菜单
Activate comprehensive exploration mode. Use when user says 'deep research' or when a task requires thorough investigation of both internal codebase and external sources before proceeding.
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
Activate codebase exploration mode. Use when user says 'explore codebase' or 'explore the codebase', or when comprehensive codebase mapping is needed before making changes.
Activate code review mode via Oracle agent. Use when user says 'review', 'self-review', or 'code review', or after completing significant implementations. Surfaces critical issues, security concerns, and regressions.
Activate maximum multi-agent coordination mode. Use when user says 'ultrawork' or 'ulw', or when a task requires aggressive parallel research across multiple agents.
| name | deep-research |
| description | Activate comprehensive exploration mode. Use when user says 'deep research' or when a task requires thorough investigation of both internal codebase and external sources before proceeding. |
DEEP RESEARCH MODE — Comprehensive exploration requested.
Required actions:
Research pattern (all Agent calls in ONE message):
// All run in background automatically — fire and continue
Agent(subagent_type: "explorer", description: "Find implementations", prompt: "...")
Agent(subagent_type: "explorer", description: "Find related tests", prompt: "...")
Agent(subagent_type: "librarian", description: "Find official docs", prompt: "...")
Agent(subagent_type: "librarian", description: "Find OSS examples", prompt: "...")
// When all agents complete -> retrieve, synthesize, then act
Now execute deep research for: "$ARGUMENTS"
Fire at least 3-4 agents in parallel covering both internal codebase exploration and external documentation/examples. Synthesize all findings before taking any action.