Loading...
Loading...
Found 44 Skills
Patterns for efficient ML data pipelines using Polars, Arrow, and ClickHouse. TRIGGERS - data pipeline, polars vs pandas, arrow format, clickhouse ml, efficient loading, zero-copy, memory optimization.
Python performance optimization patterns using profiling, algorithmic improvements, and acceleration techniques. Use when optimizing slow Python code, reducing memory usage, or improving application throughput and latency.
Memory-efficient fine-tuning with 4-bit quantization and LoRA adapters. Use when fine-tuning large models (7B+) on consumer GPUs, when VRAM is limited, or when standard LoRA still exceeds memory. Builds on the lora skill.
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
Titanium SDK official fundamentals and configuration guide. Use when working with, reviewing, analyzing, or examining Titanium projects, Hyperloop native access, app distribution (App Store/Google Play), tiapp.xml configuration, CLI commands, memory management, bridge optimization, CommonJS modules, SQLite transactions, or coding standards. Applies to both Alloy and Classic projects.
Expert knowledge of Godot performance optimization, profiling, bottleneck identification, and optimization techniques. Use when helping improve game performance or analyzing performance issues.
Analyze code performance, detect bottlenecks, suggest optimizations for algorithms, queries, and resource usage. Use when improving application performance or investigating slow code.
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.
Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not for CPU/GPU frequency tuning.
Design memory hierarchy with progressive loading for optimal context management. Use when organizing CLAUDE.md imports, implementing just-in-time context loading, or designing priming hierarchies for agents.
Troubleshoot and optimize the performance of Ascend C operators. This skill is applicable when users develop, review or optimize Ascend C kernel operators, or triggered when users mention keywords such as Ascend C performance optimization, operator optimization, tiling, pipeline, data copy, memory optimization, NPU/Ascend.
Expert skill for AI model quantization and optimization. Covers 4-bit/8-bit quantization, GGUF conversion, memory optimization, and quality-performance tradeoffs for deploying LLMs in resource-constrained JARVIS environments.