The Agent Skills Directory

[SAFE]: The skill instructions define a staff-level engineer persona focused on simplicity and minimalism. There are no patterns of prompt injection intended to bypass safety or exfiltrate data.
[SAFE]: The skill does not instruct the agent to perform network operations, access sensitive files, or execute external scripts. Mentions of libraries or functions (e.g., fetch, axios, lodash) are used purely as illustrative examples for coding style.
[SAFE]: No obfuscation, privilege escalation, or persistence mechanisms are present. The content is entirely transparent and focused on behavioral alignment.

moyu-ja