菜单
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
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。
基于 SOC 职业分类
Use when a Claude Code session should delegate a well-scoped task to Codex CLI for isolated execution, then summarize Codex report. 适用于在 Claude Code 中让 Codex 执行已明确范围的任务并回报结果。
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
A relentless interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go. Combines grilling with domain-modeling.
Audit Claude Code configuration for malicious hooks, MCP servers, and suspicious commands. Use this skill whenever the user clones a new project, installs a skill/plugin, configures MCP servers, or asks to check security. Also trigger when the user mentions "audit", "security check", "malicious", "hooks", or "is this safe".
| name | grill-me |
| description | Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me". |
| install-targets | claude |
Interview the user relentlessly about every aspect of their plan until you reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one.
Use the AskUserQuestion tool for every question you ask. Never pose questions as plain text in your response — always use the multiple-choice popup so the user can quickly select an answer or type a custom one.
Ask one question at a time. Wait for the user's answer before moving to the next question. This keeps the conversation focused and prevents overwhelm.
For each question, provide 2–4 concrete multiple-choice options representing the most likely answers or directions. Think about what the user would realistically choose — generic options like "Yes" / "No" aren't helpful unless the question is genuinely binary. The user always has the "Other" field available to write something custom.
