Menu
深度推理分析 - 使用 Codex 结构化推理、证据检索和可选只读 child agent 处理复杂问题。
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
AI-native code annotation protocol that encodes intent, risk, dependencies, constraints, and test expectations in machine-parseable comments.
Professional Codex-native multi-agent code review with confidence scoring
架构规划专家 - 使用 Codex 本地上下文、仓库证据和只读 child agent 进行大型系统架构设计与规划。
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
Imported from everything-codex command checkpoint
Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.
| name | thinkdeep |
| description | 深度推理分析 - 使用 Codex 结构化推理、证据检索和可选只读 child agent 处理复杂问题。 |
| auto_invoke | true |
| tags | ["thinkdeep","reasoning","codex-native","analysis"] |
| version | 0.2.0 |
| source | fork |
| checksum | cc09198458e40858784ec0f9625ebd1449295af2143195153dffc0b262d82841 |
| updated_at | "2026-05-29T03:50:00.000Z" |
| layer | research |
用于复杂决策、战略分析、多假设推理和高不确定性问题。默认在当前 Codex 会话内完成推理，并结合本地证据、命令验证和可选 child agent；不调用外部模型 CLI。
手动触发：
使用 thinkdeep 分析：<复杂问题>
适用条件：
不适用时，直接给简短结论或使用更具体的 skill。
输出：
按问题类型读取本地或外部证据：
rg、rg --files、相关测试和配置至少列出 2-4 个候选解释或方案：
| Hypothesis / Option | Evidence For | Evidence Against | Verification | Confidence |
需要独立视角时：
spawn_agent(agent_type="explorer", message="<explore evidence for/against options>")
spawn_agent(agent_type="reviewer", message="<challenge assumptions and risks>")
wait_agent
close_agent
给出：
## ThinkDeep Analysis
### Problem
[问题和成功标准]
### Known Facts
- [事实 + 来源]
### Options
| Option | Pros | Cons | Risk | Confidence |
### Recommendation
[推荐方案]
### Verification Plan
1. [step] -> verify: [check]
### Open Questions
[仍需用户或外部状态确认的问题]
如果没有足够证据，不要编造结论。明确列出缺口，并给出可执行的取证步骤。