self correcting skills

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

learn

01

toejough/engram

Skill Claude CodeCodex

Use after work begun with recall, or any work requiring more than one tool call or non-trivial thought. Use immediately for explicit save requests ("remember this", "save that", "note for next time"), and the moment a review, failing check, or user correction confirms a lesson; capture it before applying the fix. Also…

8 2d ago A 118 tokens original Apache-2.0

recall

02

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.

8 2d ago A 54 tokens original Apache-2.0

route

03

toejough/engram

Skill Claude CodeCodex

Use when you are about to dispatch a subagent and must decide its agent type, model, and effort level. Triggers on any delegation decision, and when you recognize a unit is too large for one focused agent and needs decomposition before dispatch.

8 2d ago A 51 tokens original Apache-2.0