客观中立度量化技能。量化评估输出的客观中立度(0-100分)。评估维度:事实准确率(40%)、立场偏倚度(30%)、证据充分度(20%)、逻辑严谨度(10%)。基于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-objectivity --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Metago Objectivity?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/metago-ai-metago-objectivity-6e04b4e3)More formats (shields.io, HTML) on the badges page.
---
name: "metago-objectivity"
description: "客观中立度量化技能。量化评估输出的客观中立度(0-100分)。评估维度:事实准确率(40%)、立场偏倚度(30%)、证据充分度(20%)、逻辑严谨度(10%)。基于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:
- "评估客观度"
- "检测立场偏倚"
- "量化客观中立"
- "事实准确率评估"
- "偏见检测分析"
---
# 客观中立度量化(metago-objectivity)
## 描述
量化评估输出的客观中立度(0-100分)。评估维度:事实准确率(40%)、立场偏倚度(30%)、证据充分度(20%)、逻辑严谨度(10%)。基于D38绝对客观中立原则。
## 触发条件
用户请求客观度评估时自动激活。输出前校验时自动触发(确保客观性达标)。
## 核心流程
1. 接收待评估内容
2. 事实准确率评估(权重40%)
3. 立场偏倚度评估(权重30%)
4. 证据充分度评估(权重20%)
5. 逻辑严谨度评估(权重10%)
6. 计算综合客观中立度得分
7. 输出评估结果
## 输出格式
返回结构化JSON,包含:
- 总评分(0-100)
- 各维度得分
- 偏倚点列表
- 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)、metago-objectivity技能定义(229-233, 395-418))
> 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:客观性是批判分析的维度之一
- 与 `metago-decision-lock` 协同:输出前客观性校验
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', ...