The Agent Skills Directory

[SAFE]: The skill provides educational content on prompt engineering for LLMs, image, and video models. All examples use the belt CLI tool, which is the platform's standard interface for interacting with inference services. The external links and installation instructions point to trusted resources from the skill's infrastructure (inference.sh) and GitHub repositories belonging to the same ecosystem. No instances of obfuscation, remote code execution from unknown sources, credential exfiltration, or persistence mechanisms were detected. The prompt examples themselves are standard teaching aids for role-playing, chain-of-thought, and few-shot prompting techniques without any adversarial intent.

prompt-engineering