The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It instructs the agent to read and analyze local project files such as package.json, configuration files (next.config.js, svelte.config.js, etc.), and database schemas (prisma/schema.prisma, drizzle.config.ts) to determine implementation details. \n
Ingestion points: Project configuration files and dependency manifests in the local file system. \n
Boundary markers: No explicit delimiters or warnings are provided to the agent to disregard instructions potentially embedded within these processed files. \n
Capability inventory: The skill allows the agent to execute shell commands via package managers and specialized CLI tools, and to write authentication logic and UI components to the project. \n
Sanitization: No explicit sanitization or validation logic is defined for the content extracted from project files before it is used to influence the agent's implementation strategy.\n- [COMMAND_EXECUTION]: The skill recommends the use of CLI tools for environment setup and database management. Specifically, it guides the user to run npx @better-auth/cli@latest migrate and npx @better-auth/cli@latest generate to sync authentication schemas with the database.\n- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the better-auth ecosystem from the npm registry and references official documentation and example repositories hosted on better-auth.com and GitHub to provide code samples and implementation guidance.

create-auth