The Agent Skills Directory

[SAFE]: The skill implements logic to manage Git worktrees and automate local environment setup without any detected malicious patterns or obfuscation.
[COMMAND_EXECUTION]: Shell commands are used to create worktrees, navigate directories, and run project tests. These commands are standard for development workflows and are used as intended within the skill's scope.
[EXTERNAL_DOWNLOADS]: The skill triggers standard package managers (npm, pip, cargo, go) to install dependencies if manifest files are present. These operations target official package registries.
[PROMPT_INJECTION]: The skill has an indirect injection surface as it reads configuration from CLAUDE.md and executes tests defined in the repository.
Ingestion points: Reads directory preferences from CLAUDE.md and uses repository-provided manifest files (SKILL.md).
Boundary markers: None present for data read from CLAUDE.md or manifest files.
Capability inventory: Execution of npm install/test, pip install, cargo build/test, go mod/test, and git worktree (SKILL.md).
Sanitization: Uses basename for project naming but lacks specific content sanitization for external data inputs.

using-git-worktrees