性能
性能分析与优化
bash-53-features
Jamie-BitFlight
Bash 5.3 release features and improvements with practical examples. Use when working with Bash 5.3 features, new command substitution, GLOBSORT, loadable builtins, or when user asks about Bash 5.3 changes, new features, or version-specific capabilities.
bash-52-features
Jamie-BitFlight
Bash 5.2 release features and improvements with practical examples. Use when working with Bash 5.2 features, variable handling enhancements, readline improvements, or when user asks about Bash 5.2 changes, new features, or version-specific capabilities.
ChartXR: 3D Dependency Visualization Skill
mmongan
MeshBuilder API: https://doc.babylonjs.com/features/featuresDeepDive/Meshes/Mesh/CreateMesh_Details
analyzing-bootkit-and-rootkit-samples
mukul975
Analyzes bootkit and advanced rootkit malware that infects the Master Boot Record (MBR), Volume Boot Record (VBR), or UEFI firmware to gain persistence below the operating system. Covers boot sector analysis, UEFI module inspection, and anti-rootkit detection techniques. Activates for requests involving bootkit analysis, MBR malware investigation, UEFI persistence analysis, or pre-OS malware detection.
analyzing-linux-kernel-rootkits
mukul975
Detect kernel-level rootkits in Linux memory dumps using Volatility3 linux plugins (check_syscall, lsmod, hidden_modules),
get-available-resources
K-Dense-AI
This skill should be used at the start of any computationally intensive scientific task to detect and report available system resources (CPU cores, GPUs, memory, disk space). It creates a JSON file with resource information and strategic recommendations that inform computational approach decisions such as whether to use parallel processing (joblib, multiprocessing), out-of-core computing (Dask, Zarr), GPU acceleration (PyTorch, JAX), or memory-efficient strategies. Use this skill before running analyses, training models, processing large datasets, or any task where resource constraints matter.
cirq
K-Dense-AI
Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.
cobrapy
K-Dense-AI
Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.
dask
K-Dense-AI
Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.
Scaffold Exercises
mattpocock
```
avoid-ai-writing
brycewang-stanford
Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detection-only mode that flags patterns without rewriting.
cpp-to-dafny-translator
ArabelaTso
Translate C/C++ programs to equivalent Dafny code while preserving semantics and ensuring verification. Use when users ask to convert, translate, or port C/C++ code to Dafny, or when they need to formally verify C/C++ algorithms using Dafny's verification capabilities. Handles functions, structs, pointers, arrays, memory management, and ensures the generated Dafny code is well-typed, executable, verifiable, and can successfully run.
acsl-annotation-assistant
ArabelaTso
Create ACSL (ANSI/ISO C Specification Language) formal annotations for C/C++ programs. Use this skill when working with formal verification, adding function contracts (requires/ensures), loop invariants, assertions, memory safety annotations, or any ACSL specifications. Supports Frama-C verification and generates comprehensive formal specifications for C/C++ code.
code-translation
ArabelaTso
"Convert code between programming languages while preserving functionality and semantics. Use when: (1) Translating functions, classes, or modules between languages (Python, JavaScript/TypeScript, Java, Go, Rust, C/C++), (2) Migrating entire projects to a different language, (3) Need idiomatic translation that follows target language conventions, (4) Converting between different paradigms (OOP to functional, etc.), (5) Porting legacy code to modern languages. Provides language-specific patterns, idiomatic translation guides, and project migration strategies."
code-optimizer
ArabelaTso
Analyzes and optimizes code for better performance, memory usage, and efficiency. Use when code is slow, memory-intensive, or inefficient. Supports Python and Java optimization including execution speed improvements, memory reduction, database query optimization, and I/O efficiency. Provides before/after examples with detailed explanations of why optimizations work, complexity analysis, and measurable performance improvements.
c-cpp-to-lean4-translator
ArabelaTso
Translate C or C++ programs into equivalent Lean4 code, preserving program semantics and ensuring the generated code is well-typed, executable, and can run successfully. Use when the user asks to convert C/C++ code to Lean4, port C/C++ programs to Lean4, translate imperative code to functional Lean4, or create Lean4 versions of C/C++ algorithms.
fpf:decay
NeoLabHQ
"Manage evidence freshness by identifying stale decisions and providing governance actions"
reflexion:memorize
NeoLabHQ
Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering
reflexion:reflect
NeoLabHQ
Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification
huggingface-tokenizers
NousResearch
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
peft-fine-tuning
NousResearch
Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.
huggingface-tokenizers
NousResearch
Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.
optimizing-attention-flash
NousResearch
Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.
llama-cpp
NousResearch
Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.