Loading...
Loading...
Found 657 Skills
Create and manage agent graphs — directed graphs of AI Configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.
模型自动降级与故障切换。当主模型请求失败、超时、达到速率限制或配额耗尽时，自动切换到备用模型，确保服务连续性。支持多供应商、多优先级的智能模型选择，提供健康监控、自动重试和错误恢复机制。
Explains Single Page Applications (SPA), Multi Page Applications (MPA), and hybrid architectures. Use when discussing app architecture decisions, comparing SPA vs MPA, explaining how traditional vs modern web apps work, or when building a new web application.
This skill should be used when users want to route LLM requests to different AI providers (OpenAI, Grok/xAI, Groq, DeepSeek, OpenRouter) using SwiftOpenAI-CLI. Use this skill when users ask to "use grok", "ask grok", "use groq", "ask deepseek", or any similar request to query a specific LLM provider in agent mode.
Entry point for ASCII CLI banners. Choose the Python built-in font skill or the figlet.js/FIGfont skill depending on needs.
Complete guide to implementing deep links and universal links in Capacitor apps. Covers iOS Universal Links, Android App Links, custom URL schemes, and navigation handling. Use this skill when users need to open their app from links.
Parallel execution engine for high-throughput task completion
Discover the latest Claude Code resources added to Vibe Index
Decision framework for React Three Fiber projects. Routes to specialized R3F skills (fundamentals, geometry, materials, performance, drei) based on task requirements. Use when starting an R3F project or needing guidance on which R3F skills to combine.
Build modern Next.js apps with App Router and best practices
Load this first. Routes to the right Eve SE skill for developing, deploying, and debugging Eve-compatible apps.
Robust URL-to-Markdown extraction for OpenClaw workflows. Use this when the user needs to "extract/summarize/convert a webpage to Markdown" (especially for WeChat official accounts at mp.weixin.qq.com) and web_fetch or browser access is blocked or returns messy content. It first uses a low-cost probe via web_fetch, then falls back to the official MinerU API (through the local mineru-extract skill), and returns a traceable result contract with source links.