批判性分析技能。对任何输入进行L1-L5分级批判性分析,检测逻辑漏洞、认知偏差、事实错误、论证不充分、概念混淆。基于D45批判分级原则和D38绝对客观中立原则。
Scanned 9/3/2026
Install to Claude Code
npx -y skills add metago-ai/metagolifeform --skill metago-critique --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Metago Critique?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/metago-ai-metago-critique-e7673dda)More formats (shields.io, HTML) on the badges page.
---
name: "metago-critique"
description: "批判性分析技能。对任何输入进行L1-L5分级批判性分析,检测逻辑漏洞、认知偏差、事实错误、论证不充分、概念混淆。基于D45批判分级原则和D38绝对客观中立原则。"
version: "1.0.0"
author: "MetaGO"
category: "数据分析"
platforms: ["cursor","claude-code","codex","trae","codebuddy","qoder","zcode","workbuddy","qclaw","ima"]
trigger:
- "批判性分析一下"
- "找出逻辑漏洞"
- "检测认知偏差"
- "验证论证充分性"
- "检查概念混淆"
---
# 批判性分析(metago-critique)
## 描述
对任何输入进行L1-L5分级批判性分析,检测逻辑漏洞、认知偏差、事实错误、论证不充分、概念混淆。基于D45批判分级原则和D38绝对客观中立原则。
## 触发条件
用户请求批判分析时自动激活。重大决策输出前强制触发(与决策锁协同)。
## 核心流程
1. 接收输入内容
2. 按L1-L5分级进行批判性分析:
- L1:逻辑漏洞检测
- L2:认知偏差检测
- L3:事实错误检测
- L4:论证充分性检测
- L5:概念混淆检测
3. 输出结构化JSON结果
4. 附评估依据和改进建议
## 输出格式
返回结构化JSON,包含:
- 总评分(0-100)
- 各维度得分(L1-L5)
- 判定结论
- 改进建议
## 根源文档
`元构全息智能引擎.txt`(D38绝对客观中立原则(80)、D45批判分级原则(87)、metago-critique技能定义(199-289))
> 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:决策锁通过后触发批判性分析
- 与 `metago-objectivity` 协同:批判分析包含客观性维度
- 与 `metago-fact-check` 协同:L3事实错误检测联动事实核查
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', ...