The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill interfaces with Cloudflare's official Model Context Protocol (MCP) server at https://mcp.cloudflare.com/mcp to retrieve domain registration data and internet traffic insights. Cloudflare is a trusted organization and a well-known service provider.
[COMMAND_EXECUTION]: The instructions specify the execution of a bundled Python script, scripts/score_domains.py, which is used to rank domain candidates based on researched evidence. The script uses standard libraries and does not perform network operations or access sensitive local files.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from potentially untrusted external sources, such as search engine results and API responses.
Ingestion points: Search results (Step 4 of SKILL.md) and Cloudflare API data (Step 3 of SKILL.md) are loaded into the agent's context for evaluation.
Boundary markers: The skill does not provide specific instructions to the agent to treat external search data as untrusted or to ignore instructions embedded within it.
Capability inventory: The agent has the capability to execute local Python scripts and perform network searches via integrated tools.
Sanitization: The scripts/score_domains.py script implements basic sanitization by escaping markdown pipe characters in its output to maintain report formatting integrity.

domain-research