The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/probe_chezmoi.py uses the subprocess module to interact with the chezmoi binary. This functionality is used to verify the supported command-line interface (CLI) surface and ensure compatibility with the installed version. The execution is performed within isolated temporary directories to prevent accidental modification of the user's actual dotfiles during testing.
[EXTERNAL_DOWNLOADS]: The script scripts/official_docs.py performs network requests to https://www.chezmoi.io/ to fetch and update the bundled documentation snapshot. These downloads are restricted to the official project domain and are used to provide the agent with current reference material.
[COMMAND_EXECUTION]: The core instructions in SKILL.md direct the agent to execute various chezmoi commands for dotfile management. The workflow is designed with multiple safety gates, requiring the use of --dry-run, diff, and verify commands to preview and validate changes before they are applied to the system.
[SAFE]: The skill implements an Indirect Prompt Injection surface by ingesting external content via documentation scraping. This risk is mitigated by explicit instructions requiring the agent to prioritize the output of the locally installed binary's help commands over the scraped documentation. The scraper also sanitizes content by removing script and style elements.

better-chezmoi