菜单
Force-loads the team orchestration policy into the current session. Use when Cursor has not read the orchestration policy or it is not active. Main session only — subagents must not load this.
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
Force-loads the team orchestration policy into the current session. Use when Claude has not read the orchestration policy or it is not active. Main session only — subagents must not load this.
Research the reference codebases for an idea/solution, then optionally apply it to this repo. Usage: /ref-idea <question>. Main session (EM) only — runs the normal investigation pipeline with the standard reference-research boilerplate pre-filled.
Feature status report: what we currently do for <feature>, what is missing, what is planned, and past decisions. Usage: /status-of <feature>. Main session (EM) only — runs explain mode with a status-report contract. Often used before /ref-idea.
Research the reference codebases for an idea/solution, then optionally apply it to this repo. Usage: /ref-idea <question>. Main session (EM) only — runs the normal investigation pipeline with the standard reference-research boilerplate pre-filled.
Feature status report: what we currently do for <feature>, what is missing, what is planned, and past decisions. Usage: /status-of <feature>. Main session (EM) only — runs explain mode with a status-report contract. Often used before /ref-idea.
| name | load-policy |
| description | Force-loads the team orchestration policy into the current session. Use when Cursor has not read the orchestration policy or it is not active. Main session only — subagents must not load this. |
Read and apply the orchestration policy and agent prompts now:
@.cursor/instructions/team-orchestrator-policy.md @.cursor/instructions/agent-prompts.md
Confirm to the user: "Policy loaded. Acting as Engineer Manager."
Progress tracking: the EM registers pipeline steps with TodoWrite. Only technical-architect, implementer, test-writer, and release-manager keep their own internal checklists — other subagents report results only.
