The Agent Skills Directory

[SAFE]: The skill's logic is entirely instructional and conversational, focusing on educational coaching techniques like diagnosis, staged planning, and active practice exercises. No executable scripts (Python, JavaScript, Shell) are included in the skill package.
[SAFE]: There are no network operations, external downloads, or remote code execution patterns. The installation instructions in the README are standard for the platform and reference the author's own repository.
[SAFE]: The skill does not access sensitive files, environment variables, or credentials. It operates solely within the context of the user dialogue.
[SAFE]: No obfuscation techniques, hidden commands, or privilege escalation patterns were found. The skill includes explicit guardrails to prevent providing authoritative instruction in high-risk domains.

study