The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to perform diagnostics, such as checking file counts, validating git worktrees, and checking running processes. These are used strictly for local health checks.
[EXTERNAL_DOWNLOADS]: The skill checks for the presence of external tools like agent-browser and portless via local commands (command -v) to provide recommendations, but it does not perform unauthorized remote code execution.
[DYNAMIC_CONTEXT_INJECTION]: The skill uses the ! syntax (e.g., ! bash scripts/check-plugin-health.sh) to inject real-time diagnostic data into its instructions at load time. This is a legitimate use of the platform's dynamic context feature for health reporting.
[SAFE]: No malicious patterns, prompt injections, or data exfiltration attempts were detected. The skill follows best practices by providing machine-readable outputs and remediation suggestions for found issues.

doctor