Extract durable, non-obvious lessons from the current dialogue and route them to project guidance, memory, documentation, or the active task conclusion. Use when the user asks to reflect on a session or preserve learnings.
Scanned 9/9/2026
Install to Claude Code
Skills Directorynpx -y skills add btseytlin/ultrapack --skill reflect --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Reflect?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/btseytlin-reflect)More formats (shields.io, HTML) on the badges page.
---
name: reflect
description: Extract durable, non-obvious lessons from the current dialogue and route them to project guidance, memory, documentation, or the active task conclusion. Use when the user asks to reflect on a session or preserve learnings.
---
# Reflect
Use this as the Codex and Pi equivalent of `/up:reflect`.
1. Identify non-obvious user corrections, discovered conventions, external-system details, and decisions the code does not explain. Discard one-off debugging facts and anything already documented.
2. Route each remaining lesson to the right home: `CLAUDE.md` for durable repository guidance, memory for cross-session personal context, project docs for domain knowledge, or the task conclusion for task-specific discoveries.
3. Write concise actionable entries: what the rule is, why it matters when non-obvious, and when it applies. Do not duplicate a learning across destinations.
4. Show the user a proposed diff before committing changes to `CLAUDE.md`. Re-read every entry as a fresh agent would and tighten anything that still needs unstated context.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
