The Agent Skills Directory

[SAFE]: The skill is well-documented and follows best practices for AI agent skills. It includes clear boundaries, safety guidelines, and data handling principles.
[SAFE]: The screen_lists tool in scripts/entity_research.py fetches public sanctions lists from official government and international organization domains (US Treasury, UK government, and UN), which are well-known and trusted sources.
[SAFE]: The skill uses standard Python libraries (stdlib) for its bundled helpers and does not require third-party packages or remote code execution.
[SAFE]: The instructions explicitly warn against using the skill for automated actions, clearing/blocking entities, or compilation of sensitive personal data, adhering to privacy and regulatory guardrails.
[SAFE]: Data handling principles ensure that sensitive relationship context is not leaked to external search queries.

entity-research