Adversarial analysis to critique, fix.
Scanned 9/10/2026
Install to Claude Code
npx -y skills add luokai0/ai-agent-skills-by-luo-kai --skill oc-adversarial-prompting --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Oc Adversarial Prompting?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/luokai0-oc-adversarial-prompting)More formats (shields.io, HTML) on the badges page.
---
name: oc-adversarial-prompting
version: 1.0.0
description: Adversarial analysis to critique, fix.
author: luo-kai
tags: [adversarial-prompting, openclaw, community]
source: https://clawskills.sh/skills/adversarial-prompting
---
# Adversarial Prompting
## Overview
Adversarial analysis to critique, fix.
## Before Starting
1. What specific task do you need this skill for?
2. What inputs are available?
3. What is the expected output format?
## Usage
This skill integrates with the OpenClaw/ClawHub ecosystem.
Install via: `npx clawhub install adversarial-prompting`
## Core Functionality
Refer to the original skill documentation at: https://clawskills.sh/skills/adversarial-prompting
This skill enables: Adversarial analysis to critique, fix.
## Best Practices
- Always test in a sandbox environment first
- Check the skill's latest version before deploying
- Review the source documentation for advanced configuration
## Related Skills
- agent-installer
- clawhub-publisher
- openclaw-setup-expert
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.