视角修正 Skill(View Correction)

SkillAI & models

Correct the viewpoint first, then invoke the method — default checks, evidence validation, consequence questioning, and eight correction perspectives

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the 视角修正 Skill(View Correction) skill

What this skill tells your AI

The instructions your AI receives, as published by gmaxxxie/ai-native-product-agent-skills in skills/p12a-contemplation-view-correction/SKILL.md and read by ahel’s review.

适用场景

  • 团队对同一事实有截然不同的解读
  • 决策基于未经检验的默认假设
  • 需要从多个视角审视同一个问题

输入

字段说明
initial_view当前/主流的看法
supporting_evidence支持该看法的证据
underlying_assumptions隐含的默认假设

输出

  • 证据可信度评估
  • 假设检验结果
  • 修正后的多视角描述
  • 八种修正视角的应用记录

工作流程

  1. 默认检查:识别观点中的隐含前提(如"用户是理性的""增长是好的")
  2. 证据校验:区分事实/观点/推测,检验证据链的完整性
  3. 后果追问:如果这个看法成立,会导致什么行动?会产生什么结果?
  4. 八种修正:应用八种修正视角(反面看、整体看、动态看、关系看、代价看、边界看、历史看、他人看)

注意事项

  • 此 Skill 在调用任何具体方法之前执行
  • "修正看法"不是"和稀泥",而是让判断建立在更坚实的基础上
  • 八种修正视角是启发式工具,不是必须全部使用

Signals

GitHub stars
46
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
p12a-contemplation-view-correction
Source
github.com/gmaxxxie/ai-native-product-agent-skills