The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a provided Python script (scripts/query_opentargets.py) using the uv tool. This script acts as a controlled interface for querying the external database and processing the resulting data.
[EXTERNAL_DOWNLOADS]: The Python script performs network operations to retrieve genomic and pharmacological evidence from the Open Targets Platform GraphQL API (api.platform.opentargets.org). This is the primary intended function of the skill and targets a reputable scientific resource.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API, creating a surface for potential indirect prompt injection if the retrieved content contains malicious instructions.
Ingestion points: Data is fetched from the Open Targets API in scripts/query_opentargets.py and written to a local JSON file.
Boundary markers: Output is stored in structured JSON format, but the skill does not provide specific delimiters or instructions for the agent to ignore potentially adversarial content within the fetched data.
Capability inventory: The skill includes network access to the specified API and file writing capabilities to the path provided via the --output argument.
Sanitization: The script uses standard JSON serialization but does not perform specialized sanitization or filtering of the natural language strings returned by the database.

opentargets-database