Loading...
Loading...
Found 23 Skills
Efficient AI techniques including model compression, quantization, pruning, knowledge distillation, and hardware-aware optimization for production systems.
Use when reducing model size, improving inference speed, or deploying to edge devices - covers quantization, pruning, knowledge distillation, ONNX export, and TensorRT optimizationUse when ", " mentioned.
Optimizes Snowflake query performance using query ID from history. Use when optimizing Snowflake queries for: (1) User provides a Snowflake query_id (UUID format) to analyze or optimize (2) Task mentions "slow query", "optimize", "query history", or "query profile" with a query ID (3) Analyzing query performance metrics - bytes scanned, spillage, partition pruning (4) User references a previously run query that needs optimization Fetches query profile, identifies bottlenecks, returns optimized SQL with expected improvements.
Use when creating, rewriting, pruning, or reviewing `AGENTS.md` or `CLAUDE.md`, especially to remove repo summaries, stale rules, and other low-signal global instructions. Trigger when deciding what belongs in always-on agent files versus a task-specific skill.
Native Arrow filesystem integration with PyArrow. Optimized for Parquet workflows, zero-copy data transfer, predicate pushdown, and column pruning. Covers S3, GCS, HDFS with PyArrow datasets.
Use this skill when managing persistent user memory in ~/.memory/ - a structured, hierarchical second brain for AI agents. Triggers on conversation start (auto-load relevant memories by matching context against tags), "remember this", "what do you know about X", "update my memory", completing complex tasks (auto-propose saving learnings), onboarding a new user, searching past learnings, or maintaining the memory graph - splitting large files, pruning stale entries, and updating cross-references.
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with multi-agent evaluation
Use when integrating Foundation Models framework, implementing on-device AI with Apple Intelligence, building tool-calling AI features, working with guided generation schemas, converting models with Core ML and coremltools, or running open-source LLMs on Apple Silicon. Covers Foundation Models (LanguageModelSession, @Generable, @Guide, SystemLanguageModel, structured output, tool calling), Core ML (coremltools, model conversion, quantization, palettization, pruning, Neural Engine, MLTensor), MLX Swift (transformer inference, unified memory), and llama.cpp (GGUF, cross-platform LLM).
Interactive macOS system cleanup for any dev machine. Frees disk space by pruning caches, package managers, unused apps, stale dev artifacts, and more. Discovers what's installed rather than assuming a specific setup. Always consults the user before deleting anything. Use when the user asks to: clean up their Mac, free disk space, remove unused apps, prune caches, clean developer artifacts, or any disk space maintenance task.
PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then applies 2D detection — used in autonomous driving and robotics. Use when training, evaluating, exporting, pruning, retraining, or running inference for a TAO PointPillars model. Trigger phrases include "train PointPillars", "LiDAR 3D detection", "point-cloud object detection", "pillar-based 3D detector".
Switches NixOS/Home Manager configurations, cleans old generations, and performs system maintenance. Use when running os/home switch, pruning the Nix store, or managing system generations.