---
name: reflection-or-replay
description: Use when a user keeps replaying an event after the main facts and usable lesson are already known. Test whether another round is producing new information, a decision, or an action.
license: CC-BY-NC-SA-4.0
compatibility: Portable Agent Skills compatible. No local binaries or private CBT Cards data required.
metadata:
  author: "CBT Cards / MetalHatsCats"
  version: "1.0.0"
  homepage: "https://cbt-cards.github.io/skills/"
  source-id: "practice-reflection-or-replay"
---

# Reflection or Replay?

## Purpose

Use this skill for one bounded self-reflection task. It is general wellness material, not medical advice, diagnosis, treatment, emergency support, or a substitute for qualified professional care.

## Use when

- The main facts and any usable lesson are already identified.
- The loop is non-urgent.

## Do not use when

- Important information is still missing for accountability or a concrete decision.
- Stopping analysis would avoid a real task, repair, investigation, or safety action.

## Procedure

1. Ask what new fact, decision, or action the last round produced.
2. If there is new information, use it once.
3. If there is only repetition, summarize the lesson in one sentence and end the review deliberately.
4. Name the next concrete activity.

## Response contract

Return: New information? → Usable lesson → Next action. Do not use this skill to evade responsibility or necessary fact-finding.

Keep the response concrete and proportionate. Do not infer a disorder from the user's wording. Do not remove genuine safety measures, protective boundaries, accessibility aids, medication instructions, professional requirements, or legal/compliance controls.

## Source and review

- Source ID: `practice-reflection-or-replay`
- Reviewed CBT Cards practice: https://cbt-cards.github.io/practice/#practice-reflection-or-replay
- Marketplace record: https://cbt-cards.github.io/data/skill-marketplace.json
- Review authority: https://cbt-cards.github.io/data/toolkit-review.json
- License: CC BY-NC-SA 4.0

For a technique skill, the reviewed practice record is the authority for fit and `avoid_when`. For a metaphor skill, the toolkit review overlay must explicitly publish the source record for the `agent_skill` surface. If the authoritative source no longer supports this skill, return `no_match` rather than improvising.