The Agent Skills Directory

[COMMAND_EXECUTION]: The skill enables the agent to execute shell commands and scripts defined in project configuration files (mise.toml) or the mise-tasks/ directory using the mise run and mise x commands. This is the core functionality of the tool.
[REMOTE_CODE_EXECUTION]: Reference materials document the ability to define and execute tasks from remote sources, such as shell scripts hosted on external URLs or within Git repositories (e.g., https://example.com/build.sh).
[EXTERNAL_DOWNLOADS]: The skill describes tool installation workflows that fetch binaries and packages from well-known registries and services, including GitHub Releases, npm, PyPI (via pipx), and Cargo.
[SAFE]: The documentation emphasizes security best practices by describing the 'mise trust' mechanism, which requires explicit user approval before mise will execute hooks or tasks from a project configuration file. It also highlights secret redaction features for environment variable management.

mise