The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and JSON evaluation schemas. There is no executable code, automation scripts, or system-level configuration present.
[EXTERNAL_DOWNLOADS]: The skill includes several links to official Anthropic documentation on platform.claude.com. These are used for factual grounding of model capabilities and pricing, which aligns with the skill's stated purpose of educating on model routing.
[NO_CODE]: No indicators of remote code execution, privilege escalation, or persistence mechanisms were found. The skill does not perform any network operations, file system modifications, or package installations.

claude-opus