A high-performance TypeScript task queue for OpenClaw that orchestrates multi-agent workflows with priority scheduling and dependency management.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-task-queue
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-task-queue using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Agent Task Queue?
The Agent Task Queue skill provides a robust foundation for managing complex, multi-agent workflows within the OpenClaw ecosystem. It addresses the challenges of coordinating asynchronous tasks by offering features like priority queuing, delayed execution, and sophisticated dead-letter queue handling for failed operations. This implementation is a cornerstone for developers building reliable automation within the Openclaw Skills ecosystem.
By leveraging the bundled TypeScript runtime, developers can implement intricate task dependencies and parallel execution patterns. This skill ensures that your AI agents operate reliably under load, with built-in support for retries, timeouts, and persistent storage via SQLite or Redis, making it an essential component for high-scale agentic applications.
Agent Task Queue Use Cases
- Orchestrating complex workflows involving multiple specialized AI agents.
- Scheduling time-delayed tasks or recurring background operations for autonomous systems.
- Managing task dependencies where an agent output is required for the next step in a sequence.
- Implementing reliable retry logic and failure handling for external API integrations.
- Scaling agent workloads using distributed Redis-backed task processing across multiple nodes.
How Agent Task Queue Works
- Initialize the system by importing the TaskQueue and Scheduler components from the core library.
- Configure the preferred storage backend, selecting between InMemory for testing, SQLite for single-node persistence, or Redis for distributed environments.
- Register specific task handlers that define the logic for different agent actions and task types.
- Enqueue tasks with specific metadata including priority levels, execution timestamps, and logical dependencies.
- Trigger the scheduler to start polling the queue and executing tasks based on concurrency limits and priority.
- Monitor execution through integrated logs, metrics, and state snapshots provided by the queue manager.
Agent Task Queue Setup
To begin using this skill within your Openclaw Skills environment, install the necessary dependencies and initialize the runtime:
npm install
To verify the installation and run the internal validation suite to ensure storage and scheduling are configured correctly, execute:
npm run check
Ensure that your storage backend (like Redis or SQLite) is accessible if you are moving beyond the default in-memory storage for production use cases.
Agent Task Queue Data Schema & Taxonomy
The skill organizes data around task objects and their lifecycle states to ensure full traceability within Openclaw Skills. The schema includes:
| Property | Description |
|---|---|
taskId |
Unique identifier for the task instance |
priority |
Numerical weight for queue ordering |
runAt |
Timestamp for delayed execution or scheduling |
dependencies |
List of task IDs that must be completed before this task becomes runnable |
retryPolicy |
Configuration for max retries and backoff strategies |
status |
Current state (ready, running, completed, or dead_letter) |
Logs and metrics are automatically aggregated to provide real-time visibility into queue performance and agent throughput.
Agent Task Queue Advanced Features
- DAG (Directed Acyclic Graph) validation to prevent circular dependencies in complex agent workflows.
- Automated result propagation where dependency outputs are automatically injected into downstream task contexts.
- Concurrency control to strictly limit the number of parallel agent executions and manage resource consumption.
- AbortSignal integration for clean cancellation and timeout handling of long-running agent tasks.
- Pluggable storage architecture allowing seamless transitions from local development to production-grade Redis clusters.
SKILL.md
Loading
Related Openclaw Skills
Agent Memory Persistence
A robust SQLite-backed storage system for AI agents that provides long-term memory, metadata management, and semantic retrieval.
Agent Communication Hub
A high-performance communication layer providing direct messaging, pub/sub events, and persistent storage for autonomous agent interactions.
Feishu Image Message Skill
A comprehensive toolkit for automating image uploads, messaging, and visual analysis within the Feishu (Lark) communication platform.
Feishu FAQ Bot
A high-performance FAQ management tool for Feishu bots that builds searchable knowledge bases from Markdown files using fuzzy matching.
Agent Usage Tracker
A TypeScript-powered SQLite utility for real-time tracking of AI model token usage and automated budget enforcement.
Daily Hot Push
An intelligent news aggregation skill that filters and delivers the top 10 trending news stories from major Chinese platforms directly to your communication tools.
Featured*
