run-once

Official

Ad-hoc agent task execution on demand.

Authorrunbear-io
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Manually dispatch an ad-hoc debugging task to aweek agents. The task follows the exact same execution path as a heartbeat tick, including per-agent lock handling, per-agent .env loading, and a full activity/execution log, but does not affect the weekly plan.

Core Features & Use Cases

  • Deterministic ad-hoc runs that validate agent behavior without altering the weekly schedule.
  • End-to-end execution trace including per-agent environment, lock status, and comprehensive activity logs for debugging.

Quick Start

Invoke this skill to dispatch a single ad-hoc task to a chosen agent, providing a prompt, and review the resulting execution log.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: run-once
Download link: https://github.com/runbear-io/aweek/archive/main.zip#run-once

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.