The Agent Skills Directory

[SAFE]: The skill functions as a developer tool assistant for the uv package manager. All demonstrated workflows (initialization, dependency addition, script execution) are consistent with the documented purpose and use standard industry practices for Python development.
[COMMAND_EXECUTION]: The skill uses the bash tool to execute uv commands based on user input in SKILL.md. This is the primary intended functionality of the skill, enabling automated environment setup and dependency management.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted instructions from $ARGUMENTS and using them to execute shell commands via the bash tool.
Ingestion points: $ARGUMENTS variable in SKILL.md.
Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the processed data.
Capability inventory: The skill has access to Bash, Write, Edit, Glob, and Grep tools as defined in the YAML frontmatter of SKILL.md.
Sanitization: Absent; the skill does not perform validation or escaping on the user-provided arguments before command construction.

uv-expert