From claude-reflect
Reminds the user to run /reflect so queued corrections get written into their CLAUDE.md memory. Use when the user finishes a work unit, corrects you in a way worth persisting, says "remember this", or when context is about to compact with learnings pending. Capturing corrections is the hook's job, not yours — this skill is only the nudge to process them.
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-reflect:claude-reflectThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Capture is automatic: a `UserPromptSubmit` hook detects corrections and queues
Capture is automatic: a UserPromptSubmit hook detects corrections and queues
them to ~/.claude/learnings-queue.json. You do not capture anything.
Your one job here is the nudge: notice when the queue is worth processing and
remind the user to run /reflect. The /reflect command owns the rest (review,
routing, memory tiers) — point to it, don't restate it.
Keep it one line, and let the user decide — surface the nudge, don't nag.
npx claudepluginhub caioniehues/claude-reflectGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Implements work from a spec or tickets using TDD at agreed seams, with regular typechecking and test runs, followed by code review.