Detects when the user is correcting, reworking, pointing out mistakes, or requesting long-term notes to be preserved; launches a human-confirmation loop. Supports both `mistake` and `note` entry types, writing to project-level and/or global-level mistakebook / notebook, and synchronously refreshes cached project memory and global memory. If the same case is rejected twice or more by the user, or the user says 'use the most effective method you have seen to handle this' or inputs '/ascended', automatically escalates to Ascended Mode — comprehensively retrieving project/global mistakes, notes, memory cache, and current knowledge base before proceeding. Common triggers: 'you are wrong', 'this is not right', 'redo this', 'let me correct you', 'still not fixed', 'write to notebook', 'note this item', '/mistakebook', '/ascended'.
Codex skill entrypoint for Mistakebook Ascended Mode. Use this chip-style skill when you want the strongest retrieval workflow without expanding a long prompt into the composer.
Codex skill entrypoint for Mistakebook note mode. Use this chip-style skill when you want to organize and archive a long-term note without expanding a prompt body into the composer.
Codex skill entrypoint for Mistakebook scholar preflight. Use this chip-style skill on a fresh normal task when you want lightweight retrieval without expanding a long prompt into the composer.
识别用户正在纠正你、要求返工、指出你重复犯错，或要求记录长期注意事项的场景，进入带人工确认的闭环。统一支持 `mistake` 与 `note` 两类条目，写入项目级和/或全局级错题集 / 记事本，并同步刷新缓存式记忆。如果同一个案例被用户否定两次以上，或用户说“你需要根据你见过最有效的方法来处理这个问题”或输入“/ascended”，自动升级到飞升模式（Ascended Mode），全面检索项目级/全局级错题、记事本、记忆和当前知识库后再处理。