automate

Solid

Set up a scheduled headless afk run that pushes a summary to Telegram. Use when the user wants to automate a recurring task via the afk daemon scheduler (cron) with push-notified results.

AI & Automation 45 stars 11 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 79/100

Stars 20%
55
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

Set up a recurring headless task using afk's **native** scheduler. Do NOT hand-roll launchd plists or shell scripts — afk has first-class scheduling: the `create_schedule` tool writes `~/.afk/config/schedules.json` entries that `afk daemon` runs on cron. Dispatch two sub-agents in parallel: 1. **Scout** — call `list_schedules` and inspect `~/.afk/config/schedules.json` for existing or overlapping jobs, run `afk service status` to see whether the daemon is installed as a launchd service and running, confirm Telegram is configured (`TELEGRAM_BOT_TOKEN` + `AFK_TELEGRAM_ALLOWED_CHAT_IDS`), and scan the target project folder for conventions. Report conflicts, daemon/service state, and any missing prerequisite. 2. **Prompt designer** — draft the recurring task's `command` string: a self-contained prompt (or `/skill --flags` invocation) sent verbatim into a freshly spawned session each run. The daemon session starts cold, so encode all input context explicitly, and require the run to END by calling the `send_telegram` tool with a concise, push-ready summary. When both return: - If Telegram is unconfigured, stop and tell the user to run `/telegram-setup` first — `send_telegram` fails closed without `TELEGRAM_BOT_TOKEN` and `AFK_TELEGRAM_ALLOWED_CHAT_IDS`. - Create the job with the `create_schedule` tool: `name`, the designed `command`, the requested 5-field `cron`, `trigger: "cron"`, and `notifyOn: "failure"` as a crash safety-net (the per-run summary comes from the agent's own `se...

Details

Author
griffinwork40
Repository
griffinwork40/agent-afk
Created
1 months ago
Last Updated
today
Language
TypeScript
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category