The Agent Skills Directory

[SAFE]: The skill is purely informational and instructional. It defines a persona for the AI to adopt when answering business and product questions.
[PROMPT_INJECTION]: No attempts to bypass safety filters, extract system prompts, or override agent constraints were detected. The instructions are focused on maintaining a specific character and philosophy.
[DATA_EXFILTRATION]: There is no code or instruction that accesses local files, environment variables, or credentials. No network operations are present.
[REMOTE_CODE_EXECUTION]: The skill does not perform any external downloads or execute remote scripts. The installation command mentioned in the README is a standard platform mechanism for adding the skill and is not executed by the skill itself at runtime.
[COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic context injections (!command) are present in any of the skill files.
[OBFUSCATION]: All content is provided in plain text. No base64 encoding, hidden characters, or homoglyph substitutions were found.

dinglei-perspective