
from claude-reflect1,051
Capture user corrections during sessions and manage a /reflect flow to apply learnings to CLAUDE.md for future behavior improvements.
Claude Reflect is a small self-learning system for Claude Code that captures user corrections and preference signals during sessions, queues them for review, and provides a manual /reflect command to apply vetted learnings to CLAUDE.md or project-specific CLAUDE files. It focuses on preserving human-in-the-loop oversight while making agent behavior incremental and maintainable.
Use when users provide corrections, say 'remember this', or when there's a pattern of repeated fixes. It's helpful during prolonged collaboration, onboarding project rules, or when you want to retain model-specific conventions across sessions.
Best suited for agents built on Claude Code or similar environments that support session hooks and manual command entry.
This skill has not been reviewed by our automated audit pipeline yet.