async-job-orchestration

Orchestrate long-running asynchronous LLM jobs with durable state tracking.

10|Updated Mar 31, 2026

Search Tags:#parallel execution #LLM #async job #durable results #cache awareness

Ready to run

npx skills add https://github.com/verivus-oss/llm-cli-gateway --skill async-job-orchestration

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: async-job-orchestration
Source: https://github.com/verivus-oss/llm-cli-gateway/tree/main/.agents/skills/async-job-orchestration
Command: npx skills add https://github.com/verivus-oss/llm-cli-gateway --skill async-job-orchestration

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of managing long-running asynchronous jobs with large language models (LLMs), ensuring durable results and efficient execution of parallel tasks.

Core Features & Use Cases

Async Job Management: Handle tasks requiring more than 2 minutes, parallel jobs, and non-blocking execution.
Cache Awareness: Supports cache-aware promptParts and cache-state:// resources for efficient caching.
Job Lifecycle: Tracks job states, handles polling, and provides durable results that survive gateway restarts.
Use Case: Ideal for implementing review workflows, long-running analysis, or parallel processing tasks that benefit from asynchronous execution.

Quick Start

Dispatch a long-running analysis job using the claude_request_async command.

Frequently Asked Questions about async-job-orchestration

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

FAQPage Schema

How do I manage long-running async LLM jobs that take more than 2 minutes?▼

To manage long-running async LLM jobs over 2 minutes, you can dispatch non-blocking tasks using the `claude_request_async` command, which handles parallel execution and tracks job states efficiently. This ensures durable results that survive gateway restarts.

What is cache awareness in async LLM job orchestration?▼

Cache awareness in async LLM job orchestration utilizes cache-aware `promptParts` and `cache-state://` resources to optimize caching. This mechanism reduces redundant processing during parallel executions and maintains efficient prompt state tracking.

How do I track job state for parallel LLM executions across gateway restarts?▼

To track job state for parallel LLM executions across gateway restarts, the orchestration system provides durable job state tracking. This feature monitors job lifecycles, handles polling, and ensures results persist without data loss during interruptions.

Can I run multiple non-blocking LLM analysis tasks in parallel?▼

Yes, you can run multiple non-blocking LLM analysis tasks in parallel. The orchestration system supports parallel execution of asynchronous jobs, making it ideal for implementing review workflows and long-running analysis tasks simultaneously.

When should I use asynchronous execution for large language model tasks?▼

You should use asynchronous execution for large language model tasks when operations exceed 2 minutes, require parallel processing, or need non-blocking execution. This approach is ideal for long-running analysis and review workflows requiring durable results.