Break a failed implementation loop by tracing attempts, identifying the real blocker, and proposing a materially different direction before further changes. Use when repeated fixes or investigations are not converging.
Scanned 9/9/2026
Install to Claude Code
Skills Directorynpx -y skills add btseytlin/ultrapack --skill step-back --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Step Back?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/btseytlin-step-back)More formats (shields.io, HTML) on the badges page.
---
name: step-back
description: Break a failed implementation loop by tracing attempts, identifying the real blocker, and proposing a materially different direction before further changes. Use when repeated fixes or investigations are not converging.
---
# Circuit breaker
Stop the current approach. Do not make another fix until the user confirms a new direction.
1. State the user-facing goal in one sentence.
2. List the last three to five attempts and what failed in each.
3. Name the common root issue in one sentence: an invalid assumption, unsupported capability, architectural constraint, or needless complexity.
4. Propose a genuinely different approach, why it avoids the blocker, and its risks or trade-offs.
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!
