The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses various shell commands including wt, git, find, and cargo to manage tool configuration and perform validation tasks.
[COMMAND_EXECUTION]: Instructions include executing a local installer script (~/dotfiles/install.sh) and running tests via cargo, which are standard for development and setup of the 'wt' environment.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it reads and acts upon data from untrusted files within a repository (e.g., README.md, .wt.toml) to determine configuration changes.
Ingestion points: Reads from repository files such as README.md, docs/consistency.md, .wt.toml, config.toml, and profile.toml.
Boundary markers: No specific delimiters or instructions to ignore embedded commands in these external files are present.
Capability inventory: The skill can execute shell commands (wt, git, cargo) and modify configuration files based on the processed data.
Sanitization: No sanitization or integrity checks for the content of external files are mentioned.

wt-setup