{"skill":{"slug":"self-correction","displayName":"self-correction","summary":"模型自我检查与纠错技能。当用户表达反对意见或指出错误时触发，如\"不对\"、\"你回答错了\"、\"不是这样\"、\"重新理解\"、\"等等\"、\"我说的不是这个意思\"等表达。用于重新分析和优化用户原始意图，而非修改上一轮回答。","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":114,"installsAllTime":0,"installsCurrent":0,"stars":1,"versions":1},"createdAt":1775378036499,"updatedAt":1775378207545},"latestVersion":{"version":"1.0.0","createdAt":1775378036499,"changelog":"self-correction 1.0.0\n\n- Initial release providing model self-check and self-correction capability.\n- Detects user denials, objections, or correction cues in Chinese and triggers a re-analysis of the original user intent.\n- Explicitly avoids editing or apologizing for previous answers; instead, focuses on understanding and re-optimizing the user’s original prompt.\n- Offers structured output: self-check alert, re-understood requirements, problem point analysis, and a new answer.\n- Includes extensive detection templates, typical scenarios, and a checklist to ensure outputs are focused, concise, and non-repetitive.","license":"MIT-0"},"metadata":null,"owner":{"handle":"hauxu","userId":"s17afsr671sw9hgfcw9adcfbcd84981y","displayName":"华胥","image":"https://avatars.githubusercontent.com/u/95280092?v=4"},"moderation":null}