self-correcting skills

11 tagged self-correcting, measured the same way as everything else here.

Browse within: LLM 11agent 11

recall

01

toejough/engram

Skill Claude CodeCodex

Use after any user request that might entail more than a single tool call or anything more than quick, shallow thinking. This surfaces relevant memories that are VITAL to recall for a good user experience and a greater chance at first-pass success for the user's request.

not rated 8 changed 16d ago A SkillSpector: warn 54 tokens original Apache-2.0

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: