Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →xuzhougeng/pixi-environment-builder
Use when creating, migrating, or debugging pixi environments, especially for scientific Python, bioinformatics, single-cell analysis, CUDA/PyTorch, Jupyter/VS Code kernels, conda-to-pixi migration, or conda + PyPI mixed dependency issues.
Passed 19 of 21 test cases with the skill, and 14 of 21 without it.
and 5 more in the full report
6 fixed15 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
When running environment installation on a restricted build node, downloading PyPI metadata timed out mid-operation. Changing the index URL alone did not solve the issue because old corrupted index metadata remained cached. What exact command clears the PyPI solver cache before retrying `pixi install`?
| Checked | Without skill | With skill |
|---|---|---|
| Executes pixi clean cache --pypi to clear stale PyPI solver metadata | Passed | Passed |
| Re-runs installation across all configured workspace environments using the all flag | Missed | Passed |
The instructions your model reads when the skill loads.
Use this skill to design, migrate, and debug pixi-managed environments. The core principle is to clarify environment intent before editing pixi.toml: version constraints, project scope, package source priority, mirror/network policy, special packages, cache location, and validation tasks.
Pixi can solve dependencies automatically, but mixed conda + PyPI environments need deliberate package ownership. Most hard failures come from unclear ownership, unconstrained top-level packages, inaccessible mirrors, or non-registry packages.
Before creating or changing a pixi environment, ask these questions unless the answer is already known from repo files, user context, or error logs:
Required versions
python, cuda, pytorch, domain packages, model libraries, analysis frameworks.Environment scope
pixi.toml.pixi global for reusable CLI tools, not complex project workflows.Package source priority
Multiple environments or kernels
Mirror and network policy
pypi.org, files.pythonhosted.org, prefix.dev, or internal mirrors?Non-registry packages
Cache and storage
test cases passed, vs 14 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.