Setup & Installation
openclaw skills install @moodykong/queue-task
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install queue-task
What This Skill Does
Manages durable, resumable batch job queues using append-only JSONL state files. Tracks progress, failures, and locks to prevent concurrent runs across sessions. Works within task-father task folder conventions.
Unlike in-memory job queues, all state persists to disk so jobs survive crashes and can be resumed without reprocessing completed items.
When to use it
- Resuming a large data import after an interrupted run
- Processing thousands of records in small batches without data loss
- Preventing duplicate processing with idempotency keys
- Scheduling recurring batch jobs with cron expressions
- Inspecting batch progress and clearing stale locks mid-job
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: set up a resumable batch job to process 500 records with a batch size of 20
AGENT
- 1Creates config.env with BATCH_SIZE=20, WORKSPACE_DIR, TASKS_DIR, and other required keys
- 2Runs `python3 scripts/queue_task.py init <slug>` to create queue.jsonl, progress.json, and related state files
- 3Verifies setup with `python3 scripts/queue_task.py status <slug>`
- 4Generates worker template via `python3 scripts/queue_task.py print-supervisor-template`
OUTPUT
Queue initialized and ready; worker template printed for the user to fill in batch processing logic