Agent skill
cron-scheduling
Create, list, and remove persistent scheduled tasks using cron expressions.
Install this agent skill to your Project
npx add-skill https://github.com/SawyerHood/middleman/tree/main/apps/backend/src/swarm/skills/builtins/cron-scheduling
SKILL.md
Cron Scheduling
Use this skill when the user asks to schedule, reschedule, or cancel reminders/tasks for later.
Before creating a schedule, confirm:
- exact schedule timing (cron expression),
- timezone (IANA, for example
America/Los_Angeles), - task message content.
If the request is ambiguous, ask a follow-up question before adding a schedule.
Commands
Use the embedded CLI. It talks to the backend schedule service and stores schedules in SQLite.
middleman schedule add \
--cron "0 9 * * 1-5" \
--message "Remind me about the daily standup" \
--description "Daily standup reminder" \
--timezone "America/Los_Angeles"
One-shot schedule (fires once at the next matching cron time):
middleman schedule add \
--cron "30 14 * * *" \
--message "Check deployment status" \
--description "One-time deployment check" \
--timezone "America/Los_Angeles" \
--one-shot
Remove a schedule:
middleman schedule remove \
"<schedule-id>"
List schedules:
middleman schedule list
Override manager context manually when needed:
middleman schedule list --manager "manager"
Output
All commands return JSON:
- Success:
{ "ok": true, ... } - Failure:
{ "ok": false, "error": "..." }
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
brave-search
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
memory
Update persistent swarm memory in ${SWARM_MEMORY_FILE} when the user explicitly asks to remember, update, or forget durable information.
image-generation
Generate images using Google Gemini (gemini-3-pro-image-preview). Requires GEMINI_API_KEY.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Didn't find tool you were looking for?