The Agent Skills Directory

[SAFE]: The skill follows security best practices by implementing a mandatory 'User Review Gate' (Phase 6) that requires explicit approval before performing network-facing operations such as creating a Pull Request via the GitHub CLI.\n- [COMMAND_EXECUTION]: The skill utilizes common developer tools including git, go, npm, and pytest. These tools are used for repository analysis and pre-flight validation (Phase 3), which aligns with the skill's stated purpose.\n- [DATA_EXPOSURE]: The provided validation script (scripts/validate.sh) performs a check for a neighboring skill directory (../beads/SKILL.md). This is a legitimate structural check within a multi-skill project environment and does not involve sensitive user data.\n- [DATA_EXFILTRATION]: The skill uses the gh (GitHub CLI) to submit data to GitHub. This is a well-known service, and the data transfer is triggered only after the user has reviewed and approved the generated PR body.

pr-prep