mistakebook

mistakebook is a Session review & learning skill for AI agents, published by Septemc in the MistakebookSkill repository on GitHub. Skillspace rates mistakebook C (73/100) and it passed the safety scan; the rating is based on static analysis only.

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'.

Grade

C

Quality

73 / 100

Safety

Passed

GitHub stars

20

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.