Browse reusable instructions for your AI tools. Copy and customize a prompt, or download a skill for a supported agent.
Reduce feature dimensionality using PCA, t-SNE, and feature selection for feature reduction, visualization, and computational efficiency
Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.
Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.
実装内容が数学的・物理学的に妥当か検証する
Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.
Python development principles and decision-making.
Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.
Calculates the number of disorder pairs (inversions) in a list where i < j and pi > pj, optimized for large datasets.
Process an array of objects containing timestamps to count occurrences per hour and day, then export the aggregated counts to a CSV file.
Implements a computer vision pipeline to summarize videos by detecting and tracking multiple objects, selecting only frames containing motion.
Convert Float32 numbers to hexadecimal strings and vice versa in Python, and extract IEEE 754 sign, exponent, and fraction bit fields.
Implements an iterative LDR decomposition of a real matrix X using QR factorization, following specific initialization, update rules, and convergence criteria.
Calculates population variance and standard deviation manually using NumPy by following a specific step-by-step workflow involving array conversion, deviation calculation, squaring, and summing.
Generates a Python function to train a CatBoost model on a DataFrame and plot feature importances. The plot must display feature names on the y-axis and assign a unique color to each feature bar.
Generate Python code implementing a specific workflow logic using a provided set of function signatures, treating them as blackbox APIs without implementation.
Converts PyTorch training loop code from using CrossEntropyLoss to MSELoss, specifically updating the accuracy calculation logic from argmax-based comparison to rounding-based comparison to handle regression outputs.
Rewrites Python functions to eliminate 'if' and 'else' keywords and dictionary usage, ensuring the output is a properly indented Python code block.
Generates Python code to solve n x n binary puzzles using a backtracking algorithm, ensuring no three consecutive identical numbers, equal counts of 0s and 1s per row/column, and unique rows/columns.
Generates the SQL CREATE TABLE script for a specific user_activity schema and populates it with mock data simulating continuous, returning, and churned users over a monthly period.
Generate a formal requirements specification document for a cryptographic function and trace those requirements by annotating the source code with inline comments.
Optimizes memory consumption during PyTorch model training by implementing mixed precision training, gradient accumulation, and efficient data loading strategies to fit within hardware constraints.
Implements a robust panorama stitching pipeline using NumPy for geometric transformations (RANSAC, DLT, Warping) while comparing SIFT, SURF, and ORB features. Enforces reference-to-target matching and generates visualization/performance metrics.
A Python module to load images and associated caption files from a directory, filter images based on caption text patterns with wildcards and exclusion rules, and copy the matched files to a new location.
Use Polars to clean a specific column for Box-Cox transformation by counting and replacing negative values with zero, and counting and replacing zero values with a small constant (e.g., 0.01).
Try another platform, a broader search, or fewer filters.
Explore all resourcesResource formats: Prompts are ready to copy into a conversation. Skills install into the compatible agent shown on their page.
How it worksInclude the instructions, intended platforms, author, and license. Submissions are reviewed before publication.