Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added install.sh script for easier installation. - Updated SKILL.md with installation instructions, author, license, and metadata fields. - Streamlined documentation by removing detailed workflow and protocol sections. - No behavior changes to main scripts or logic.
What This Skill Does
A CLI-based task tracking system backed by SQLite. Handles the full task lifecycle: creation, heartbeat monitoring, completion, and recovery of stuck tasks. Consolidates task-queue-heartbeat, auto-track, and notification skills into one.
Replaces three separate skills with one unified system that persists state across restarts using a local SQLite database.
When to use it
- Tracking long-running agent jobs across sessions
- Recovering stuck or abandoned tasks automatically
- Checking daily task status from the terminal
- Managing task priority queues for automated workflows
- Logging completion notes for audit trails
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: track this request and notify me if it gets stuck
- 1Runs task-system.sh create with the request text
- 2Stores task in SQLite with pending status and default priority
- 3Calls task-system.sh heartbeat periodically to update last_updated timestamp
- 4Runs task-system.sh stuck to detect tasks that missed heartbeat intervals
- 5Marks task complete with task-system.sh complete and optional notes
Task record saved with timestamps, status transitions logged, stuck tasks surfaced for recovery