Menu
Trigger an Action Llama agent run and report the results. Use when running, triggering, or testing an agent.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Action Llama reference — agent authoring, CLI operations, and debugging. Loaded automatically when working with Action Llama projects.
Diagnose why an Action Llama agent is failing and suggest fixes. Use when debugging, troubleshooting, or investigating agent errors.
Run an Action Llama agent, analyze output, and improve its instructions. Repeats up to 3 cycles. Use when iterating on, improving, or refining an agent.
Create a new Action Llama agent with SKILL.md and config.toml. Use when creating, adding, or scaffolding a new agent.
Show a rich overview of the Action Llama project status including scheduler state and agent details. Use when checking status, health, or state of the project.
| name | run |
| description | Trigger an Action Llama agent run and report the results. Use when running, triggering, or testing an agent. |
| argument-hint | [agent-name] |
Trigger an agent run and report the results.
Call al_status to check if the scheduler is running.
al_start to start it and wait for it to become ready.Ask the user which agent to run (or use $ARGUMENTS if provided).
al_agents to list available agents.Call al_run with the agent name.
Wait a few seconds, then call al_logs with the agent name, lines: 200, to fetch the run output.
Summarize the result: