Total 50,615 skills, AI & Machine Learning has 8484 skills
Showing 12 of 8484 skills
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
AI-assisted academic conference poster generation from Overleaf source using Claude Code
Generate or edit images using Gemini's native `generateContent` via New-API. Suitable for scenarios requiring text-to-image generation, reference image editing, local PNG output, and those who want to reuse the `.sofunny-image.env` file or current shell environment variables.
Apply this when developing new features that add to or change the business logic of the system
Use this skill when designing AI agent architectures, implementing tool use, building multi-agent systems, or creating agent memory. Triggers on AI agents, tool calling, agent loops, ReAct pattern, multi-agent orchestration, agent memory, planning strategies, agent evaluation, and any task requiring autonomous AI agent design.
Run 397B parameter Mixture-of-Experts LLMs on a MacBook using pure C/Metal with SSD streaming
Generate NFT artwork using each::sense AI. Create PFP collections, generative art, 1/1 pieces, pixel art, 3D renders, animated NFTs, and trait-based characters for Web3 projects.
Gate Alpha token discovery, market viewing, trading, account, and order management skill. Use this skill whenever the user asks to browse Alpha tokens, check Alpha market tickers, buy or sell Alpha tokens, view Alpha holdings, check transaction history, or manage Alpha orders. Trigger phrases include 'alpha tokens', 'alpha market', 'alpha holdings', 'alpha portfolio', 'buy alpha', 'sell alpha', 'alpha order', 'alpha history', or any request involving Gate Alpha operations.
Enable multiple Claude Code instances to discover each other and exchange messages in real-time via a local broker daemon and MCP server.
This skill applies when OpenStoryline has been installed, and the user needs to start local MCP/Web services, create or continue a session, send editing instructions, perform multi-round re-editing, verify rendered video outputs, or make Chinese requests such as "启动 OpenStoryline", "把 OpenStoryline 跑起来", "用 OpenStoryline 剪视频".
Dispatch independent subagents in parallel for unrelated problems spanning different subsystems. Use when 2+ failures have independent root causes, multiple subsystems are broken independently, or user requests concurrent investigation. Use for "parallel", "multiple failures", "independent bugs", "fix these concurrently". Do NOT use for related failures, shared-state problems, or exploratory debugging where root cause is unknown.
Turn your AI skills into a revenue stream. Mint an agent on the Teneo Protocol — gasless, no tokens needed — and start earning USDC for every task you complete using x402 payments system.