Agent skills by ecnu-icalk

ECNU-ICALK/AutoSkill

Guides the user through packaging Python scripts into Windows executables using PyInstaller, with specific focus on using virtual environments, reducing file size via UPX and module exclusion, setting custom icons, and…

ECNU-ICALK/AutoSkill

Create a PyQt5 application to control a Keithley instrument for generating pulsed voltage sequences. The application must accept comma-separated inputs for on/off voltages and durations, execute the sequence via GPIB,…

ECNU-ICALK/AutoSkill

A skill to join user activity and user info CSV datasets using PySpark 1.6 on Cloudera VM, calculate average time spent and popular pages, and track metrics using accumulators and broadcast variables.

ECNU-ICALK/AutoSkill

Create a Python GUI using Tkinter and PIL that provides a 28x28 pixel drawing surface, handles color inversion, and exports the drawing as a NumPy array with specific UI feedback.

ECNU-ICALK/AutoSkill

Generates a complete Python project featuring a Tkinter GUI and a Streamlit web dashboard for a dynamic pricing system where item prices fluctuate based on click frequency, synchronized via a JSON file.

ECNU-ICALK/AutoSkill

Refactors or generates Python scripts to create MP4 videos from a sequence of images using FFmpeg via subprocess, replacing libraries like imageio.

ECNU-ICALK/AutoSkill

Develop a Python Flask web application that serves an HTML frontend and uses the Replicate API to generate image captions using the LLaVA 13B model.

ECNU-ICALK/AutoSkill

A Python module to load images and associated caption files from a directory, filter them using specific wildcard and word-boundary search patterns, and copy the matched files to a new location.

ECNU-ICALK/AutoSkill

Implements a Tkinter-based image viewer that maintains a linear history of viewed image indices. Navigation moves backward through history and forward through history, adding new random images from the remaining pool…

ECNU-ICALK/AutoSkill

Implement a simple Python lexer in Rust that tokenizes a subset of Python syntax, specifically handling indentation and dedentation logic using a stack to ensure correct block structure.

ECNU-ICALK/AutoSkill

Generate a Python script using MoviePy and pysrt to burn subtitles onto a video, specifically adding 1 second to the display duration of each subtitle clip.

ECNU-ICALK/AutoSkill

Generates Python scripts to perform daily ETL updates on MySQL databases, combining insert and update operations using UNION ALL logic and parameterized queries for security.

ECNU-ICALK/AutoSkill

Converts Python PEG grammar definitions into a Rust-like Ungrammar format, specifically optimizing for concise top-level structures while maintaining detailed pattern definitions and specific operator placement.

ECNU-ICALK/AutoSkill

Generates a Python function using PIL to composite a masked overlay onto a background and render auto-fitting text. The text is centered, shadowed, uppercased, uses baseline-based line spacing, and randomly highlights…

ECNU-ICALK/AutoSkill

Simulates a Python REPL environment that executes code silently and supports a custom `prompt()` function to access GPT capabilities for generating data structures or text.

ECNU-ICALK/AutoSkill

Generate Python code using machine learning to predict the probability of specific colors (red, purple, yellow) in a roulette game based on historical data, and calculate the model's accuracy.

ECNU-ICALK/AutoSkill

Implements a Python-based query executor that converts informal keywords to SQL commands, parses queries preserving string literals, and executes operations on pandas DataFrames.

ECNU-ICALK/AutoSkill

Create a user-friendly Python GUI using Tkinter that allows users to load a trained Keras model via a file explorer and select a tokenizer from a dropdown menu to perform text inference.

ECNU-ICALK/AutoSkill

Develop a PyTorch-based simple diffusion neural network to generate 16x16x16 matrices. The implementation must include a custom dataset loader that reads .raw files from a 'dataset/' directory, extracts the text prompt…

ECNU-ICALK/AutoSkill

Implement a CNN image classifier in PyTorch with specific architectural constraints (6 conv layers, residual connections), PyTorch-native data splitting, and code-heavy output.

ECNU-ICALK/AutoSkill

Implements a PyTorch Transformer model with configurable layer dimensions and attention masking, and a training loop that retains the best performing model based on validation loss.

ECNU-ICALK/AutoSkill

Modifies PyTorch data preparation scripts for RNN/LSTM models to limit the dataset size by dividing it into chunks controlled by a hyperparameter, ensuring the first dimension of input/target tensors fits memory…

ECNU-ICALK/AutoSkill

Implements PyTorch functions for hard negative mining and triplet loss calculation using cosine similarity, specifically handling scenarios where anchors have multiple positive samples and requiring mask-based…

ECNU-ICALK/AutoSkill

Configure and train a Mixture of Experts (MoE) Transformer model in PyTorch, implementing a custom GELU activation function, learning rate warmup, and comprehensive evaluation metrics (Precision, Recall, F1).