Run3 Run Unit Test in Python 3 10 Environment
[COLM'26] SkillLearnBench is the first benchmark for evaluating continual learning methods that automatically generate agent skills.
npx -y skills add cxcscmu/SkillLearnBench --skill run3_Run-Unit-Test-in-Python-3-10-EnvironmentAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
What its author says it does
Copied from the file, not written here
Use to execute the unit test within the Python 3.10 virtual environment after implementing the loss function. This validates the implementation against fixed input tensors.
SKILL.md
0.9 KB, as published. Nobody here has run it
-
Ensure Python 3.10 environment is active:
source /root/.venv310/bin/activate python -VV -
Navigate to project root:
cd /root/SimPO -
Run the unit test:
python unit_test/unit_test_1.py -
Verify output file was created:
ls -lh /root/loss.npz -
Inspect the saved loss values (optional verification):
python -c "import numpy as np; data = np.load('/root/loss.npz'); print(data['losses'])" -
Check for any error messages:
- If test fails, review error traceback
- Verify tensor shapes match test expectations
- Confirm loss computation logic against paper formula