write-skills-demo

Use when creating new skills, editing existing skills, or verifying skills work before deployment

This skill is coherent for skill authors and testers, but review and use it carefully: 1) it explicitly instructs agents to check local skill directories and to use convincing, high-pressure scenarios — avoid running those scenarios against production systems or with access to real secrets; 2) the guidance encourages forceful language and persuasion techniques (authority/commitment) which are effective for compliance but can be coercive if misused; 3) run tests in an isolated/sandbox environment, verify no sensitive files or credentials are referenced, and limit the agent's filesystem/network permissions while validating skills.

Type: OpenClaw Skill Name: write-skills-demo Version: 1.0.0 The skill bundle, particularly `SKILL.md`, `persuasion-principles.md`, and `testing-skills-with-subagents.md`, describes a sophisticated methodology for influencing and controlling AI agent behavior. It explicitly teaches 'persuasion principles' (Authority, Commitment, Scarcity) to ensure agent compliance with instructions, 'bulletproofing skills against rationalization,' and creating 'pressure scenarios' to prevent agents from deviating. While framed as improving skill quality and agent adherence to best practices, these techniques represent powerful control mechanisms over an AI agent's decision-making, which are inherently risky capabilities that could be repurposed for malicious objectives by a different skill author.