The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown files. There are no executable scripts or binaries included in the skill package itself.
[COMMAND_EXECUTION]: The skill provides examples of using the bun runtime for local development tasks such as project scaffolding, package installation, and script validation. These are standard developer operations and do not target sensitive system files or unauthorized remote servers.
[PROMPT_INJECTION]: The skill describes a process for generating agent instructions from user input. While this creates a data ingestion surface, the templates provided do not include any patterns intended to bypass AI safety filters or override system-level instructions.

create-skill