Search Skills

Provides core PyTorch fundamentals including tensor operations, autograd, model architecture, and training loop implementation.

Converts C/C++ build and test scripts to support incremental builds, ensuring idempotency and compatibility with out-of-tree builds and Docker workflows.

Prevents XSS and injection attacks by sanitizing and validating user input in TypeScript applications.

Generates, optimizes, and explains regex patterns for text matching, input validation, and CLI command parsing.

Enables building, training, and optimizing deep learning models with PyTorch, including data pipelines and distributed training.

Executes Python scripts and manages dependencies via uv, replacing pip for faster, reliable package handling in development workflows.

Optimizes machine learning model inference performance via compression, distillation, and edge deployment strategies.

Automates video downloads and AI-powered transcription from 1000+ platforms, supporting quality selection and playlist processing.

Provides efficient linear algebra operations in NumPy, including matrix multiplication, SVD, and least squares fitting for data science and AI applications.

Transforms and exports data using DuckDB SQL, supporting multiple formats and complex operations like joins and aggregations for efficient data processing.

Enforces C development standards with GCC, Valgrind, and static analysis for code quality and build management.

High-performance tokenization for NLP research and production, supporting BPE, WordPiece, and Unigram algorithms with Hugging Face Transformers integration.

Provides UTF-8 JSON file I/O utilities to prevent Windows encoding issues (CP-1252 vs UTF-8).

Provides numerical algorithms and computational techniques specifically for statistical analysis and data processing tasks.

Debugs memory-related issues in the Breenix kernel including page faults, heap allocation, and virtual memory mapping errors.

Generates unit test code for functions and methods, ensuring test coverage and correctness in software development workflows.

Scans codebases for exposed secrets like API keys, tokens, and passwords to prevent security breaches before committing changes.

Scans Python code for security vulnerabilities, maps to CWE/OWASP, and provides remediation guidance for CI/CD pipelines.

Provides foundational knowledge for writing Stan 2.37 statistical models, covering structure, type system, distributions, and best practices.

Guides configuration and startup of QEMU virtual machines with serial console access, ISO booting, and troubleshooting procedures.

Expert guidance on PKI and X.509 certificate management including structure, CSR generation, signing, revocation, and OpenSSL commands for secure cryptographic operations.

Creates standalone CLI tools for PyTorch model inference by reimplementing neural network forward passes in C/C++ and extracting model weights to portable formats.

High-performance CLI for splitting, merging, and analyzing SQL dump files across databases, with integrity validation, ERD generation, and DuckDB analytics.

Guides construction of complex regex patterns for extracting and validating data from log files, including IP addresses, dates, and boundary conditions.