决策评估技能。评估决策质量和潜在风险。评估维度:逻辑完整性、证据充分性、风险可控性、替代方案、可执行性。返回0-100分及各维度评分。
Scanned 9/3/2026
Install to Claude Code
npx -y skills add metago-ai/metagolifeform --skill metago-decision-eval --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Metago Decision Eval?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/metago-ai-metago-decision-eval-3ec6e354)More formats (shields.io, HTML) on the badges page.
---
name: "metago-decision-eval"
description: "决策评估技能。评估决策质量和潜在风险。评估维度:逻辑完整性、证据充分性、风险可控性、替代方案、可执行性。返回0-100分及各维度评分。"
version: "1.0.0"
author: "MetaGO"
category: "商业管理"
platforms: ["cursor","claude-code","codex","trae","codebuddy","qoder","zcode","workbuddy","qclaw","ima"]
trigger:
- "评估这个决策"
- "决策风险分析"
- "多维度打分"
- "方案对比评估"
- "决策质量检查"
---
# 决策评估(metago-decision-eval)
## 描述
评估决策质量和潜在风险。评估维度:逻辑完整性、证据充分性、风险可控性、替代方案、可执行性。返回0-100分及各维度评分。
## 触发条件
用户请求决策评估时自动激活。重大决策输出前自动触发(与决策锁协同)。
## 核心流程
1. 接收决策内容
2. 逻辑完整性评估
3. 证据充分性评估
4. 风险可控性评估
5. 替代方案分析
6. 可执行性评估
7. 输出综合评分与建议
## 输出格式
返回结构化JSON,包含:
- 总评分(0-100)
- 各维度评分
- 风险点列表
- 改进建议
## 根源文档
`元构全息智能引擎.txt`(metago-decision-eval技能定义(241-245, 454-482))
> 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-decision-lock` 协同:决策锁关卡1意图验证时调用
- 与 `metago-whatif` 协同:替代方案分析联动反事实推演
- 与 `metago-compliance` 协同:风险可控性包含合规维度
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', ...