automation-recipes

Create event-driven automation routines with cron tasks and reaction workflows in the Ravi runtime.

6|2|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/filipexyz/ravi --skill automation-recipes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: automation-recipes
Source: https://github.com/filipexyz/ravi/tree/main/src/plugins/internal/ravi-system/skills/automation-recipes
Command: npx skills add https://github.com/filipexyz/ravi --skill automation-recipes

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the complexity of building reliable, long-lived agent automations that require state persistence, cron-based scheduling, and event-driven reactions without losing context or triggering unnecessary LLM calls.

Core Features & Use Cases

  • Operational Recipes: Provides standardized patterns for cron-based tasks, reaction-based approvals, and interactive UI flows.
  • State Management: Implements durable local storage patterns to ensure agent routines survive restarts and maintain idempotency.
  • Use Case: Use these recipes to build a system where a cron job identifies pending tasks, posts them for human approval via Slack reactions, and executes the final action only after a valid reaction is detected.

Quick Start

Use the automation-recipes skill to configure a new cron-based sentinel routine that monitors for approval candidates and handles reaction-based state updates.

Frequently Asked Questions about automation-recipes

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build durable, event-driven automation routines for AI agents?

To build event-driven automation routines, you use standardized recipes that implement cron-based tasks, reaction-based workflows, and interactive UI interactions while ensuring state persistence and idempotency. These recipes run within the Ravi runtime environment.

How do I maintain state persistence for cron-based agent workflows across restarts?

State persistence for cron-based workflows is maintained using durable local storage primitives integrated with the runtime's event bus. This ensures agent routines survive restarts, maintain idempotency, and preserve context without losing data or triggering unnecessary LLM calls.

What is the best way to trigger agent task execution via Slack reactions?

Triggering task execution via Slack reactions involves a cron job that identifies pending tasks and posts them for human approval. The final action executes only after a valid reaction is detected and processed through the event-driven state management system.

Does this automation recipe approach require integration with a specific event bus?

Yes, this approach requires integration with Ravi's internal event bus, local storage primitives, and shell-based execution environment. These components are necessary to facilitate durable state management and event-driven reactions properly.

How do I configure a cron-based sentinel routine to monitor for approval candidates?

Configuring a cron-based sentinel routine involves using the automation recipes to monitor for approval candidates and handle reaction-based state updates. This standardizes the creation of scheduled tasks within the event-driven runtime.

Why do my event-driven agent automations lose context or trigger duplicate LLM calls?

Event-driven agent automations lose context or trigger duplicate LLM calls when they lack durable local storage patterns and idempotency controls. Implementing standardized state management recipes ensures routines survive restarts and prevent unnecessary API requests.