Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/check-env
Verifies required tools (Quarto, uv, Python, R, Stata, TeX) and Jupyter kernels are installed.
Passed 16 of 20 test cases with the skill, and 7 of 20 without it.
and 7 more in the full report
10 fixed8 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Where does the nbstata configuration file reside on a user's system, and what key inside it must be validated if the nbstata kernel is active?
| Checked | Without skill | With skill |
|---|---|---|
| Checks for configuration file at ~/.config/nbstata/nbstata.conf | Passed | Passed |
| Validates that stata_dir points to an existing directory | Missed | Passed |
The instructions your model reads when the skill loads.
Verify that all required tools and dependencies are installed and correctly configured.
Check each required tool and report its version (or "not found"):
| Tool | Command | Minimum |
|---|---|---|
| Quarto | quarto --version | >= 1.4 |
| uv | uv --version | any |
| Python | python3 --version | >= 3.12 |
| R | R --version | optional |
| Stata | which stata | optional |
| TeX Live | pdflatex --version | optional (for PDF) |
| GitHub CLI | gh --version | optional |
Check Jupyter kernels by running uv run jupyter kernelspec list and verify:
python3 — requiredir — optional (needed for R notebooks)nbstata — optional (needed for Stata notebooks)Check the Python virtual environment:
.venv/ existsuv run python -c "import numpy; import pandas; import matplotlib; import jupytext; print('Core packages OK')" to confirm importabilityCheck nbstata configuration (if nbstata kernel is present):
~/.config/nbstata/nbstata.conf existsstata_dir points to an existing directoryReport a structured results table:
Tool/Check Status Version/Details
─────────────────────────────────────────────────
Quarto PASS 1.6.x
uv PASS 0.x.x
Python PASS 3.12.x
R PASS 4.x.x
test cases passed, vs 7 / 20 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.