The Agent Skills Directory

[COMMAND_EXECUTION]: The script examples/learn_chart_examples.py utilizes subprocess.run to invoke an internal CLI (graph_memory.agent_cli). This implementation follows security best practices by passing arguments as a list rather than a single string with shell=True, effectively preventing shell injection vulnerabilities.
[SAFE]: The primary functionality in create_architecture.py involves communicating with a local server (localhost:3001) via HTTP PUT requests. This is consistent with the skill's purpose as a local visualization tool for developers.
[SAFE]: The skill implements a security-conscious 'Mutation Authorization Gate' that requires a human-authored JSON file (--execution-gate) to permit architecture modifications, ensuring human-in-the-loop control for sensitive operations.
[SAFE]: Pipeline definitions are parsed using yaml.safe_load(), which protects against YAML-based code execution attacks.

create-architecture