The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional content and configuration settings. It defines architectural and workflow principles for software development, such as breaking work into verifiable units and sequencing commits for clarity.
[NO_CODE]: There are no executable scripts, shell commands, or network operations included in the skill files. The configuration in agents/openai.yaml and the YAML frontmatter in SKILL.md are standard platform settings that do not introduce security risks.

principle-sequence-verifiable-units