The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes scripts/mcp-call.sh, a utility script that uses curl and jq to interact with the atypica.ai API. This script is a documented convenience tool for performing research operations.
[EXTERNAL_DOWNLOADS]: The skill communicates with https://atypica.ai/mcp/study for its primary functionality. This is the official API endpoint for the vendor's research service.
[SAFE]: The skill possesses a data ingestion surface for indirect instructions when retrieving content from the research API.
Ingestion points: External data enters the agent context via atypica_study_get_messages, atypica_study_get_report, and atypica_study_get_podcast as documented in SKILL.md and references/api-reference.md.
Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions within the retrieved research data.
Capability inventory: The skill utilizes network operations and shell execution (via mcp-call.sh) to manage research sessions and retrieve artifacts.
Sanitization: No specific sanitization or validation logic is defined for the content returned by the research tools.

atypica-research