The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local shell commands to verify the migration, including npx tsc --noEmit and npm test. It also provides a curl command targeting localhost:3000 to perform a smoke test on the new authentication endpoints, which is a standard practice for local development validation.\n- [EXTERNAL_DOWNLOADS]: The skill points users to the official documentation at better-auth.com and utilizes the library's official CLI via npx @better-auth/cli for schema generation. These references target the legitimate infrastructure of the 'better-auth' project.\n- [PROMPT_INJECTION]: As a migration tool, the skill naturally ingests existing project code to generate refactoring plans, which constitutes a surface for indirect prompt injection.\n
Ingestion points: The skill audits the existing authentication library configuration, database schema files, and seed data scripts to build a migration context (SKILL.md).\n
Boundary markers: No specific delimiters or instructions are used to separate user-provided code from the agent's internal instructions.\n
Capability inventory: The skill uses the /refactor-codebase tool to write files and executes local shell commands for project testing (SKILL.md).\n
Sanitization: The skill does not describe any specific sanitization or validation logic for the code it reads before processing it.\n- [SAFE]: The REFERENCE.md file follows secure practices for managing environment variables by using descriptive placeholders (e.g., BETTER_AUTH_SECRET=) and explicitly warning users to keep these values private, rather than hardcoding sensitive credentials.

migrate-to-better-auth