The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and YAML configuration files. There are no scripts (Python, JavaScript, shell) or executable binaries included in the skill folder.
[SAFE]: All external references and URLs point to well-known research repositories (arXiv), official blogs (DeepMind, OpenAI, Meta, Epoch AI), and established documentation sites. These are used strictly for academic and engineering reference.
[SAFE]: No sensitive file paths, credentials, or environment variables are accessed or requested. The skill operates as a static reference for model sizing calculations.
[SAFE]: The worked examples provided in SKILL.md are mathematical demonstrations for educational purposes and do not involve dynamic code generation or command execution.
[SAFE]: There are no signs of prompt injection, obfuscation, or persistence mechanisms. The metadata in the YAML frontmatter and agents/openai.yaml is consistent with the stated purpose of the skill.

ai-scaling-laws