The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses Bash to execute local Python scripts (validate-entities.py and register-entity.py) for data validation and manifest updates. These scripts are located within the plugin's own directory and are used for internal data integrity rather than executing arbitrary user-supplied code.
[DATA_MODEL_VALIDATION]: The skill enforces a strict data model by requiring the AI to read a reference schema (data-model.md) and run a validator before committing any data to the portfolio manifest.
[VENDOR_RESOURCES]: The skill interacts with 'cogni-projects' portfolio structures and scripts, which are consistent with the author's namespace ('cogni-work'). These are legitimate internal tools for the skill's stated purpose.

projects-entities