2097 个 · 按相关度排序
Improve MNN inference on OpenCL by measuring bottlenecks and refining GPU kernels, the code that performs calculations. The skill guides baseline measurements, correctness checks, Android device benchmarks, and integration of new OpenCL features with compatibility fallbacks.
中文简介正在准备中。当前显示英语简介。
Develop or port CPU kernels, the low-level calculation routines used by MNN. Follow staged implementation guidance, check data layout agreements, register functions, and verify correctness across processor instruction sets and numerical precision settings.
中文简介正在准备中。当前显示英语简介。
Review Doris code changes using project-specific checklists for data correctness, concurrency, memory safety, compatibility, performance, and tests. Trace related code paths and explain findings with concrete failure scenarios, using query plan trees when reviewing optimizer behavior.
中文简介正在准备中。当前显示英语简介。
Optimize transformer attention, the calculation that relates tokens to one another, using Flash Attention. The skill guides PyTorch integration, GPU memory reduction, performance measurement, and output comparisons for training or inference with long sequences.
中文简介正在准备中。当前显示英语简介。
Build and debug mobile apps for iOS and Android with React Native and Expo. Implement navigation, adapt screens to each platform, integrate native modules that access platform features, and improve list rendering, keyboard behavior, and memory use.
中文简介正在准备中。当前显示英语简介。
Investigate slow PostgreSQL and MySQL queries using execution plans, which show how the database runs a query. Develop index, SQL, and configuration changes, then compare measurements before and after each change to validate the results.
中文简介正在准备中。当前显示英语简介。
Assess a website separately for five AI search services, including ChatGPT and Google AI Overviews. Compare scores, identify gaps in content and platform presence, and receive actions organized by priority and timeframe.
中文简介正在准备中。当前显示英语简介。
Assess a website’s readiness for AI search alongside traditional SEO. Review content citation readiness, crawler access, brand mentions, technical foundations, and structured data, then generate scores, prioritized recommendations, and client reports.
中文简介正在准备中。当前显示英语简介。
Audit Microsoft Advertising tracking, search and audience campaigns, Google Ads imports, keywords, bidding, and budgets. Get prioritized recommendations with supporting evidence and clearly marked gaps, while keeping campaign changes outside the audit.
中文简介正在准备中。当前显示英语简介。
Review YouTube Ads campaign setup, video formats, creative, audiences, brand safety, bidding, and measurement. Receive prioritized recommendations supported by account evidence, with uncertainties and missing inputs identified, while keeping all account changes as drafts.
中文简介正在准备中。当前显示英语简介。
Review TikTok Ads measurement, mobile video creative, audiences, commerce campaigns, bidding, and budgets. Receive prioritized recommendations with supporting evidence, missing information, and uncertainty clearly identified, while keeping the review read-only.
中文简介正在准备中。当前显示英语简介。
Review Facebook and Instagram ads through a read-only audit of measurement, creative, audiences, placements, budgets, and account structure. Receive prioritized recommendations that account for missing evidence and distinguish account, Pixel, and conversion history.
中文简介正在准备中。当前显示英语简介。
Audit Google Ads conversion measurement, search terms, keywords, creative assets, bidding, budgets, and settings. Use account evidence to identify wasted spend and prioritize improvements across Search, Shopping, Performance Max, and Demand Gen without changing campaigns.
中文简介正在准备中。当前显示英语简介。
Assess an existing Convex app and turn the findings into a prioritized improvement plan. With explicit approval, update outdated components, address production error monitoring gaps, and reassess the app to show how its score changed.
中文简介正在准备中。当前显示英语简介。
Diagnose slow loading, high memory use, and low frame rates in USD 3D scenes. Coordinate scene structure checks, validation, optimization, and before-and-after performance comparisons, then produce a report documenting findings and changes.
中文简介正在准备中。当前显示英语简介。
Improve a web page’s loading speed, response to user actions, and visual stability. The skill guides targeted fixes for LCP, INP, and CLS, with code examples, measurement methods, and checklists for each metric.
中文简介正在准备中。当前显示英语简介。
Create, audit, and improve pages for AI search engines by checking crawl access, metadata, clear answers, sources, and structured data that describes page content. It produces prioritized fixes and citation-friendly pages without guaranteeing inclusion in AI answers.
中文简介正在准备中。当前显示英语简介。
Improve how search engines discover and understand a website by reviewing titles, descriptions, links, and sitemaps. Add structured data, machine-readable descriptions of page content, and use checklists to identify technical and on-page SEO issues.
中文简介正在准备中。当前显示英语简介。
Measure and improve animation performance on frontend pages. Identify offscreen activity, pause CSS and canvas or WebGL loops, audit resource cleanup, and compare runtime observations before and after changes to investigate scrolling issues and long-session slowdowns.
中文简介正在准备中。当前显示英语简介。
Review and improve SKILL.md files using nine evaluation criteria and test prompts. Independent agents compare original and revised versions, while user checkpoints, version history, and result cards help track which changes are retained or rolled back.
中文简介正在准备中。当前显示英语简介。
Analyze code, database queries, or systems for performance problems involving speed, memory, and frontend file size. Get prioritized recommendations with code examples, expected impact, implementation effort, risks, and a roadmap for improvements.
中文简介正在准备中。当前显示英语简介。
Evaluate AI agents by preparing test cases, scoring responses and tool use, investigating failures, and comparing results after changes. Supports built-in checks and custom scoring rules, including evaluations performed by a language model.
中文简介正在准备中。当前显示英语简介。
Guide a development task through requirements research, solution comparison, planning, implementation, optimization, and review. The workflow asks for approval at key stages and saves plans and completed task records in the project.
中文简介正在准备中。当前显示英语简介。
Review nine parts of a LinkedIn profile and get prioritized fixes with before-and-after rewrites. Tailor headlines, About sections, work experience, and featured content to attracting clients, finding a job, or establishing professional expertise.
中文简介正在准备中。当前显示英语简介。