The Agent Skills Directory

[COMMAND_EXECUTION]: Executes shell commands to manage the software development lifecycle. \n
Evidence: Runs git commands for versioning and uv sync to manage project dependencies.\n- [DATA_EXFILTRATION]: Performs network operations to synchronize code with a remote repository. \n
Evidence: Uses git push to upload local changes and tags to the 'origin' remote, which is the primary intended function of the skill.\n- [PROMPT_INJECTION]: Processes git commit history, which constitutes an ingestion point for untrusted data that could influence agent behavior. \n
Ingestion points: Reads commit messages via git log <latest-tag>..HEAD --oneline (SKILL.md).\n
Boundary markers: No explicit delimiters or ignore instructions are used around the logs.\n
Capability inventory: Shell command execution (git, uv), file modification (pyproject.toml), and network pushes (git push).\n
Sanitization: The skill includes a mandatory human-in-the-loop checkpoint, instructing the agent to present the summary to the user and wait for confirmation before any destructive or network actions.

release