The Agent Skills Directory

[SAFE]: The skill is composed entirely of static text files (Markdown and YAML) providing cognitive frameworks and persona guidelines. It contains no executable scripts, binaries, or system commands.\n- [PROMPT_INJECTION]: Instructions define a specific educational persona based on Richard Feynman for teaching purposes. The guidelines focus on communication style and pedagogical methods and do not attempt to bypass safety guardrails or extract system-level prompts.\n- [DATA_EXFILTRATION]: No network operations, API calls, or sensitive file access patterns were detected. The skill operates strictly within the conversational text context.\n- [CREDENTIALS_UNSAFE]: No hardcoded secrets, API keys, private tokens, or sensitive configuration data were found in the skill repository.\n- [COMMAND_EXECUTION]: There are no shell commands, subprocess spawns, or platform-specific command execution patterns (such as dynamic context injection) in any of the files.

feynman-perspective