一键导入
agent-infra-standalone-audit
Use when the user asks for a quality audit of recent changes, or before committing to check for LLM-specific code quality problems
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。
菜单
Use when the user asks for a quality audit of recent changes, or before committing to check for LLM-specific code quality problems
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 the user asks for a structured explanation of a system, module, or concept in the codebase
Use when the user asks for a bug audit of a project or component
Use when designing, implementing, or improving program flow to minimize complexity
Use when analyzing variable and data flow for debugging, auditing, or new package development
Use when the user asks for a commit message draft, or when work is complete and changes should be committed
Use when evaluating whether package architecture results in calls to all its elements
| name | agent-infra-standalone-audit |
| description | Use when the user asks for a quality audit of recent changes, or before committing to check for LLM-specific code quality problems |
| argument-hint | [description of what the changes are trying to accomplish] |
Run a standalone quality audit on the current diff using the agent-standalone-quality-audit agent.
If $ARGUMENTS is provided, pass it as the stated goals. If not, pass "infer" so the agent determines intent from the diff and recent commits.
Launch the agent with the Agent tool (subagent_type: general-purpose) and include the goals in the prompt. When the agent returns, display the report path and a concise summary of the findings to the user.