Loading...
Loading...
Found 69 Skills
Generate Triton kernel code for Ascend NPU based on operator design documents. Used when users need to implement Triton operator kernels and convert requirement documents into executable code. Core capabilities: (1) Parse requirement documents to confirm computing logic (2) Design tiling partitioning strategy (3) Generate high-performance kernel code (4) Generate test code to verify correctness.
Expert guidance for GraalVM native image development with Java frameworks, build optimization, and high-performance application deployment
Senior Database Administrator with expertise in PostgreSQL, MySQL, MongoDB, and enterprise database systems. Specializes in high availability architectures, performance tuning, backup strategies, and database security for production environments.
CSS architecture and styling expert with deep knowledge of modern CSS features, responsive design, CSS-in-JS optimization, performance, accessibility, and design systems. Use PROACTIVELY for CSS layout issues, styling architecture, responsive design problems, CSS-in-JS performance, theme implementation, cross-browser compatibility, and design system development. If a specialized expert is better fit, I will recommend switching and stop.
Optimize Granola transcription quality and note performance. Use when improving transcription accuracy, reducing processing time, or enhancing note quality. Trigger with phrases like "granola performance", "granola accuracy", "granola quality", "improve granola", "granola optimization".
MySQL 数据库管理与运维
· Configure/tune/migrate PostgreSQL, MongoDB, MySQL/MariaDB, MSSQL. Triggers: 'database', 'postgres', 'mysql', 'mongodb', 'schema', 'migration', 'pgbouncer', 'EXPLAIN'.
Use when building SwiftUI interfaces for iOS, iPadOS, macOS, or visionOS. Triggers on Liquid Glass adoption, SwiftUI animation/transitions, layout patterns, state management, design tokens, performance optimization, accessibility in SwiftUI, or creating "Apple-level" UI quality.
Optimize Groq API performance with caching, batching, and connection pooling. Use when experiencing slow API responses, implementing caching strategies, or optimizing request throughput for Groq integrations. Trigger with phrases like "groq performance", "optimize groq", "groq latency", "groq caching", "groq slow", "groq batch".
Complete ClickHouse operations guide for DevOps and SRE teams managing production deployments. Provides practical guidance on monitoring essential metrics (query latency, throughput, memory, disk), introspecting system tables, performance analysis, scaling strategies (vertical and horizontal), backup/disaster recovery, tuning at query/server/table levels, and troubleshooting common issues. Use when diagnosing ClickHouse problems, optimizing performance, planning capacity, setting up monitoring, implementing backups, or managing production clusters. Includes resource management strategies for disk space, connections, and background operations plus production checklists.
Expert patterns for Godot 3D lighting including DirectionalLight3D shadow cascades, OmniLight3D attenuation, SpotLight3D projectors, VoxelGI vs SDFGI, and LightmapGI baking. Use when implementing realistic 3D lighting, shadow optimization, global illumination, or light probes. Trigger keywords: DirectionalLight3D, OmniLight3D, SpotLight3D, shadow_enabled, directional_shadow_mode, directional_shadow_split, omni_range, omni_attenuation, spot_range, spot_angle, VoxelGI, SDFGI, LightmapGI, ReflectionProbe, Environment, WorldEnvironment.
Autonomous iterative experimentation loop for any programming task. Guides the user through defining goals, measurable metrics, and scope constraints, then runs an autonomous loop of code changes, testing, measuring, and keeping/discarding results. Inspired by Karpathy's autoresearch. USE FOR: autonomous improvement, iterative optimization, experiment loop, auto research, performance tuning, automated experimentation, hill climbing, try things automatically, optimize code, run experiments, autonomous coding loop. DO NOT USE FOR: one-shot tasks, simple bug fixes, code review, or tasks without a measurable metric.