The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Python scripts to automate development workflows, including executing shell commands via subprocess.run and subprocess.Popen in eval-viewer/generate_review.py and scripts/run_eval.py. These are used for legitimate project management tasks like checking if a network port is in use and invoking the claude CLI for evaluation.
[EXTERNAL_DOWNLOADS]: The skill references official best practices from platform.claude.com and agentskills.io, and uses the anthropic Python SDK and claude CLI. These are well-known, trusted sources for AI development tools.
[SAFE]: Static analysis identified subprocess calls which are justified by the skill's primary purpose of automating CLI-based development and evaluation workflows.

skill-creator