The Agent Skills Directory

[NO_CODE] (SAFE): The documentation files (references/) contain benign instructional patterns and examples for LLM behavior.
[COMMAND_EXECUTION] (SAFE): The Python scripts (scripts/) perform local file system operations (reading, writing zip files) necessary for their stated purpose of packaging skills. They do not execute arbitrary shell commands.
[EXTERNAL_DOWNLOADS] (SAFE): No external downloads or network requests were detected in the scripts or documentation.
[CREDENTIALS_UNSAFE] (SAFE): No hardcoded credentials or sensitive environment variable access were found.
[REMOTE_CODE_EXECUTION] (SAFE): The scripts use yaml.safe_load() for parsing configuration, which prevents unsafe object instantiation. There is no use of eval(), exec(), or remote script execution.

skill-creator