AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Cron Management

skill-omnigentx-jarvis-cron-management · by omnigentx

>

No reviews yet
0 installs
46 views
0.0% view→install

Install

$ agentstack add skill-omnigentx-jarvis-cron-management

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-omnigentx-jarvis-cron-management)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Cron Management? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Cron Management Skill

  • DO NOT read files, browse code, or run shell commands to "learn" the cron system.
  • DO NOT use readtextfile, execute, grep, or any tool other than the cron tools.
  • ONLY call directly: cron_create, cron_list, cron_update, cron_delete, get_current_time.
  • Violating this wastes tokens and slows the request.

You have 4 ready-to-call tools: cron_create, cron_list, cron_update, cron_delete. No discovery needed.

Cron expression rules (REQUIRED)

A cron expression has 5 fields: minute hour day_of_month month day_of_week.

Common examples

  • 0 9 * * * → every day at 9:00
  • 0 9 * * 1-5 → 9:00 Monday through Friday
  • */30 * * * * → every 30 minutes
  • 0 */4 * * * → every 4 hours
  • 0 7 27 4 * → April 27 at 7:00 every year
  • 0 15 31 3 * + one_shot=true → once on March 31 at 15:00

Calendar type (REQUIRED)

  • Solar (Gregorian) — DEFAULT for normal date/month references.
  • Lunar — use ONLY when the user explicitly references lunar concepts (1st-of-month, full-moon, Lunar New Year, lunar death anniversary, etc.).
  • 0 7 15 * * + calendar_type="lunar" → 15th of every lunar month
  • 0 6 1 * * + calendar_type="lunar" → 1st of every lunar month
  • 0 7 10 3 * + calendar_type="lunar" → 10/3 lunar

Exec mode (REQUIRED)

| User intent | Exec mode | Meaning | |---|---|---| | Plain reminder ("remind me") | reminder | Send a notification text to the user | | Action ("summarise / analyse / check / crawl / find") | agent_turn | An agent executes a task automatically |

  • exec_mode = "reminder"exec_payload is the reminder text. No exec_agent needed.
  • exec_mode = "agent_turn"exec_payload is the direct execution prompt, exec_agent is the agent name (REQUIRED). Valid agents:
  • jarvis — synthesis, analysis, complex queries
  • ResearchAgent — web search, news
  • FinanceAgent — stock / gold / crypto prices

⚠️ Writing execpayload for agentturn (IMPORTANT)

exec_payload is the prompt sent to the agent when the cron triggers — it must be a direct action prompt.

DO NOT copy the user's scheduling phrasing verbatim (e.g. "Every day at 7am, please..."). DO rewrite it as an action prompt:

| ❌ WRONG (scheduling text copied in) | ✅ RIGHT (action prompt) | |---|---| | "Every day at 7am, check the weather in HN" | "Check today's weather in Gia Lam, HN and send a notification" | | "Daily 8am summarise AI news" | "Summarise the day's notable AI news as bullet points" | | "Remind me every Saturday morning to log TAS" | (use execmode=reminder, not agentturn) |

Pause / resume

  • Pause: cron_update(job_id="...", status="paused")
  • Resume: cron_update(job_id="...", status="active")

Always confirm with the user

After creating a job, summarise back:

  • job name
  • schedule (explained in the user's language)
  • mode (reminder vs AI-executed)
  • next run time

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.