菜单
How to use uv and Python packaging commands in this environment, including when to use run-in-nw-sandbox for index access and how to run offline installs from `/home/user/pip-cache` with `--no-index --find-links`.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Use when working with source control for a project within /home/user/workspace/code or code-agent.
Turn a recent human-agent interaction into a portable workflow description.
Work through a proposal by starting a tracked /goal, reading the proposal, breaking it into milestone-sized tasks, and delegating each implementation milestone to fresh subagents instead of implementing directly in the main agent. Use when the user wants proposal-driven execution with explicit progress tracking and milestone-by-milestone delegation.
Draft new proposal documents for a codebase in the local proposal style. Use when the user wants a new proposal written before implementation, or wants an idea turned into a structured design/proposal document with motivation, problem statement, proposal, non-goals, verification, and success criteria.
Manage npm package dependencies in this environment. Use when adding or updating npm packages, editing package.json/package-lock.json, or when network access must be constrained to `run-in-nw-sandbox -- npm install --no-scripts [--save | --save-dev] -- package-spec ...` followed by `npm rebuild` outside the sandbox.
How to use the run-in-nw-sandbox helper to run commands with network access
| name | uv-pip-offline-download |
| description | How to use uv and Python packaging commands in this environment, including when to use run-in-nw-sandbox for index access and how to run offline installs from `/home/user/pip-cache` with `--no-index --find-links`. |
Use these commands to create an offline cache and install from it.
For requirements file input:
run-in-nw-sandbox -- uv run --python /usr/bin/python3 pip download -r requirements.txt -d /home/user/pip-cache
For explicit package specs:
run-in-nw-sandbox -- uv run --python /usr/bin/python3 pip download pandas==2.0.3 -d /home/user/pip-cache
For multiple packages, place all specs before -d:
run-in-nw-sandbox -- uv run --python /usr/bin/python3 pip download pandas==2.0.3 numpy==1.26.4 -d /home/user/pip-cache
Use --no-index to block index access and --find-links to point pip to the local cache:
uv pip install --no-index --find-links /home/user/pip-cache -r requirements.txt
Or install direct specs from cache:
uv pip install --no-index --find-links /home/user/pip-cache pandas==2.0.3
For project dependency workflows, pass offline index flags directly:
uv add --no-index --find-links /home/user/pip-cache pandas==2.0.3
uv sync --no-index --find-links /home/user/pip-cache
List downloaded artifacts:
ls -1 /home/user/pip-cache
Optionally test network-isolated install by repeating install commands with --no-index --find-links only.
--python /usr/bin/python3 for uv run pip download to match command policy exactly.-d /home/user/pip-cache for downloads; policy requires this cache location.run-in-nw-sandbox -- for download commands that access package indexes.uv run pip download for downloading (download is not available via uv pip).--no-index --find-links for uv pip install, uv add, and uv sync, and run them without the network wrapper.