Browse All Agent Skills
Explore our collection of Agent Skills to enhance your AI workflow.
Distribution Search
Finds probability distributions that satisfy specific statistical constraints like KL divergence targets through mathematical analysis and optimized parameterization.
SQLite with gcov Coverage
Configures and troubleshoots C/C++ projects with gcov instrumentation to ensure accurate code coverage data generation and analysis.
OCaml GC Debugging
Diagnoses and resolves low-level memory management bugs in the OCaml garbage collector runtime, specifically targeting segmentation faults and pointer arithmetic errors.
Cancel Async Tasks
Implements robust Python asyncio task cancellation and signal handling patterns to ensure graceful shutdowns and proper resource cleanup.
COBOL Modernization
Translates legacy COBOL programs into modern programming languages while ensuring functional equivalence and byte-level output compatibility.
Fix Code Vulnerability
Identifies, analyzes, and patches security flaws and CWE-classified vulnerabilities using a systematic workflow and thorough test-driven verification.
ReLU Model Extraction
Extracts internal weight matrices and biases from black-box ReLU neural networks using input-output query strategies and functional equivalence testing.
Raman Fitting
Provides specialized guidance and implementation patterns for analyzing and curve-fitting peaks in Raman spectroscopy data.
HTML JavaScript & XSS Filter
Removes JavaScript and XSS attack vectors from HTML documents while maintaining the original file formatting and structure.
Financial Document Processor
Extracts structured data from financial documents using OCR and text extraction while enforcing rigorous data safety and verification protocols.
PyTorch Model Recovery
Reconstructs PyTorch model architectures from saved state dictionaries, enables selective layer fine-tuning, and facilitates TorchScript conversion for deployment.
Headless Terminal
Implements programmatic terminal interfaces to control shell sessions through terminal emulation and pseudo-terminal wrappers.
SAM Cell Segmentation
Implements SAM-based biological image segmentation pipelines, converting binary masks to polygon coordinates for microscopy data processing.
DNA Insert Primer Design
Designs specialized primers for inserting DNA sequences into circular plasmids using Q5 site-directed mutagenesis and inverse PCR techniques.
Protein Assembly
Designs optimized DNA gBlock sequences for fusion proteins by combining sequences from multiple databases with precise linker and codon constraints.
Torch Pipeline Parallelism
Implements PyTorch pipeline parallelism to distribute large language model training across multiple GPUs using All-Forward-All-Backward (AFAB) scheduling.
Protein Assembly
Designs and optimizes multi-component fusion protein sequences for FRET biosensors and gene synthesis.
Modernize Scientific Stack
Upgrades legacy Python 2 scientific computing code and analysis pipelines to modern Python 3 standards using contemporary libraries like NumPy and pandas.
MTEB Retrieval and Ranking
Optimizes semantic similarity retrieval tasks through expert guidance on document preprocessing, embedding model selection, and similarity ranking.
PyTorch Model Recovery
Reconstructs PyTorch model architectures from weight files and state dictionaries by analyzing tensor shapes and naming patterns.
Headless Terminal
Implements programmatic terminal interfaces to control interactive shell sessions and automate command-line program interactions.
Raman Spectroscopy Peak Fitting
Analyzes and fits peaks in Raman spectroscopy data using physically-constrained models like Lorentzian, Gaussian, and Voigt functions.
SQLite Truncated Database Recovery
Recovers data from corrupted or truncated SQLite database files through manual binary analysis and custom parsing when standard tools fail.
Path Tracing Reverse Engineering
Reconstructs source code from compiled binaries with a focus on achieving byte-for-byte identical output and exact functional parity.
Data Resharding and Partitioning
Reorganizes large-scale datasets into hierarchical directory structures while enforcing strict file size and item count constraints.
Chess Best Move
Analyzes chess board images to detect piece positions, validate board legality, and determine optimal moves using computer vision and engine analysis.
Git Repository Sanitization
Identifies and removes sensitive credentials, API keys, and private tokens from git repositories and version control history.
Modernize Scientific Stack
Migrates legacy Python 2 scientific computing code to Python 3 using modern libraries like pandas, numpy, and pathlib.
LLM Inference Batching Scheduler
Optimizes LLM inference request grouping and scheduling to minimize operational costs while satisfying latency and padding constraints.
LaTeX Overfull Hbox Fixer
Fixes LaTeX overfull hbox warnings by strategically replacing words with shorter synonyms from a restricted, predefined vocabulary.
Scroll for more results...