The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to execute standard development commands necessary for scaffolding a Rails application, including Docker Compose orchestration, Rails CLI generators, and database migration management.
[EXTERNAL_DOWNLOADS]: The skill references official and well-known external resources, such as Ruby and PostgreSQL Docker images from Docker Hub and standard packages from the RubyGems and NPM registries. These references are used for legitimate environment setup and tooling.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) as it processes user-supplied JSON specifications to drive code generation.
Ingestion points: Specification data is ingested through the JSON file read in 'steps/01_check_specification.md'.
Boundary markers: The skill relies on structured schema validation and a multi-step workflow rather than explicit prompt delimiters.
Capability inventory: The agent is instructed to perform file system writes, execute shell commands, and run SQL migrations.
Sanitization: The skill contains specific guidance in 'steps/05_design_db_schema.md' and 'steps/09_implement_orm.md' to prevent SQL injection by advocating for the use of placeholders and parameterization.
[SAFE]: No evidence of malicious intent, data exfiltration, or obfuscation was found. The use of 'sudo' in the setup scripts is limited to legitimate file permission correction in the context of Docker-based development.

orchestrating-api-implementation