Experiment Code
lingzhi227/agent-research-skillsRunning machine learning experiments for a research paper can be tricky. You need to write code that trains models, logs results, and creates graphs. This skill helps you do all that step by step.
You can generate new experiment code from a plan or idea. You can improve existing code by reviewing results and making small changes. You can debug errors with up to four tries. And you can plot publication-quality figures from saved results.
The code uses popular libraries like PyTorch or scikit-learn. It saves each run in its own folder with logs and figures. This makes your experiments clear and reproducible.
Add Experiment Code skill to your workflow
Global
mkdir -p ~/.claude/skills/experiment-codeProject
mkdir -p .claude/skills/experiment-codeSource Repository
More Data Science & ML Claude Code Skills
Explore Runlllllllama/rigorpilot-skills
Plan and rank quick deep learning exploration runs with clear boundaries
Run Trainlllllllama/rigorpilot-skills
Run deep learning training conservatively with structured logs and metrics
Env And Assets Bootstraplllllllama/rigorpilot-skills
Safe and careful setup of conda environments and asset paths for deep learning reproduction
Env And Assets Bootstraplllllllama/ai-paper-reproduction-skill
Prepare conda-first environment and asset paths for deep learning reproduction
Data Visualizationanthropics/knowledge-work-plugins
Pick the right chart, write clean Python code, and design for everyone
Powerbi Modelinggithub/awesome-copilot
Expert guidance for building optimized Power BI semantic models with star schemas and DAX
Power Bi Dax Optimizationgithub/awesome-copilot
Make your Power BI DAX formulas faster and easier to maintain
Bigquery Basicsgoogle/skills
Easily analyze massive datasets with SQL and built-in machine learning