The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like grep, find, and jq to analyze the project structure and dependencies in the local directory. It also executes docker buildx build and docker-compose to validate the generated Dockerfile and ensure the resulting container is operational.
[EXTERNAL_DOWNLOADS]: The skill includes logic to download and execute official installation scripts for development tools such as Rust (sh.rustup.rs) and Bun (bun.sh). These downloads are directed to well-known, official service domains and are used to set up the build environment within the container.
[DATA_EXFILTRATION]: The skill uses curl to perform health checks against localhost endpoints. This is done to verify that the application starts correctly after being containerized. No evidence was found of data being transmitted to external or unauthorized domains.
[PROMPT_INJECTION]: The skill uses clear, instructional language for the agent's workflow. While it uses terms like "IMPORTANT" and "CRITICAL" to emphasize certain steps, it does not attempt to bypass safety filters or override system-level instructions.
[DYNAMIC_EXECUTION]: The skill dynamically generates Dockerfiles, .dockerignore files, and entrypoint scripts. It also iteratively modifies the Dockerfile if build failures occur. This behavior is central to the skill's primary purpose of automated project containerization.

dockerfile-skill