The Agent Skills Directory

[SAFE]: The skill consists of Markdown-based instructions and research documentation. No executable scripts, binaries, or hidden code are included in the package.
[SAFE]: The role-playing instructions in SKILL.md are standard persona-maintenance rules. They do not contain instructions to bypass safety guidelines, override ethical protocols, or extract system prompts.
[SAFE]: No sensitive data, hardcoded credentials, or commands targeting sensitive local file paths (e.g., .ssh, .env) were found in any of the files.
[SAFE]: The 'Agentic Protocol' describes using platform-provided tools like WebSearch to verify facts before responding. It does not attempt to execute arbitrary shell commands or download/execute remote scripts.
[SAFE]: External URLs within the research documents point to well-known and reputable sites, including academic repositories, official news organizations (BBC, People.cn), and mainstream media platforms (YouTube, Bilibili).
[SAFE]: No obfuscation techniques (Base64-encoded commands, zero-width characters, or homoglyphs) were detected in the prompt text or metadata.

guodegang-perspective