The Agent Skills Directory

[SAFE]: The skill is composed entirely of natural language instructions and structural templates for a decision-making framework. It does not include any executable scripts, shell commands, or binary files.
[SAFE]: The YAML frontmatter includes disable-model-invocation: true, which restricts the agent from calling external tools or other models, effectively eliminating the risk of tool-based attacks or unauthorized tool execution.
[SAFE]: No patterns associated with data exfiltration, credential harvesting, or prompt injection were found. The skill operates solely on user-provided text inputs within a safe reasoning context.

decision-framework