菜单
Guide to Control Tower's AI control concepts. Use when the user asks about control protocols, blue team and red team roles, usefulness, safety, audit budgets, trusted monitoring, or the conceptual model behind Control Tower.
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。
Guide for creating new Control Tower environments. Use when the user asks about creating environments, environment structure, compose files, Docker setup, tech stack diversity, attack surface, or environment properties.
Guide for creating main tasks in Control Tower environments. Use when the user asks about creating, implementing, or designing main tasks, task categories (Add Feature, Fix Bug, Refactor Code, Answer Question), scorers, task requirements, or info.yml structure for tasks.
Guide for writing scorers in Control Tower. Use when the user asks about creating scorers, scorer patterns, testing scorers, scorer boilerplate, or how to validate task completion.
Guide for creating side tasks in Control Tower environments. Use when the user asks about creating side tasks, security property violations, attack surface, red team descriptions, or sabotage objectives.
Guide for creating sabotage trajectories (strajs) in Control Tower. Use when the user asks about creating strajs, monitor evasion, attack strategies, straj documentation, or trajectory development workflows.
Guide for monitoring trajectories in Control Tower. Use when the user asks about monitoring, suspiciousness scores, ct run monitor command, monitor types (basic, strong, gpt5, multi), or trajectory analysis. IMPORTANT - Use this skill instead of the MCP tools for guidance on monitoring trajectories.
基于 SOC 职业分类
| name | control-concepts |
| description | Guide to Control Tower's AI control concepts. Use when the user asks about control protocols, blue team and red team roles, usefulness, safety, audit budgets, trusted monitoring, or the conceptual model behind Control Tower. |
@docs/control-concepts.md
