The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local script scripts/validate_project.py to inspect the generated code. Analysis of the script shows it performs safe, read-only file operations using standard Python libraries to verify project structure and security markers.
[DATA_EXFILTRATION]: The workflow and validation script include explicit checks to prevent the accidental inclusion of sensitive files like .env or hardcoded credentials in the generated output.
[SAFE]: No obfuscation, unauthorized network access, or malicious prompt injection patterns were detected. The skill uses a structured interpretation phase to confirm user intent, which acts as a safeguard against accidental misinterpretation of complex instructions.

spec-to-repo