Loading...
Loading...
Found 1,766 Skills
Deep Performance Optimization Skill for Triton Operators on Ascend NPU, dedicated to achieving the Triton operator performance improvement required by users. Core technologies include but are not limited to Unified Buffer (UB) capacity planning, multi-Tokens parallel processing, MTE/Vector pipeline parallelism, mask optimization, etc. This Skill must be triggered when the user mentions the following: performance optimization of Vector-type Triton operators on Ascend NPU.
When the user wants to optimize multiple conflicting objectives, find Pareto-optimal solutions, or balance trade-offs between cost, service, quality, and sustainability. Also use when the user mentions "multi-objective," "Pareto optimization," "NSGA-II," "trade-off analysis," "scalarization," "weighted objectives," "goal programming," or "multiple criteria optimization." For single objective, see optimization-modeling.
When the user wants to solve the Vehicle Routing Problem (VRP), optimize multi-vehicle routes, or plan fleet delivery routes. Also use when the user mentions "VRP," "fleet routing," "multi-vehicle routing," "delivery route planning," "vehicle dispatch," "fleet optimization," or "route assignment." For single vehicle, see traveling-salesman-problem. For time windows, see vrp-time-windows.
When the user wants to optimize maintenance strategies, improve equipment reliability, reduce downtime, or implement predictive maintenance. Also use when the user mentions "preventive maintenance," "predictive maintenance," "TPM," "Total Productive Maintenance," "MTBF," "MTTR," "reliability analysis," "equipment maintenance," "condition monitoring," "CBM," "failure analysis," or "spare parts optimization." For quality improvements, see quality-management. For OEE, see lean-manufacturing.
When the user wants to optimize delivery routes, solve vehicle routing problems, or minimize transportation costs. Also use when the user mentions "route planning," "delivery optimization," "VRP," "TSP," "multi-stop routing," "route sequencing," or "dispatch optimization." For fleet sizing and management, see fleet-management. For last-mile specific challenges, see last-mile-delivery.
MLA (Multi-Latent Attention) cost models, regime analysis, and kernel selection guide. Use when: (1) reasoning about which kernel approach to use for a given regime, (2) understanding cost model tradeoffs between FlashMLA, FlashAttention, and MLAvar6+, (3) analyzing roofline behavior across decode/speculative/prefill regimes, (4) setting optimization targets, (5) understanding MLA math and absorption trick.
Guide for using Netlify Image CDN for image optimization and transformation. Use when serving optimized images, creating responsive image markup, setting up user-uploaded image pipelines, or configuring image transformations. Covers the /.netlify/images endpoint, query parameters, remote image allowlisting, clean URL rewrites, and composing uploads with Functions + Blobs.
Perform code optimization for .vue, .js, .css, .scss, .less files in Vue2 projects. By default, optimize git changed files, or execute according to the user-specified scope. Unify code structure, BEM styles, semantic naming and key comments to improve readability and collaboration efficiency. Do not generate new components or modify business logic. Trigger scenarios: Users request code optimization, code structure standardization, unified naming, Vue2 component optimization, and code style organization.
DDEV local development environment patterns for Drupal, including configuration, commands, database management, debugging tools, and performance optimization.
Expert China e-commerce operations specialist covering Taobao, Tmall, Pinduoduo, and JD ecosystems with deep expertise in product listing optimization, live commerce, store operations, 618/Double 11 campaigns, and cross-platform strategy.
You are **Studio Operations**, an expert operations manager who specializes in day-to-day studio efficiency, process optimization, and resource coordination. You ensure smooth operations, maintain ...
Art-to-engine pipeline specialist - Masters shaders, VFX systems, LOD pipelines, performance budgeting, and cross-engine asset optimization