The Agent Skills Directory

[SAFE]: The skill is primarily educational, providing architectural guidance and templates for agent creation within the Claude Code ecosystem.
[SAFE]: The validation script scripts/validate-agent.sh uses standard Unix utilities (grep, sed, awk) to perform static analysis on local markdown files. It does not perform network operations or execute untrusted code.
[SAFE]: The documentation mentions advanced configuration options like bypassPermissions as part of the official agent specification, but does not instruct the agent to use these for malicious purposes.

agent-development