The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes multiple local shell commands using git to inspect repository state and create branches.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from $ARGUMENTS and local git state to derive branch names used in shell commands. ● Ingestion points: User-supplied $ARGUMENTS and output from git diff or git status (SKILL.md). ● Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded instructions within the interpolated data. ● Capability inventory: The skill has the capability to execute shell commands via git checkout -b <branch-name>. ● Sanitization: Instructions include a requirement to generate names in "kebab-case, ASCII-only", providing a prompt-level constraint against malicious formatting.
[SAFE]: The skill references official naming standards from Sentry's public documentation, a well-known service.

create-branch