菜单
Starts a new playground session and returns its ID. Use when you need to spin up a sandbox environment for testing or debugging.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Debugs an existing challenge by starting it, inspecting tasks, troubleshooting over SSH, fixing source files, and restarting. Use when a challenge's tasks are failing or hanging.
Gets detailed status and output of a specific examiner task on a playground. Use to debug why a task is failing.
Lists all examiner tasks (init and regular) for a playground. Use to check the status of challenge/tutorial tasks.
Executes a command on a playground VM via SSH. Use when you need to run commands on a playground for testing, debugging, or verification.
Applies a scripted solution to a running challenge (single- or multi-VM) and verifies every non-helper task completes. Use to validate a .solution.sh / .solution-NN.sh end-to-end.
Starts a challenge playground session. Use when you need to launch a challenge for testing or solving.
基于 SOC 职业分类
| name | start-playground |
| description | Starts a new playground session and returns its ID. Use when you need to spin up a sandbox environment for testing or debugging. |
| argument-hint | <playground-name> |
Start a new playground session for playground $0.
Run the following command:
labctl playground start $0 --quiet --skip-wait-init
The --quiet flag makes the command print only the playground ID.
The --skip-wait-init flag avoids blocking indefinitely waiting for init tasks to complete
(useful because init tasks may fail during debugging).
Capture and report the returned playground ID - it is needed for all subsequent playground operations (SSH, running commands, checking tasks).
After starting, use the list-running-playgrounds skill or labctl playground list
to verify the playground is running.