The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple shell commands to manage Git worktrees and set up project environments.
It constructs commands using variables like $BRANCH_NAME and $LOCATION which are derived from repository metadata or user input.
It automatically runs environment-specific setup commands (npm install, cargo build, pip install, poetry install, go mod download) and test runners (npm test, cargo test, pytest, go test).
[EXTERNAL_DOWNLOADS]: The skill automates the download and installation of external dependencies through standard package managers when project-specific configuration files are detected.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via malicious repository content.
Ingestion points: The agent reads and reacts to files present in the repository, including package.json, Cargo.toml, requirements.txt, pyproject.toml, and go.mod, as well as branch names.
Boundary markers: None are specified to prevent the agent from interpreting instructions embedded in these files.
Capability inventory: The skill has the ability to execute shell commands, install software packages, and run arbitrary test code provided by the repository.
Sanitization: There is no evidence of sanitizing the content of project files or branch names before they are used in shell command interpolation.

using-git-worktrees