Total 32,743 skills
Showing 12 of 32743 skills
Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).
Use when building any system where email content triggers actions — AI agent inboxes, automated support handlers, email-to-task pipelines, or any workflow processing untrusted inbound email. Always use this skill when the user wants to receive emails and act on them programmatically, even if they don't mention "agent" — the skill contains critical security patterns (sender allowlists, content filtering, sandboxed processing) that prevent untrusted email from controlling your system.
Curate a Chinese reading digest from a fixed bundle of RSS and Atom feeds, with a strong preference for AI agent thinking, frontier AI commentary, deep interviews, and non-boring high-signal essays. Use when Codex needs to pull the latest week's posts by default, or a specific day's posts when explicitly requested, summarize them, score each article on a 10-point scale, and output only the posts scoring above 7 in a concise Chinese daily-brief style.
Use this skill when the user mentions wallet login, sign in, verify OTP, create wallet, switch account, wallet status, logout, wallet balance, assets, holdings, send tokens, transfer ETH, transfer USDC, pay someone, send crypto, send ERC-20, send SPL, transaction history, recent transactions, tx status, tx detail, order list, call smart contract, interact with contract, execute contract function, send calldata, invoke smart contract, show my addresses, wallet addresses, deposit, receive, receive address, top up, fund my wallet. Chinese: 登录钱包, 钱包登录, 验证OTP, 创建钱包, 切换账户, 钱包状态, 退出登录, 余额, 资产, 钱包列表, 账户列表, 发送代币, 转账, 交易历史, 交易记录, 合约调用, 我的地址, 钱包地址, 充值, 充币, 收款, 收款地址, 入金. Manages the wallet lifecycle: auth (login, OTP verify, account creation, switching, status, logout), authenticated balance queries, wallet address display (grouped by XLayer/EVM/Solana), token transfers (native & ERC-20/SPL), transaction history, and smart contract calls. Do NOT use for DEX swaps — use okx-dex-swap. Do NOT use for token search or market data — use okx-dex-token or okx-dex-market. Do NOT use for smart money / whale / KOL signals — use okx-dex-signal. Do NOT use for meme token scanning — use okx-dex-trenches. Do NOT use for transaction broadcasting (non-wallet) — use okx-onchain-gateway. Do NOT use when the user says only a single word like 'wallet' or 'login' without specifying an action or context. Do NOT use for security scanning (token/DApp/tx/sig) — use okx-security. Do NOT use for querying a specific public address's portfolio balance (user provides an explicit address like 0xAbc...) — use okx-wallet-portfolio. Do NOT use for PnL analysis (win rate, realized/unrealized PnL, DEX history) — use okx-dex-market.
Like and unlike posts on X through Shift's Skill Router.
Repost and undo reposts on X through Shift's Skill Router.
Retrieve the authenticated X user profile through Shift's Skill Router.
Read home timeline, mentions, and user posts on X through Shift's Skill Router.
AI design intelligence skill for building professional UI/UX across multiple platforms with 161 reasoning rules, 67 styles, and automated design system generation
Query NVIDIA PTX ISA 9.1, CUDA Runtime API 13.1, Driver API 13.1, Programming Guide v13.1, Best Practices Guide, Nsight Compute, Nsight Systems local documentation. Debug and optimize GPU kernels with nsys/ncu/compute-sanitizer workflows. Use when writing, debugging, or optimizing CUDA code, GPU kernels, PTX instructions, inline PTX, TensorCore operations (WMMA, WGMMA, TMA, tcgen05), or when the user mentions CUDA API functions, error codes, device properties, memory management, profiling, GPU performance, compute capabilities, CUDA Graphs, Cooperative Groups, Unified Memory, dynamic parallelism, or CUDA programming model concepts.
Develop, debug, and optimize SGLang LLM serving engine. Use when the user mentions SGLang, sglang, srt, sgl-kernel, LLM serving, model inference, KV cache, attention backend, FlashInfer, MLA, MoE routing, speculative decoding, disaggregated serving, TP/PP/EP, radix cache, continuous batching, chunked prefill, CUDA graph, model loading, quantization FP8/GPTQ/AWQ, JIT kernel, triton kernel SGLang, or asks about serving LLMs with SGLang.