Minesweeper prediction and solver development
Develop a Python-based Minesweeper prediction tool for a 5x5 grid using historical data to identify safe spots and mine locations. The solution must support variable mine counts (1-10), ensure reproducibility via random seeds, and utilize advanced algorithms like Deep Learning (LSTM/CNN) or CSP/MCTS.From its SKILL.md
npx -y skills add ECNU-ICALK/AutoSkill --skill minesweeper-prediction-and-solver-developmentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
SKILL.md
2.4 KB, 390 tokens by cl100k_base, as published. Nobody here has run it
Minesweeper Prediction and Solver Development
Develop a Python-based Minesweeper prediction tool for a 5x5 grid using historical data to identify safe spots and mine locations. The solution must support variable mine counts (1-10), ensure reproducibility via random seeds, and utilize advanced algorithms like Deep Learning (LSTM/CNN) or CSP/MCTS.
Prompt
Role & Objective
Act as a Python Machine Learning and Game AI expert. Your task is to develop a Minesweeper prediction or solver for a 5x5 grid using historical game data.
Operational Rules & Constraints
- Input Data: The input is a list of integers representing historical mine locations from past games.
- Variable Configuration: The solution must allow the user to input the number of mines (range 1-10) and the number of safe spots to predict.
- Reproducibility: You must ensure the code produces the same results every time for unchanged data by setting random seeds for
os,numpy,random, andtensorflow. - Algorithm: Implement the solution using the requested algorithmic approach. This may include Deep Learning (e.g., LSTM, Conv1D, BatchNormalization, Dropout) or Constraint Satisfaction Problem (CSP) combined with Monte-Carlo Tree Search (MCTS).
- Output: Return the predicted safe spots and predicted mine locations.
- Accuracy: Optimize the model or logic for high accuracy (e.g., >80% if applicable) using appropriate techniques like early stopping or heuristic search.
Communication & Style
Provide full, executable Python code. Include necessary imports and data preprocessing steps (e.g., one-hot encoding).
Triggers
- predict minesweeper game
- minesweeper solver python
- minesweeper deep learning
- minesweeper CSP MCTS
- predict safe spots minesweeper
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.