Task management and tracking for agents. Use this skill whenever you need to create, update, claim, or retrieve tasks for agent workflows. This skill is triggered for any request involving task lists, task assignment, or status updates.
Task management and tracking skill for agent workflows. See SKILL.md for agent instructions.
| Script | Purpose |
|---|---|
| scripts/task_tracking.sh | Core task management CLI |
| scripts/run_task_loop.sh | Operator tool: drives agents through a task list sequentially |
| scripts/mock_agent.sh | Test agent used by run_task_loop.sh in mock mode |
Orchestrates sequential task execution by claiming tasks and delegating each to an agent CLI. Run from your project root (the directory containing .tasks/).
bash <path-to-skill>/scripts/run_task_loop.sh <list-id> [--agent <cli>] [-n <max-tasks>]
Arguments:
<list-id> — task list to processOptions:
--agent <cli> — agent to use: claude, copilot, or mock (default: claude)-n <max-tasks> — stop after this many successfully completed tasks (default: run until no pending tasks remain)What it does per task:
next --claim)update-status instructionscompletedcommit-messageLogs:
.tasks/logs/<list-id>/loop.log (also printed to stdout).tasks/logs/<list-id>/<task-id>_agent.logFor testing without a real agent:
bash <path-to-skill>/scripts/run_task_loop.sh my-list --agent mock -n 3
mock_agent.sh marks each task completed and dumps the full prompt it received to the log. Git operations are printed as dry-run only — nothing is staged or committed.
Environment variables:
MOCK_AGENT_FAIL=1 — mark tasks failed instead of completedMOCK_AGENT_DELAY=N — sleep N seconds before completing (simulates work)Example test commands:
# Happy path — 3 tasks completed
bash <path-to-skill>/scripts/run_task_loop.sh my-list --agent mock -n 3
# Run all pending tasks (no limit)
bash <path-to-skill>/scripts/run_task_loop.sh my-list --agent mock
# Simulate failure on first task
MOCK_AGENT_FAIL=1 bash <path-to-skill>/scripts/run_task_loop.sh my-list --agent mock -n 3
# Slow agent
MOCK_AGENT_DELAY=2 bash <path-to-skill>/scripts/run_task_loop.sh my-list --agent mock -n 3
Google Workspace CLI for Gmail, Calendar, Drive, Contacts, Sheets, and Docs.
Manage Apple Notes via the `memo` CLI on macOS (create, view, edit, delete, search, move, and export notes). Use when a user asks OpenClaw to add a note, list notes, search notes, or manage note folders.
Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
Use when you need to control Slack from OpenClaw via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.
Manage Apple Reminders via remindctl CLI (list, add, edit, complete, delete). Supports lists, date filters, and JSON/plain output.
Manage Trello boards, lists, and cards via the Trello REST API.
Category:productivity