Schedule management with staggering, quiet hours, and wake-up override. Validates schedules, prevents collisions, and gates delivery during quiet hours.
73%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
Fix and improve this skill with Tessl
tessl review fix ./skills/cron-scheduler/SKILL.mdThe skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill asks the agent to register persistent cron entries with the host scheduler (crontab, Railway, OpenClaw), which changes machine state, but these are user-level jobs that need no sudo, create no accounts, and do not touch system service files or SSH config, so it only weakly matches the flagged categories.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow runs `gbrain sync --all` and `gbrain sources git-reconcile`, which fast-forward and ingest commits from the user's configured git remotes into the brain. Those remotes are user-chosen and could be public, so outsider-authored content could reach the brain without the agent selecting it, but outsiders cannot force delivery.
garrytan/gbrain
f4d1866
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.