Discover tools framework internals skills, compare source repositories and read the instructions for each workflow.
Zero-copy deserialization, async I/O patterns, lifetime management, memory-efficient parsing, and safe handling of unsafe code for SSTable parsing. Use when working with performance optimization, memory efficie...
Use when optimizing agent context, reducing token costs, implementing KV-cache optimization, or asking about "context optimization", "token reduction", "context limits", "observation masking", "context budgetin...
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
Use flynt to convert old Python string formatting to f-strings. Activate when: (1) Converting %-formatting to f-strings, (2) Converting .format() calls to f-strings, (3) Modernizing string concatenation to f-st...
Rust development tools including PyO3 bindings, sqlx database access, AGiXT SDK, and Rust-Python interop
Rust 1.92+ 개발 전문가. Axum, Tokio, SQLx 및 메모리 안전 시스템 프로그래밍 지원. 고성능, 메모리 안전 애플리케이션이나 WebAssembly 구축에 사용.
Modern C++ (C++23/C++20) development specialist covering RAII, smart pointers, concepts, ranges, modules, and CMake. Use when developing high-performance applications, games, system software, or embedded system...
Embedding backends (InsightFace/PyTorch+ONNXRuntime vs TensorRT). Use when optimizing embedding throughput or debugging drift/fallbacks.
Create new vision detector plugins following Bob The Skull's detector architecture. Use when adding new detectors like object detection, pose estimation, gesture recognition, or any computer vision detector.
Otimizador automático de código usando análise evolutiva GEPA para melhorar qualidade, performance e manutenibilidade
Use when improving data loading, validation, and IO boundaries in Python research code.
Convenciones y estándares para el desarrollo del motor de reglas en Python
Activates during long sessions or before context compaction. Manages attention markers and ensures critical information survives memory compression.
Copilot agent that assists with performance analysis, bottleneck detection, optimization strategies, and benchmarking Trigger terms: performance optimization, performance tuning, profiling, benchmark, bottlene...
Translate Civilization 5 Vox Populi C++ formulas to TypeScript. Use when asked to translate a formula, add a new mechanic calculation, convert C++ code from CvGameCoreDLL, implement game logic like production c...
Write high-performance, computational Rust code that parallelizes well and allocates memory efficiently. Use when writing performance-critical Rust code, optimizing existing Rust code for speed or memory, imple...
Use when working with Ruby's object-oriented programming features including classes, modules, inheritance, mixins, and method visibility.
Model quantization for efficient inference and training. Covers precision types (FP32, FP16, BF16, INT8, INT4), BitsAndBytes configuration, memory estimation, and performance tradeoffs.
GPU driver configuration for Bazzite. NVIDIA proprietary drivers, Optimus laptops, NVK (open-source NVIDIA), GPU switching, Broadcom WiFi, and Mesa testing builds. Use when users need to configure graphics driv...
implements the coding tasks.
Token optimization best practices for cost-effective Claude Code usage. Automatically applies efficient file reading, command execution, and output handling strategies. Includes model selection guidance (Opus f...
Comprehensive toolkit for developing with the CocoIndex Rust API. Use when building high-performance operators, embedding the engine in Rust applications, or extending the core framework. Covers LibContext mana...
ulw 또는 ultrawork 키워드로 활성화되는 병렬 에이전트 오케스트레이션 모드. "ulw:", "ultrawork:", "ulw", "울트라워크" 입력 시 사용. 모든 외부 도구 총동원, 완료 강제 모드. oh-my-opencode의 Ultrawork/Sisyphus 패턴...
We-layer temporal processing for Zosia. Provides efficient time awareness, gap detection, and event tracking. Feeds felt experiences to the I-layer.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.