Loading...
Loading...
Found 2,256 Skills
Integrate and optimize Core ML models in iOS apps for on-device machine learning inference. Covers model loading (.mlmodelc, .mlpackage), predictions with auto-generated classes and MLFeatureProvider, compute unit configuration (CPU, GPU, Neural Engine), MLTensor, VNCoreMLRequest, MLComputePlan, multi-model pipelines, and deployment strategies. Use when loading Core ML models, making predictions, configuring compute units, or profiling model performance.
Use when running paid advertising campaigns on Xiaohongshu, setting up promoted posts, managing ad budgets, optimizing ad performance, or scaling growth through paid promotion
Use when conducting deep analytics on Xiaohongshu accounts, tracking content performance trends, researching influencer data, monitoring category growth, or making strategic decisions with comprehensive social media analytics
Guide for diagnosing and improving MSBuild project evaluation performance. Only activate in MSBuild/.NET build context. Use when builds are slow before any compilation starts, when evaluation time is high in binlog analysis, or when dealing with expensive glob patterns and deep import chains. Covers evaluation phases, glob optimization, import chain analysis, and /pp preprocessing.
Structure a performance review with self-assessment, manager template, and calibration prep. Use when review season kicks off and you need a self-assessment template, writing a manager review for a direct report, prepping rating distributions and promotion cases for calibration, or turning vague feedback into specific behavioral examples.
Design and draft multi-email sequences with full copy, timing, branching logic, exit conditions, and performance benchmarks. Use when building onboarding, lead nurture, re-engagement, win-back, or product launch flows, when you need a complete drip campaign with A/B test suggestions, or when mapping a sequence end-to-end with a flow diagram.
Analyze stock correlations to find related companies and trading pairs. Use this skill whenever the user asks about correlated stocks, related companies, sector peers, trading pairs, or how two or more stocks move together. Triggers include: "what correlates with NVDA", "find stocks related to AMD", "correlation between AAPL and MSFT", "what moves with", "sector peers", "pair trading", "correlated stocks", "when NVDA drops what else drops", "find me a pair for", "stocks that move together", "beta to", "relative performance", "which stocks follow AMD", "supply chain partners", "correlation matrix", "co-movement", "related tickers", "sympathy plays", "if GOOGL moves what else moves", "semiconductor peers", "compare correlation", "hedging pair", "sector clustering", "realized correlation", "rolling correlation", or any request about finding stocks that move in tandem or inversely. Also triggers when the user mentions well-known pairs like AMD/NVDA, GOOGL/AVGO, LITE/COHR and wants to understand or find similar relationships. Always use this skill even if the user only provides one ticker — infer that they want to find correlated peers.
OmniStudio FlexCard creation and validation with 130-point scoring. Use when building at-a-glance UI cards, configuring data source bindings to Integration Procedures, or reviewing existing FlexCard definitions for accessibility and performance. TRIGGER when: user creates FlexCards, configures data sources, designs card layouts, or asks about OmniUiCard metadata. DO NOT TRIGGER when: building OmniScripts (use sf-omniscript), creating Integration Procedures (use sf-integration-procedure), or analyzing dependencies (use sf-omnistudio-analyze).
View social media analytics and insights. Use when the user wants to check post performance, engagement metrics, best posting times, follower stats, content decay, posting frequency, or any analytics data from their connected platforms.
React and Next.js performance optimization from Vercel Engineering. Use when building React components, optimizing performance, eliminating waterfalls, reducing bundle size, reviewing code for performance issues, or implementing server/client-side optimizations.
Gate Exchange affiliate program data query and management skill. Use this skill when users ask about their affiliate/partner commission, trading volume, net fees, customer count, trading users, or want to apply for the affiliate program. Supports queries for up to 180 days (API limited to 30 days per request, agent should split longer queries). IMPORTANT: user_id parameter in APIs refers to 'trader' not 'commission receiver' - avoid using unless explicitly specified. Aggregated data from API lists should be calculated using custom scripts, not simple summation. CRITICAL TIME CONSTRAINT: All query times are calculated based on user's system current date in UTC+8 timezone. For relative time descriptions (e.g., 'last 7 days', 'last 30 days', 'this week', 'last month'), calculate start date by subtracting days from current date, then convert both start and end dates to UTC+8 00:00:00 and 23:59:59 respectively, then convert to Unix timestamps. NEVER use future timestamps as query conditions. When timestamps are needed, obtain them via system functions, never generate manually. The 'to' parameter must always be less than or equal to the current Unix timestamp. Trigger phrases include 'my affiliate data', 'commission this week', 'partner earnings', 'team performance', 'customer trading volume', 'rebate income', 'apply for affiliate', 'can I apply', 'am I eligible', 'my application status', 'recent application', 'partner application status'.
Performance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time".