The Agent Skills Directory

[SAFE]: The skill is entirely markdown-based and serves as a set of instructions for the agent to provide methodology consulting. It contains no executable scripts or system-level interactions.
[NO_CODE]: There are no code files, configuration files, or external scripts associated with this skill.
[COMMAND_EXECUTION]: The skill does not invoke any shell commands or use any system tools beyond the agent's default conversational capabilities.
[DATA_EXFILTRATION]: No network calls or access to sensitive environment variables or files (e.g., .ssh, .aws) were detected.
[PROMPT_INJECTION]: The skill ingests user input via the $ARGUMENTS placeholder to provide tailored advice.
Ingestion points: User-provided text in the Input section of SKILL.md.
Boundary markers: None identified.
Capability inventory: No file system, network, or subprocess capabilities are present.
Sanitization: None identified.
Risk Assessment: The risk is negligible as the skill only outputs conversational text and does not perform any actions that could be hijacked.

consult