메뉴
Action Llama reference — agent authoring, CLI operations, and debugging. Loaded automatically when working with Action Llama projects.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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.
Trigger an Action Llama agent run and report the results. Use when running, triggering, or testing an 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 | al |
| description | Action Llama reference — agent authoring, CLI operations, and debugging. Loaded automatically when working with Action Llama projects. |
| user-invocable | false |
Action Llama (al) is a CLI tool for running LLM agents as scripts, triggered by cron schedules and webhooks.
Load the relevant supporting file based on what you need:
agents/<name>/ containing SKILL.md (portable instructions) and config.toml (runtime config)SKILL.md + optional Dockerfile) that can be shared and installedconfig.toml (committed) → .env.toml (gitignored) → environment file (machine-level)~/.action-llama/credentials/<type>/<instance>/<field>al mcp serve) exposes tools: al_run, al_start, al_stop, al_status, al_agents, al_logs, al_pause, al_resume, al_kill