反事实推演技能。推演'如果...会怎样'的假设情景。识别当前状态的关键变量,设定假设条件,推演不同选择导致的不同结果,量化结果差异,给出最优建议。
Scanned 9/3/2026
Install to Claude Code
npx -y skills add metago-ai/metagolifeform --skill metago-whatif --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Metago Whatif?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/metago-ai-metago-whatif-metagolifeform)More formats (shields.io, HTML) on the badges page.
---
name: "metago-whatif"
description: "反事实推演技能。推演'如果...会怎样'的假设情景。识别当前状态的关键变量,设定假设条件,推演不同选择导致的不同结果,量化结果差异,给出最优建议。"
version: "1.0.0"
author: "MetaGO"
category: "数据分析"
platforms: ["cursor","claude-code","codex","trae","codebuddy","qoder","zcode","workbuddy","qclaw","ima"]
trigger:
- "如果...会怎样"
- "反事实推演"
- "假设情景分析"
- "What If 推演"
- "情景模拟推演"
---
# 反事实推演(metago-whatif)
## 描述
推演"如果...会怎样"的假设情景。识别当前状态的关键变量,设定假设条件,推演不同选择导致的不同结果,量化结果差异,给出最优建议。
## 触发条件
用户请求反事实推演时自动激活。方案评估时自动激活(提供替代方案分析)。
## 核心流程
1. 识别当前状态的关键变量
2. 设定假设条件("如果X不同,会怎样")
3. 推演不同选择导致的不同结果
4. 量化结果差异
5. 给出最优建议
## 输出格式
返回结构化JSON,包含:
- 假设条件列表
- 各假设下的推演结果
- 结果差异量化
- 最优建议
## 根源文档
`元构全息智能引擎.txt`(metago-whatif技能定义(217-220, 353-370)、元进化五阶段(140-149))
> 注:完整蓝本未随公开仓库发布,以上为出处留存备查;本技能正文已自包含全部操作定义,运行时无需读取蓝本。
## 与其他技能的协同
- 与 `metago-critique` 协同:推演结果接受批判性分析
- 与 `metago-decision-eval` 协同:推演结果用于决策评估
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...