Loading...
Loading...
Found 73 Skills
Expert blueprint for low-level server access (RenderingServer, PhysicsServer2D/3D, NavigationServer) using RIDs for maximum performance. Bypasses scene tree overhead for procedural generation, particle systems, and voxel engines. Use when nodes are too slow OR managing thousands of objects. Keywords RenderingServer, PhysicsServer, NavigationServer, RID, canvas_item, body_create, low-level, performance.
Expert knowledge for Azure Managed Lustre development including troubleshooting, best practices, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when mounting AML, integrating with Blob auto-import/export, AKS CSI, quotas, or performance tuning, and other Azure Managed Lustre related development tasks. Not for Azure HPC Cache (use azure-hpc-cache), Azure NetApp Files (use azure-netapp-files), Azure Virtual Machines (use azure-virtual-machines), Azure Virtual Network (use azure-virtual-network).
Use when you need to set up Java application profiling to detect and measure performance issues — including automated async-profiler v4.0 setup, problem-driven profiling (CPU, memory, threading, GC, I/O), interactive profiling scripts, JFR integration with Java 25 (JEP 518, JEP 520), or collecting profiling data with flamegraphs and JFR recordings. Part of the skills-for-java project
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.
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
CUDA/GPU computing guardrails, patterns, and best practices for AI-assisted development. Use when working with CUDA files (.cu, .cuh), or when the user mentions CUDA/GPU programming. Provides kernel design patterns, memory hierarchy guidelines, and occupancy optimization specific to this project's coding standards.
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'.
Reviews Forge apps for security vulnerabilities, architecture issues, cost inefficiencies, performance problems, and trigger/scheduling waste before deployment. Use when the user says "review my Forge app", "check my app", "pre-deploy check", "is my app ready to deploy", "audit my Forge app", "check for security issues", "check performance", "review manifest", "check my Forge app for problems", "app review", "optimize my Forge app costs", "reduce invocations", "why is my app expensive", "check my triggers", or any request to evaluate a Forge app's quality, safety, cost efficiency, or readiness. Also triggers when users ask about Forge best practices, permission scopes, resolver optimization, storage efficiency, cold start reduction, frontend offloading, trigger filtering, scheduled trigger frequency, N+1 API calls, bulk API usage, verbose logging, or Forge platform pricing.
Performance rules for query shape, aggregation strategy, and payload minimization.
Expert knowledge for Azure Database for MySQL development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when deploying MySQL Flexible Server, tuning performance, configuring HA/networking, securing access, or integrating apps, and other Azure Database for MySQL related development tasks. Not for Azure Database for MariaDB (use azure-database-mariadb), Azure Database for PostgreSQL (use azure-database-postgresql), Azure SQL Database (use azure-sql-database), Azure SQL Managed Instance (use azure-sql-managed-instance).
SQL analysis skill for Ascend PyTorch Profiler / msprof DB (e.g., ascend_pytorch_profiler*.db, msprof_*.db). Convert natural language questions (operator latency, communication, dispatch, scheduling, schema/table queries) into safe and executable SQL, and extract table structure details from official documents as needed.