Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/run-experiment
Deploy and run ML experiments on local or remote GPU servers.
Passed 17 of 20 test cases with the skill, and 8 of 20 without it.
and 9 more in the full report
11 fixed9 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
GPU 0 has 2000 MiB used, GPU 1 has 120 MiB used, and GPU 2 has 800 MiB used. I need to launch `python train.py`. Which GPU should be assigned, and why?
| Checked | Without skill | With skill |
|---|---|---|
| Selects GPU 1 for the experiment execution | Passed | Passed |
| Rejects GPU 0 because its memory usage exceeds 500 MiB | Missed | Passed |
The instructions your model reads when the skill loads.
Deploy and run ML experiment: $ARGUMENTS
Read the project's AGENTS.md to determine the experiment environment:
If no server info is found in AGENTS.md, ask the user.
Check GPU availability on the target machine:
Remote:
ssh <server> nvidia-smi --query-gpu=index,memory.used,memory.total --format=csv,noheader
Local:
nvidia-smi --query-gpu=index,memory.used,memory.total --format=csv,noheader
# or for Mac MPS:
python -c "import torch; print('MPS available:', torch.backends.mps.is_available())"
Free GPU = memory.used < 500 MiB.
Check the project's AGENTS.md for a code_sync setting. If not specified, default to rsync.
Only sync necessary files — NOT data, checkpoints, or large files:
test cases passed, vs 8 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.