The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and behavioral instructions. It does not include any scripts, executable binaries, or configuration that grants the agent additional tool access.
[SAFE]: The SKILL.md file defines a meta-workflow for task discovery and engineering principles (e.g., surfacing assumptions, managing confusion, simplicity). These are benign and promote safe, collaborative development practices.
[SAFE]: The references/definition-of-done.md provides a standard quality checklist for engineering tasks. It is purely informational and contains no malicious patterns.
[SAFE]: All external references point to a well-known and reputable GitHub repository (addyosmani/agent-skills). These are provided for attribution and source verification purposes and do not involve runtime downloads or execution.

using-agent-skills