The Agent Skills Directory

[SAFE]: The skill consists of instructional markdown and YAML frontmatter meant to guide the agent through authoring other skills. It does not perform any functional operations, script executions, or network requests.
[SAFE]: File path references (e.g., ~/.claude/skills/) and tool mentions (e.g., gh, pnpm) are used strictly in a descriptive context for documentation purposes and are not part of any executable command sequences.
[SAFE]: No obfuscation, prompt injection, or data exfiltration patterns were detected in the instructions or examples provided.

create-skill