Use when activity is high but requirements, blockers, tests, and deliverables remain unchanged across repeated edit, search, test, review, or planning cycles.
Scanned 9/6/2026
Install to Claude Code
npx -y skills add ihabkhaled/AI-Psychiatry --skill livelock-recovery --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Livelock Recovery?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ihabkhaled-livelock-recovery)More formats (shields.io, HTML) on the badges page.
---
name: livelock-recovery
description: Use when activity is high but requirements, blockers, tests, and deliverables remain unchanged across repeated edit, search, test, review, or planning cycles.
---
# Livelock Recovery
## Core principle
Stop repeated activity, identify the unchanged outcome, change strategy materially, and reduce the search space.
## Procedure
1. Freeze the repeating action.
2. Compare recent actions semantically.
3. Name the outcome that did not change.
4. Remove speculative branches and invalid assumptions.
5. Choose a new hypothesis, evidence source, isolation, or layer.
6. Reduce scope, retry once, then escalate or block if still unchanged.
## Required output
Repeated cycle, unchanged metric, new strategy, reduced scope, and retry result.
## Limits
Reset after 4 stalled cycles or 3 same-strategy attempts.
## Common mistakes
Do not make recovery generate more hypotheses or perform a fourth equivalent attempt.
## Stop condition
Stop when measurable progress resumes or an exact blocker is proven.
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 communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.