The Agent Skills Directory

[COMMAND_EXECUTION]: The skill generates and runs shell commands using the sports-skills CLI. These commands are constructed dynamically based on user-provided parameters such as team names, player names, and event dates.
[EXTERNAL_DOWNLOADS]: During setup, the skill prompts for the installation of the sports-skills package from PyPI or the author's official GitHub repository (github.com/machina-sports/sports-skills.git). As these are vendor-owned resources, they are treated as standard operational dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill fetches external sports data, news headlines, and play-by-play descriptions which are then interpolated into article templates.
Ingestion points: Data retrieved from external CLI modules described in SKILL.md and references/api-reference.md, including news and live match updates.
Boundary markers: The skill uses narrative templates defined in references/article-templates.md to structure its output, providing a fixed format for the ingested data.
Capability inventory: The skill can execute CLI commands and install Python packages via pip.
Sanitization: There is no explicit sanitization or validation logic described for the external data before it is processed by the agent, relying on the agent's default processing capabilities.

sports-reporter