The Agent Skills Directory

[PERSISTENCE]: The skill's core functionality involves modifying persistent system schedulers including crontab, OpenClaw cron, and Railway cron to maintain task execution across sessions.
[COMMAND_EXECUTION]: The skill generates and executes shell commands, specifically invoking the gbrain sync utility with flags such as --parallel and --workers to perform bulk synchronization tasks.
[INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing job configurations that may ingest untrusted data, creating a potential surface for indirect injection.
Ingestion points: Job definitions including user-provided names, cron expressions, and target skill paths referenced in SKILL.md.
Boundary markers: There are no explicit delimiters or "ignore instructions" warnings described to prevent the agent from executing instructions embedded within the referenced job skills.
Capability inventory: The skill utilizes put_page for file modification, crontab for persistence, and the gbrain CLI for task execution.
Sanitization: The skill lacks explicit sanitization or validation logic for job parameters before they are used in shell command construction or scheduling registration.

cron-scheduler