The Agent Skills Directory

[SAFE]: The skill uses the Bash tool to execute the 'gh issue list' command, which is a standard operation for development-focused agents and is limited to its intended purpose of codebase investigation.
[SAFE]: No obfuscation, data exfiltration patterns, or attempts to access sensitive system files or credentials were found in the skill or its instructions.
[SAFE]: The skill includes explicit checkpoints (AskUserQuestion) to validate the problem and design with the user, ensuring that actions remain under human oversight.
[SAFE]: Although the skill ingests user input and codebase data, it does not perform unsafe interpolation into execution environments; the use of sub-agents for approach comparison is a standard reasoning technique and does not introduce additional security risk.

forge-brainstorm