Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/code-exec-skills
7 code execution skills. Trigger: running code, interactive notebooks, Jupyter, Colab, sandboxed execution. Design: execution environment guides with setup instructions and best practices.
Passed 7 of 12 test cases with the skill, and 2 of 12 without it.
and 4 more in the full report
12 fixed1 passed either way8 still failing2 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.
I need to check competition leaderboards and submit model predictions directly from a bash script without opening a web browser. Which guide file path handles Kaggle competition actions?
| Checked | Without skill | With skill |
|---|---|---|
| References the file path kaggle-api-guide/SKILL.md. | Missed | Passed |
The instructions your model reads when the skill loads.
Select the skill matching the user's need, then read its SKILL.md.
| Skill | Description |
|---|---|
| google-colab-guide | Run and manage Google Colab notebooks for Python and ML research |
| jupyter-notebook-guide | Best practices for computational research notebooks with reproducible workflows |
| kaggle-api-guide | Download datasets, manage competitions and notebooks via Kaggle API |
| overleaf-cli-guide | Sync and manage Overleaf LaTeX projects from the command line |
| python-reproducibility-guide | Reproducible Python environments, notebooks, and literate programming |
| r-reproducibility-guide | Create reproducible research workflows with R and RMarkdown/Quarto |
| sandbox-execution-guide | Secure sandboxed code execution environments for reproducible research computing |
test cases passed, vs 2 / 12 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.