The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references an external GitHub repository (github.com/LLMQuant/skills) for settlement methods. This is an official resource from the skill author (llmquant).
[COMMAND_EXECUTION]: Instructs the agent to use the hermes cron create command to schedule the playbook. This is a platform-native persistence mechanism for automated tasks.
[SAFE]: The skill processes untrusted data from market events and news cross-checks, representing a potential surface for indirect prompt injection.
Ingestion points: polymarket_event_browse and news_browse tool outputs (SKILL.md).
Boundary markers: None provided to distinguish external data from system instructions.
Capability inventory: Scheduled command execution via hermes CLI.
Sanitization: No explicit validation of external data strings before processing.

polymarket-watch