The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands through npx skills to interact with the agent skills ecosystem, including finding, adding, checking, and updating skills.
[EXTERNAL_DOWNLOADS]: The skill facilitates downloading and installing remote content from external repositories (such as GitHub) via the npx skills add command. It identifies well-known sources like Vercel Labs for these downloads.
[DYNAMIC_EXECUTION]: The core functionality of the skill is to dynamically extend the agent's capabilities at runtime by installing new modules or 'skills'.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill ingests external data in the form of search results from the npx skills find command into the agent's context.
Boundary markers: There are no explicit delimiters defined in the instructions for how the agent should process search results before presenting them to the user.
Capability inventory: The skill has the ability to execute shell commands (npx) and modify the agent's environment by adding new skills.
Sanitization: The instructions do not specify any sanitization or validation of the search results returned by the external registry.

find-skills