, and compatibility checks. Use for "security headers", "CSP", "HTTP headers", or "XSS protection".
Google Gemini File Search for managed RAG with 100+ file formats. Use for document Q&A, knowledge bases, or encountering immutability errors, quota issues, polling failures. Supports Gemini 3 Pro/Flash (Gemini 2.5 legacy).