skills/crony/SKILL.md
Manage cron jobs with natural language scheduling. Use this skill when the user wants to schedule tasks to run later or recurring, manage scheduled jobs, view job logs, or run jobs on-demand. Supports both one-off and recurring schedules with natural language syntax like "in 5m", "every 1h", "every monday".
npx skillsauth add lirrensi/agent-cli-helpers cronyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Manage cron jobs with natural language scheduling and inspect computed upcoming run times.
crony --help
If not installed:
uv tool install "git+https://github.com/lirrensi/agent-sommelier"
crony add <name> <schedule> <command>
crony add <name> "<cron_expr>" <command> --cron
The --cron flag treats the schedule as a raw 5-field cron expression instead of natural language:
crony add myjob "*/5 * * * *" "python script.py" --cron
crony add nightly "0 2 * * *" "backup.sh" --cron
Working directory preservation: When a job is added, crony automatically captures the current working directory. When the OS scheduler runs the job, it cds to that directory first, so relative paths in commands work correctly regardless of where the scheduler executes.
You can still manually add cd anyway: cd /path/to && command.py
crony list
crony list --sync
crony list --json
crony list shows a Next Run column for one-off and recurring jobs. crony list --json includes a computed next_run field for each job.
crony rm <name>
crony run <name>
crony logs <name>
crony add backup "in 5m" "python --version"
crony add report "at 15:30" "python send_report.py"
crony add deploy "on 2026-03-10" "python deploy.py"
crony add ping "every 1h" "python --version"
crony add cleanup "every 24h" "python cleanup.py"
crony add weekly "every monday" "python weekly_report.py"
crony add weekday "every weekday" "python daily_check.py"
# Raw cron expression (bypasses natural language parser)
crony add nightly "0 2 * * *" "backup.sh" --cron
crony add every-5min "*/5 * * * *" "python check.py" --cron
in 5m, in 1h, in 2d - Relative one-offat 15:30, at "2026-03-10 10:00" - Absolute one-offevery 1h, every 30m, every 24h - Interval recurringevery monday, every weekday, every weekend - Day-based recurring# Health check every hour
crony add health "every 1h" "python --version"
# Daily backup
crony add backup "every 24h" "python backup.py"
# Weekly report
crony add report "every friday" "python generate_report.py"
# One-time reminder
crony add remind "in 30m" "python --version"
# Inspect upcoming run times
crony list
crony list --json
Jobs are registered with the native OS scheduler:
crontab — wraps command with cd /path && cmd via shlex.quote().bat wrapper in ~/.crony/scripts/ with cd /d "CWD"The working directory is captured at add time and stored in the cwd field of ~/.crony/jobs.json so relative paths in commands work reliably.
Job metadata is stored in ~/.crony/jobs.json for easy management.
data-ai
Portable SSH profile manager for agents. Run remote commands on saved hosts by friendly name instead of typing user@host -i key every time. Type less crap around your SSH commands.
development
Autonomous execution mode triggered by the word "engage". Use when the user has finished planning and wants the agent to execute autonomously without further questions until the workflow is fully complete. The agent must build, test, verify, and deliver proof of work — never exiting with an incomplete or unverified result. Trigger on: "engage", "go autonomous", "execute the plan", "run it", "make it happen", or any explicit signal to switch from planning mode into fully autonomous build-and-verify mode.
tools
Use this skill when you need to manage project tasks — create, update, complete, prioritize, filter, review, track dependencies, or find unblocked work. Trigger on: 'add a task', 'create task', 'show tasks', 'what's next', 'mark done', 'update task', 'task status', 'task history', 'next task', 'task inbox', 'list tasks', 'init tasks', 'task deps', 'ready tasks', 'blocked tasks', 'search tasks', 'tag-any', 'dependency graph'. Also use proactively when starting a new work session — check `tasks status` and `tasks ready` to orient yourself. This skill covers the project's static, file-based task system (persistent, in-repo history) with typed dependency tracking, ready queue, and priority management — NOT ephemeral runtime task tools.
tools
On-demand skill loading from a local skill registry. Trigger on: "skill store", "load skill", "find a skill", "list skills", "import skill", "skill-store", "browse skills", "search skills", or any request to fetch a skill that is NOT currently loaded in the active context. This skill is NOT for managing the already-loaded skills in your prompt. It is for accessing the much larger skill storage (~100s to 1000s) that you only bring into context when you need them. Think of it as a lazy loader: the skills here stay on disk until you explicitly call for them via CLI.