prompt-engineer

Expert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, an...

This skill appears to be a legitimate prompt-engineering playbook, but it contains one potentially dangerous rule: it requires the agent to always display the full prompt text in a single block. That can accidentally reveal system prompts, chain-of-thought content, or any secrets embedded in prompts. Before installing or enabling this skill, consider: (1) remove or modify the 'ALWAYS display the complete prompt' instruction or restrict it to non-sensitive examples; (2) ensure system prompts and secrets are never injected into prompts the skill will display; (3) add or supply the referenced resources/implementation-playbook.md or remove the reference; (4) test the skill in a safe sandbox to verify it does not leak confidential data. If you cannot control prompt contents or user-supplied inputs, treat this skill as higher risk and avoid enabling it for agents with access to sensitive data.

Type: OpenClaw Skill Name: mupeng-prompt-engineer Version: 1.0.0 The skill bundle is benign. The `SKILL.md` provides detailed instructions for an AI agent to act as an expert prompt engineer, focusing on prompt design, optimization, and safety. All instructions, including the structured output format and behavioral traits, are aligned with the stated purpose. The only file system interaction instruction is to 'open `resources/implementation-playbook.md`' for detailed examples, which refers to an internal resource within the skill bundle itself and is a common, non-malicious pattern for skills to access their own documentation.