Skill Claude Code needs its repo
Two-mode learning system — raw signal scanning before compaction, quality-gated consolidation at session end. Invoke with /learning-loop.
not rated 22
changed 8d ago B 29 tokens
original MIT
Claude Code skill for capturing and codifying learnings before session ends / context lost
This repository also configures its own agents. See what learning-loop-skill tells them →
Skill Claude Code needs its repo
Two-mode learning system — raw signal scanning before compaction, quality-gated consolidation at session end. Invoke with /learning-loop.