The Agent Skills Directory

[SAFE]: The skill is purely instructional and data-driven, providing a structured cognitive framework for an AI agent to emulate Warren Buffett's decision-making process.
[REMOTE_CODE_EXECUTION]: No remote scripts, package installations (beyond the skill's own installation command), or shell execution patterns were detected.
[DATA_EXFILTRATION]: The skill does not perform any network operations or access sensitive local files such as SSH keys or environment variables.
[OBFUSCATION]: All content is written in plain-text markdown (Chinese and English). No base64 encoding, zero-width characters, or homoglyph attacks were found.
[PROMPT_INJECTION]: The skill uses detailed roleplay instructions to maintain a persona, which is standard behavior for personality-driven skills and does not attempt to bypass core safety guidelines.
[DYNAMIC_CONTEXT_INJECTION]: The SKILL.md file does not use the dynamic context execution syntax (!command) to run shell commands at load time.

buffett-perspective