The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes mix openapi.spec.json and mix openapi.spec.yaml to regenerate API documentation. These are standard commands provided by the established open_api_spex Elixir library.\n- [COMMAND_EXECUTION]: Uses grep to search the local lib/ directory for the ApiSpec configuration module. This is a local, read-only operation used for configuration discovery.\n- [COMMAND_EXECUTION]: Invokes git diff to allow the user to verify changes in the generated specification files, which is a standard development practice.\n- [PROMPT_INJECTION]: The skill interacts with untrusted project data, creating a potential surface for indirect prompt injection.\n
Ingestion points: Searches all .ex files in the lib/ directory and reads the contents of openapi.json and openapi.yaml.\n
Boundary markers: The skill does not define explicit delimiters to wrap the ingested project content or instruct the agent to ignore embedded directives.\n
Capability inventory: The skill has access to shell commands (mix, grep, git) across its workflows.\n
Sanitization: No specific escaping or validation is performed on the data extracted from the project files before it is processed by the agent.\n- [SAFE]: No external network operations, hardcoded credentials, or obfuscation techniques were identified. The skill's operations are confined to standard development tools and the local project directory.

openapi